Decision coordinator
decision-coordinator v1Runs one marketing decision from the open question through to the recorded answer. It works out what the decision has to settle and by when, commissions the evidence from the agents that gather it, puts two or three candidate answers in front of the people who decide, convenes the room where the decision gets made, writes down what was agreed and who disagreed and why, hands the answer to the agents that will act on it, and sets the date the answer gets looked at again. This agent decides nothing itself, which is what makes the record it leaves worth trusting later.
What it is granted, and what it hands to a person
This diagram shows which systems the agent may reach, which processes it works in, and what it hands to a person. Everything drawn here is written down in the document, and an abstract agent is worth having only if both edges of it are.
Convenes the briefing that opens the decision, so every agent that owes evidence hears the same question and the same due date at once. Commissions collect-and-report for that evidence, and every line keeps the source and the agent it came from. Convenes the meeting where the decision is made, puts the candidate answers in front of the people who decide, and writes down the answer with the reasons behind it. Runs decide-and-announce afterwards, so every agent that has to act on the answer hears it at the same time and knows when it applies from. Requests the approval when the process names a signer for the decision. Answers roll-calls with which decisions are open, what each one is waiting on, and when each one is due.
What is in the package
25 skills and the systems they need, written to version 1.1.0 of the Agent Plugins standard. Nothing in these files names a product. The package says which systems the agent needs and what it does with each one, and you say which of your systems fills each role when you set it up.
# Where this abstract agent stops Does not decide anything. It runs the decision and named people make it, which is what keeps the answer theirs. Does not gather the evidence itself: the researcher agent finds what is true outside the organization, the analytics agent reads the organization's own numbers and reports them with their sources, and the forecaster agent says what a model predicts. Does not run a campaign, a launch or a published piece, which are the campaign-manager, launch-coordinator and content-manager agents, and those agents run work that has already been decided on. Does not hold the standards a decision changes, which is the standards-keeper agent, and it hands the agreed change to that agent to be versioned. Does not report how the department performed over a reporting period, which is the reporting-manager agent. Does not sign anything. ## What always goes to a person - a decision that cannot be made by its date, said on the day the math stops working, because moving the date or deciding on thinner evidence is a person's call - evidence that contradicts the answer the room is moving toward - this agent puts the contradiction in front of the room and never leaves it out of the record - a disagreement among the people who decide that the process's rounds will not settle - a request to change a recorded answer, or to leave a dissent out of it. This agent never edits a decision after it is recorded. A change goes in as a new version, and the version it replaces stays where it was. - a decision made outside the process it belongs to, so a person decides whether to record it or run it again
# The records this abstract agent must leave
This is the contract. An agent implementing `decision-coordinator`
leaves the following behind, on every run.
The decision written down as a question before any evidence is gathered:
what it has to settle, who decides it, what evidence it needs and from
which agent, and the date it is due. The evidence as it came in, each
line attributed to the agent and the source behind it. The candidate
answers, each written out with what it would cost and what it would rule
out. The answer at a version, naming who decided it, on what date, for
what reasons, and anyone who disagreed with what that person said. A
handover line for each agent that has to act on the answer, naming the
agent and what it was given. The review date, set at the moment the
answer is recorded.
An agent that leaves less than this does not implement
`decision-coordinator`, whatever else it does well.
# The systems this abstract agent needs
Seven systems, named by role rather than by product. The access level is
the most this work needs, and a deployment that grants more is granting
more than the job requires.
| Role | Access | What the access is for |
|---|---|---|
| the decision record | write | Each decision lands at a version with its answer, its reasons and its dissent. |
| the evidence store | read | What the gathering agents filed for this decision. |
| the marketing standards at their versions | read | |
| the plans and commitments the decision has to sit inside | read | |
| the meeting calendar | write | Cap: which meetings it may set without asking, set by the adopting organization. |
| the notification channel | write | The answer reaches every agent that acts on it. |
| the review schedule | write | The date each recorded answer comes back up. |
Whoever builds an agent from this plugin writes the `mcp.json` that
points these roles at their own systems. Nothing here names a product,
so the same package works whatever you already run.
{
"$schema": "https://agent-plugins.org/schemas/1.1.0/plugin.schema.json",
"name": "decision-coordinator",
"version": "1.0.0",
"description": "The decision-coordinator abstract agent. Runs one marketing decision from the open question through to the recorded answer.",
"author": {
"name": "AgentCatalog",
"url": "https://agentcatalog.com"
},
"homepage": "https://agentcatalog.com/abstract-agents/decision-coordinator",
"repository": "https://github.com/jeffrschneider/agentcatalog",
"license": "CC-BY-4.0",
"keywords": [
"abstract-agent",
"reference",
"marketing",
"annual-marketing-plan",
"brief-executive-leadership",
"develop-marketing-strategy",
"abstract"
],
"extensions": {
"com.agentcatalog.agent": {
"agent": "decision-coordinator",
"agentVersion": 1,
"department": "marketing",
"abstract": true,
"works": "Convenes the briefing that opens the decision, so every agent that owes evidence hears the same question and the same due date at once. Commissions collect-and-report for that evidence, and every line keeps the source and the agent it came from. Convenes the meeting where the decision is made, puts the candidate answers in front of the people who decide, and writes down the answer with the reasons behind it. Runs decide-and-announce afterwards, so every agent that has to act on the answer hears it at the same time and knows when it applies from. Requests the approval when the process names a signer for the decision. Answers roll-calls with which decisions are open, what each one is waiting on, and when each one is due.",
"servers": [
{
"name": "the decision record",
"role": "decision-record",
"access": "write",
"needs": "Each decision lands at a version with its answer, its reasons and its dissent."
},
{
"name": "the evidence store",
"role": "evidence-store",
"access": "read",
"needs": "What the gathering agents filed for this decision."
},
{
"name": "the marketing standards at their versions",
"role": "marketing-standards-at-their-versions",
"access": "read"
},
{
"name": "the plans and commitments the decision has to sit inside",
"role": "plans-and-commitments-the-decision-has-to-sit-inside",
"access": "read"
},
{
"name": "the meeting calendar",
"role": "meeting-calendar",
"access": "write",
"needs": "Cap: which meetings it may set without asking, set by the adopting organization."
},
{
"name": "the notification channel",
"role": "notification-channel",
"access": "write",
"needs": "The answer reaches every agent that acts on it."
},
{
"name": "the review schedule",
"role": "review-schedule",
"access": "write",
"needs": "The date each recorded answer comes back up."
}
],
"records": [
"The decision written down as a question before any evidence is gathered: what it has to settle, who decides it, what evidence it needs and from which agent, and the date it is due.",
"The evidence as it came in, each line attributed to the agent and the source behind it.",
"The candidate answers, each written out with what it would cost and what it would rule out.",
"The answer at a version, naming who decided it, on what date, for what reasons, and anyone who disagreed with what that person said.",
"A handover line for each agent that has to act on the answer, naming the agent and what it was given.",
"The review date, set at the moment the answer is recorded."
],
"escalates": [
"a decision that cannot be made by its date, said on the day the math stops working, because moving the date or deciding on thinner evidence is a person's call",
"evidence that contradicts the answer the room is moving toward - this agent puts the contradiction in front of the room and never leaves it out of the record",
"a disagreement among the people who decide that the process's rounds will not settle",
"a request to change a recorded answer, or to leave a dissent out of it. This agent never edits a decision after it is recorded. A change goes in as a new version, and the version it replaces stays where it was.",
"a decision made outside the process it belongs to, so a person decides whether to record it or run it again"
],
"not": [
"Does not decide anything.",
"It runs the decision and named people make it, which is what keeps the answer theirs.",
"Does not gather the evidence itself: the researcher agent finds what is true outside the organization, the analytics agent reads the organization's own numbers and reports them with their sources, and the forecaster agent says what a model predicts.",
"Does not run a campaign, a launch or a published piece, which are the campaign-manager, launch-coordinator and content-manager agents, and those agents run work that has already been decided on.",
"Does not hold the standards a decision changes, which is the standards-keeper agent, and it hands the agreed change to that agent to be versioned.",
"Does not report how the department performed over a reporting period, which is the reporting-manager agent.",
"Does not sign anything."
],
"processes": [
{
"process": "ref/mkt/annual-marketing-plan",
"activities": [
"Take in the Company Targets",
"Set the Goals for the Year",
"Collect the Candidate Initiatives",
"Check What the Department Can Carry",
"Choose the Initiatives",
"Allocate the Budget",
"Build the Calendar",
"Name What Will Be Measured",
"Publish the Plan",
"Brief the Department",
"Record What the Plan Rests On"
]
},
{
"process": "ref/mkt/approve-marketing-material",
"activities": [
"Take in the Submission",
"Name the Standards and the Signers",
"Check the Submission Is Complete",
"Gather the Findings into One List",
"Return the Failures to the Submitter",
"Record an Accepted Exception",
"Get the Signatures",
"Release the Cleared Version"
]
},
{
"process": "ref/mkt/attribution-model",
"activities": [
"Choose the Model",
"Decide What Happens to Published Reports",
"Set the Review Conditions"
]
},
{
"process": "ref/mkt/brand-health",
"activities": [
"Settle What the Wave Measures",
"Report Awareness, Perception and Preference"
]
},
{
"process": "ref/mkt/brand-identity",
"activities": [
"Choose the Identity",
"Record What Was Learned"
]
},
{
"process": "ref/mkt/brand-positioning",
"activities": [
"Take in the Change",
"Audit What the Company Says Now",
"Agree Who the Company Is For",
"Draft the Candidate Positions",
"Choose the Position",
"Write the Positioning and the Promise",
"Tell the Processes that Read It",
"Record What Was Learned"
]
},
{
"process": "ref/mkt/brand-refresh",
"activities": [
"Decide What Happens to Each Surface",
"Set the Switch Date and the Order"
]
},
{
"process": "ref/mkt/brand-voice",
"activities": [
"Take in the Approved Positioning",
"Brief the Makers",
"Build the Messaging Architecture",
"Tell the Processes that Read It",
"Record What Was Learned"
]
},
{
"process": "ref/mkt/brief-executive-leadership",
"activities": [
"Take in the Cycle",
"Read the Last Meeting's Record",
"Work out What Has to Be Decided",
"Settle Marketing's Position",
"Send the Pack Ahead",
"Deliver the Briefing",
"Record the Decisions",
"Answer What Was Left Open",
"Hand the Decisions On",
"Record What Was Learned"
]
},
{
"process": "ref/mkt/channel-program",
"activities": [
"Settle the Tiers and the Terms"
]
},
{
"process": "ref/mkt/competitive-battlecard",
"activities": [
"Settle What May Be Said"
]
},
{
"process": "ref/mkt/content-calendar",
"activities": [
"Take in the Period's Goals",
"Collect the Topic Candidates",
"Score the Candidates",
"Agree the Calendar",
"Brief the Department",
"Record What the Plan Rests On"
]
},
{
"process": "ref/mkt/customer-research",
"activities": [
"Deliver the Findings"
]
},
{
"process": "ref/mkt/develop-marketing-strategy",
"activities": [
"Take in the Objectives",
"Draft the Strategic Options",
"Check What Each Option Would Take",
"Check the Options against What Is Agreed",
"Choose Where to Play and How to Win",
"Write down the Agreed Strategy",
"Name What the Strategy Will Be Judged By",
"Hand the Strategy to the Work that Follows",
"Set the Review Conditions",
"Record What Was Learned"
]
},
{
"process": "ref/mkt/engage-marketing-agency",
"activities": [
"Take in the Gap",
"Choose the Route",
"Decide What Is Handed Over",
"Set the Selection Criteria",
"Choose the Agency",
"Record What Was Learned"
]
},
{
"process": "ref/mkt/ideal-customer-profile",
"activities": [
"Take in the Question",
"Draft the Candidate Profiles",
"Name the Qualifying Signals",
"Settle on One Profile",
"Write down the Agreed Profile",
"Hand over the Profile",
"Set the Review Conditions",
"Record What Was Learned"
]
},
{
"process": "ref/mkt/lead-scoring-model",
"activities": [
"Take in the Drift or the Signal",
"Choose the Model",
"Hand over the Model",
"Set the Review Conditions",
"Record What Was Learned"
]
},
{
"process": "ref/mkt/map-buyer-journey",
"activities": [
"Take in the Persona",
"Draft the Stages",
"Find the Gaps",
"Settle the Map",
"Write down the Agreed Map",
"Hand over the Map",
"Set the Review Conditions",
"Record What Was Learned"
]
},
{
"process": "ref/mkt/media-plan",
"activities": [
"Choose the Mix"
]
},
{
"process": "ref/mkt/name-product",
"activities": [
"Take in the Naming Request",
"Set the Naming Criteria",
"Generate the Candidate Names",
"Screen the Long List",
"Cut to a Shortlist",
"Choose the Name",
"Tell the Processes that Read It",
"Record What Was Learned"
]
},
{
"process": "ref/mkt/plan-marketing-capacity",
"activities": [
"Take in the Planning Trigger",
"List the Committed Work",
"Put the Options to the People Who Decide",
"Decide the Mix",
"Name the Gaps that Remain",
"Record What Was Learned"
]
},
{
"process": "ref/mkt/prioritize-initiatives",
"activities": [
"Open the Round",
"Weigh the Requests against the Goals",
"Rank the Requests",
"Choose What Gets Committed",
"Resource the Commitments",
"Settle What Gets Displaced",
"Record the Declines",
"Tell the Requesters",
"Hand over the Commitments",
"Record What the Round Rests On"
]
},
{
"process": "ref/mkt/product-positioning",
"activities": [
"Take in the Question",
"Read the Standards in Force",
"Name the Competing Choices",
"Draft the Candidate Positions",
"Choose the Position",
"Write the Messaging",
"Issue the Positioning at a Version",
"Set the Review Conditions",
"Record What Was Learned"
]
},
{
"process": "ref/mkt/quarterly-business-review",
"activities": [
"Set What the Review Covers",
"Name the Gaps Worth Acting On",
"Ask Each Area What It Would Change",
"Hold the Review",
"Reset the Commitments",
"Move the Money",
"Publish the Reset Commitments",
"Brief the Department",
"Record What the Review Rests On"
]
},
{
"process": "ref/mkt/reallocate-media-spend",
"activities": [
"Decide the Move",
"Record Why the Money Moved"
]
},
{
"process": "ref/mkt/segment-the-market",
"activities": [
"Take in the Question",
"Set the Market Boundary",
"Choose the Dividing Traits",
"Draw the Candidate Divisions",
"Settle on One Division",
"Rank the Segments",
"Write down the Agreed Segments",
"Hand over the Segments",
"Set the Review Conditions",
"Record What Was Learned"
]
},
{
"process": "ref/mkt/select-marketing-technology",
"activities": [
"Compare the Finalists",
"Choose the Tool",
"Record What Was Learned"
]
},
{
"process": "ref/mkt/set-marketing-budget",
"activities": [
"Take in the Planning Guidance",
"Collect What Each Function Asks For",
"Test the Asks against the Goals",
"Size the Reserve",
"Settle the Split across Functions",
"Set the Rules for Moving Money",
"Phase the Money across the Year",
"Tell Every Function What It Has",
"Record What the Budget Rests On"
]
},
{
"process": "ref/mkt/size-market-opportunity",
"activities": [
"Take in the Question",
"Draw the Market Boundary",
"Choose the Sizing Method",
"Reconcile the Methods",
"Settle on the Number",
"Write down the Sizing",
"Set the Review Conditions",
"Record What Was Learned"
]
},
{
"process": "ref/mkt/win-loss-analysis",
"activities": [
"Write the Findings",
"Deliver the Themes and Recommendations"
]
}
]
}
}
}
# decision-coordinator This is an abstract agent, published as an Agent Plugin. An abstract agent is a job description rather than an implementation. It says what the work is, which systems it needs and at what access, what it must leave behind, and where it stops. Any agent that leaves the records can implement it. The plugin carries 25 skills, no `mcp.json`, and everything the abstract agent owes under `com.agentcatalog.agent/`. ## Why there is no mcp.json A conformant server entry in `mcp.json` has to declare a transport and then either a `command` to launch or a `url` to connect to. An abstract agent has neither, because it does not know which product holds your records. Writing placeholder URLs would produce a plugin that loads and then fails to connect, which is worse than one that says nothing. Section 6.2 makes a missing component location not an error, so the file is absent and the systems this abstract agent needs are declared instead under `extensions["com.agentcatalog.agent"].servers`, as a role, an access level and what the access is for. Whoever builds an agent from this plugin writes the `mcp.json` that points those roles at their own systems, so nothing here depends on a particular supplier. ## Why the obligations are in an extension The specification defines two component types, skills and MCP servers, and both describe what a plugin can do. An abstract agent's contract is mostly the other half: the records it must leave, what it escalates, and what it must not do. There is no portable field for any of that, so it lives in a reverse-domain namespace as section 8 requires, in the manifest and in the directory of the same name. ## Where this abstract agent is used `ref/mkt/annual-marketing-plan`, `ref/mkt/approve-marketing-material`, `ref/mkt/attribution-model`, `ref/mkt/brand-health`, `ref/mkt/brand-identity`, `ref/mkt/brand-positioning`, and 24 more. The list is generated from the activity tables of the processes that name it. https://agentcatalog.com/abstract-agents/decision-coordinator
--- name: check-the-evidence-holds-up description: Reads what is proposed against the standards and the goals already in force, and where two sets of numbers disagree it sets out the disagreement and what explains it. Use it when running `ref/mkt/develop-marketing-strategy`, `ref/mkt/set-marketing-budget` and `ref/mkt/size-market-opportunity`. license: CC-BY-4.0 metadata: agent: decision-coordinator agent-version: "1" --- # Check the evidence holds up ## What it does Reads what is proposed against the standards and the goals already in force, and where two sets of numbers disagree it sets out the disagreement and what explains it. ## Where it happens The agent does this in three activities across three reference processes. Each one names the activity as that process words it. - **Check the Options against What Is Agreed** - `ref/mkt/develop-marketing-strategy`, activity 9 - [Develop Marketing Strategy](../../../../processes/marketing/develop-marketing-strategy.md) - **Reconcile the Methods** - `ref/mkt/size-market-opportunity`, activity 8 - [Size Market Opportunity](../../../../processes/marketing/size-market-opportunity.md) - **Test the Asks against the Goals** - `ref/mkt/set-marketing-budget`, activity 6 - [Set Marketing Budget](../../../../processes/marketing/set-marketing-budget.md) ## What to record The decision written down as a question before any evidence is gathered: what it has to settle, who decides it, what evidence it needs and from which agent, and the date it is due. The evidence as it came in, each line attributed to the agent and the source behind it. The candidate answers, each written out with what it would cost and what it would rule out. The answer at a version, naming who decided it, on what date, for what reasons, and anyone who disagreed with what that person said. A handover line for each agent that has to act on the answer, naming the agent and what it was given. The review date, set at the moment the answer is recorded. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
--- name: collect-what-every-area-puts-forward description: Sends one request in one format with one due date to every area or agent, and gathers what comes back into a single list. Use it when running `ref/mkt/annual-marketing-plan` and 3 other reference processes. license: CC-BY-4.0 metadata: agent: decision-coordinator agent-version: "1" --- # Collect what every area puts forward ## What it does Sends one request in one format with one due date to every area or agent, and gathers what comes back into a single list. ## Where it happens The agent does this in four activities across four reference processes. Each one names the activity as that process words it. - **Ask Each Area What It Would Change** - `ref/mkt/quarterly-business-review`, activity 8 - [Conduct Quarterly Business Review](../../../../processes/marketing/quarterly-business-review.md) - **Collect What Each Function Asks For** - `ref/mkt/set-marketing-budget`, activity 4 - [Set Marketing Budget](../../../../processes/marketing/set-marketing-budget.md) - **Collect the Candidate Initiatives** - `ref/mkt/annual-marketing-plan`, activity 6 - [Build Annual Marketing Plan](../../../../processes/marketing/annual-marketing-plan.md) - **Collect the Topic Candidates** - `ref/mkt/content-calendar`, activity 4 - [Plan Content Calendar](../../../../processes/marketing/content-calendar.md) ## What to record The decision written down as a question before any evidence is gathered: what it has to settle, who decides it, what evidence it needs and from which agent, and the date it is due. The evidence as it came in, each line attributed to the agent and the source behind it. The candidate answers, each written out with what it would cost and what it would rule out. The answer at a version, naming who decided it, on what date, for what reasons, and anyone who disagreed with what that person said. A handover line for each agent that has to act on the answer, naming the agent and what it was given. The review date, set at the moment the answer is recorded. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
--- name: convene-the-room-where-it-is-decided description: Convenes the people who decide, puts each option in front of them with its cost and what it rules out, runs the session, and afterwards goes and gets answers to the questions the room could not settle. Use it when running `ref/mkt/brief-executive-leadership`, `ref/mkt/plan-marketing-capacity` and `ref/mkt/quarterly-business-review`. license: CC-BY-4.0 metadata: agent: decision-coordinator agent-version: "1" --- # Convene the room where it is decided ## What it does Convenes the people who decide, puts each option in front of them with its cost and what it rules out, runs the session, and afterwards goes and gets answers to the questions the room could not settle. ## Where it happens The agent does this in four activities across three reference processes. Each one names the activity as that process words it. - **Answer What Was Left Open** - `ref/mkt/brief-executive-leadership`, activity 18 - [Brief Executive Leadership](../../../../processes/marketing/brief-executive-leadership.md) - **Deliver the Briefing** - `ref/mkt/brief-executive-leadership`, activity 16 - [Brief Executive Leadership](../../../../processes/marketing/brief-executive-leadership.md) - **Hold the Review** - `ref/mkt/quarterly-business-review`, activity 10 - [Conduct Quarterly Business Review](../../../../processes/marketing/quarterly-business-review.md) - **Put the Options to the People Who Decide** - `ref/mkt/plan-marketing-capacity`, activity 10 - [Plan Marketing Capacity](../../../../processes/marketing/plan-marketing-capacity.md) ## What to record The decision written down as a question before any evidence is gathered: what it has to settle, who decides it, what evidence it needs and from which agent, and the date it is due. The evidence as it came in, each line attributed to the agent and the source behind it. The candidate answers, each written out with what it would cost and what it would rule out. The answer at a version, naming who decided it, on what date, for what reasons, and anyone who disagreed with what that person said. A handover line for each agent that has to act on the answer, naming the agent and what it was given. The review date, set at the moment the answer is recorded. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
--- name: draft-the-candidate-answers description: Commissions the evidence and writes up two or three candidate answers to the open question, each one carrying the case for it. Use it when running `ref/mkt/brand-positioning` and 6 other reference processes. license: CC-BY-4.0 metadata: agent: decision-coordinator agent-version: "1" --- # Draft the candidate answers ## What it does Commissions the evidence and writes up two or three candidate answers to the open question, each one carrying the case for it. ## Where it happens The agent does this in six activities across seven reference processes. Each one names the activity as that process words it. - **Draft the Candidate Positions** - `ref/mkt/brand-positioning`, activity 6 - [Define Brand Positioning](../../../../processes/marketing/brand-positioning.md) - `ref/mkt/product-positioning`, activity 8 - [Develop Product Positioning](../../../../processes/marketing/product-positioning.md) - **Draft the Candidate Profiles** - `ref/mkt/ideal-customer-profile`, activity 6 - [Define Ideal Customer Profile](../../../../processes/marketing/ideal-customer-profile.md) - **Draft the Stages** - `ref/mkt/map-buyer-journey`, activity 8 - [Map Buyer Journey](../../../../processes/marketing/map-buyer-journey.md) - **Draft the Strategic Options** - `ref/mkt/develop-marketing-strategy`, activity 6 - [Develop Marketing Strategy](../../../../processes/marketing/develop-marketing-strategy.md) - **Draw the Candidate Divisions** - `ref/mkt/segment-the-market`, activity 7 - [Segment the Market](../../../../processes/marketing/segment-the-market.md) - **Generate the Candidate Names** - `ref/mkt/name-product`, activity 4 - [Name Product or Company](../../../../processes/marketing/name-product.md) ## What to record The decision written down as a question before any evidence is gathered: what it has to settle, who decides it, what evidence it needs and from which agent, and the date it is due. The evidence as it came in, each line attributed to the agent and the source behind it. The candidate answers, each written out with what it would cost and what it would rule out. The answer at a version, naming who decided it, on what date, for what reasons, and anyone who disagreed with what that person said. A handover line for each agent that has to act on the answer, naming the agent and what it was given. The review date, set at the moment the answer is recorded. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
--- name: fit-the-work-to-the-capacity description: Works out what an option would need in money and in people, what the period already owes and how much can be carried, then lays the committed work across the period with an agent, a date and a budget on each item and says what in flight has to stop or wait. Use it when running `ref/mkt/annual-marketing-plan` and 3 other reference processes. license: CC-BY-4.0 metadata: agent: decision-coordinator agent-version: "1" --- # Fit the work to the capacity ## What it does Works out what an option would need in money and in people, what the period already owes and how much can be carried, then lays the committed work across the period with an agent, a date and a budget on each item and says what in flight has to stop or wait. ## Where it happens The agent does this in six activities across four reference processes. Each one names the activity as that process words it. - **Build the Calendar** - `ref/mkt/annual-marketing-plan`, activity 11 - [Build Annual Marketing Plan](../../../../processes/marketing/annual-marketing-plan.md) - **Check What Each Option Would Take** - `ref/mkt/develop-marketing-strategy`, activity 8 - [Develop Marketing Strategy](../../../../processes/marketing/develop-marketing-strategy.md) - **Check What the Department Can Carry** - `ref/mkt/annual-marketing-plan`, activity 8 - [Build Annual Marketing Plan](../../../../processes/marketing/annual-marketing-plan.md) - **List the Committed Work** - `ref/mkt/plan-marketing-capacity`, activity 2 - [Plan Marketing Capacity](../../../../processes/marketing/plan-marketing-capacity.md) - **Resource the Commitments** - `ref/mkt/prioritize-initiatives`, activity 11 - [Prioritize Marketing Initiatives](../../../../processes/marketing/prioritize-initiatives.md) - **Settle What Gets Displaced** - `ref/mkt/prioritize-initiatives`, activity 12 - [Prioritize Marketing Initiatives](../../../../processes/marketing/prioritize-initiatives.md) ## What to record The decision written down as a question before any evidence is gathered: what it has to settle, who decides it, what evidence it needs and from which agent, and the date it is due. The evidence as it came in, each line attributed to the agent and the source behind it. The candidate answers, each written out with what it would cost and what it would rule out. The answer at a version, naming who decided it, on what date, for what reasons, and anyone who disagreed with what that person said. A handover line for each agent that has to act on the answer, naming the agent and what it was given. The review date, set at the moment the answer is recorded. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
--- name: hand-the-answer-to-the-agents-that-act description: Gives every agent and function that has to act the same account of what was decided, and takes back from each one what it is going to change. Use it when running `ref/mkt/annual-marketing-plan` and 15 other reference processes. license: CC-BY-4.0 metadata: agent: decision-coordinator agent-version: "1" --- # Hand the answer to the agents that act ## What it does Gives every agent and function that has to act the same account of what was decided, and takes back from each one what it is going to change. Whoever asked for something hears the answer, including the ones that were turned down. ## Where it happens The agent does this in fourteen activities across sixteen reference processes. Each one names the activity as that process words it. - **Brief the Department** - `ref/mkt/annual-marketing-plan`, activity 15 - [Build Annual Marketing Plan](../../../../processes/marketing/annual-marketing-plan.md) - `ref/mkt/content-calendar`, activity 13 - [Plan Content Calendar](../../../../processes/marketing/content-calendar.md) - `ref/mkt/quarterly-business-review`, activity 15 - [Conduct Quarterly Business Review](../../../../processes/marketing/quarterly-business-review.md) - **Brief the Makers** - `ref/mkt/brand-voice`, activity 4 - [Define Brand Voice and Messaging](../../../../processes/marketing/brand-voice.md) - **Deliver the Findings** - `ref/mkt/customer-research`, activity 19 - [Conduct Customer Research](../../../../processes/marketing/customer-research.md) - **Deliver the Themes and Recommendations** - `ref/mkt/win-loss-analysis`, activity 20 - [Conduct Win/Loss Analysis](../../../../processes/marketing/win-loss-analysis.md) - **Hand over the Commitments** - `ref/mkt/prioritize-initiatives`, activity 15 - [Prioritize Marketing Initiatives](../../../../processes/marketing/prioritize-initiatives.md) - **Hand over the Map** - `ref/mkt/map-buyer-journey`, activity 17 - [Map Buyer Journey](../../../../processes/marketing/map-buyer-journey.md) - **Hand over the Model** - `ref/mkt/lead-scoring-model`, activity 14 - [Maintain Lead Scoring Model](../../../../processes/marketing/lead-scoring-model.md) - **Hand over the Profile** - `ref/mkt/ideal-customer-profile`, activity 15 - [Define Ideal Customer Profile](../../../../processes/marketing/ideal-customer-profile.md) - **Hand over the Segments** - `ref/mkt/segment-the-market`, activity 16 - [Segment the Market](../../../../processes/marketing/segment-the-market.md) - **Hand the Decisions On** - `ref/mkt/brief-executive-leadership`, activity 19 - [Brief Executive Leadership](../../../../processes/marketing/brief-executive-leadership.md) - **Hand the Strategy to the Work that Follows** - `ref/mkt/develop-marketing-strategy`, activity 15 - [Develop Marketing Strategy](../../../../processes/marketing/develop-marketing-strategy.md) - **Tell Every Function What It Has** - `ref/mkt/set-marketing-budget`, activity 14 - [Set Marketing Budget](../../../../processes/marketing/set-marketing-budget.md) - **Tell the Processes that Read It** - `ref/mkt/brand-positioning`, activity 15 - [Define Brand Positioning](../../../../processes/marketing/brand-positioning.md) - `ref/mkt/brand-voice`, activity 16 - [Define Brand Voice and Messaging](../../../../processes/marketing/brand-voice.md) - `ref/mkt/name-product`, activity 15 - [Name Product or Company](../../../../processes/marketing/name-product.md) - **Tell the Requesters** - `ref/mkt/prioritize-initiatives`, activity 14 - [Prioritize Marketing Initiatives](../../../../processes/marketing/prioritize-initiatives.md) ## What to record The decision written down as a question before any evidence is gathered: what it has to settle, who decides it, what evidence it needs and from which agent, and the date it is due. The evidence as it came in, each line attributed to the agent and the source behind it. The candidate answers, each written out with what it would cost and what it would rule out. The answer at a version, naming who decided it, on what date, for what reasons, and anyone who disagreed with what that person said. A handover line for each agent that has to act on the answer, naming the agent and what it was given. The review date, set at the moment the answer is recorded. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
--- name: issue-the-answer-at-a-version description: Issues the agreed answer at a numbered version on the date it is due, and tells every reader that the version is out. Use it when running `ref/mkt/annual-marketing-plan`, `ref/mkt/product-positioning` and `ref/mkt/quarterly-business-review`. license: CC-BY-4.0 metadata: agent: decision-coordinator agent-version: "1" --- # Issue the answer at a version ## What it does Issues the agreed answer at a numbered version on the date it is due, and tells every reader that the version is out. ## Where it happens The agent does this in three activities across three reference processes. Each one names the activity as that process words it. - **Issue the Positioning at a Version** - `ref/mkt/product-positioning`, activity 15 - [Develop Product Positioning](../../../../processes/marketing/product-positioning.md) - **Publish the Plan** - `ref/mkt/annual-marketing-plan`, activity 14 - [Build Annual Marketing Plan](../../../../processes/marketing/annual-marketing-plan.md) - **Publish the Reset Commitments** - `ref/mkt/quarterly-business-review`, activity 14 - [Conduct Quarterly Business Review](../../../../processes/marketing/quarterly-business-review.md) ## What to record The decision written down as a question before any evidence is gathered: what it has to settle, who decides it, what evidence it needs and from which agent, and the date it is due. The evidence as it came in, each line attributed to the agent and the source behind it. The candidate answers, each written out with what it would cost and what it would rule out. The answer at a version, naming who decided it, on what date, for what reasons, and anyone who disagreed with what that person said. A handover line for each agent that has to act on the answer, naming the agent and what it was given. The review date, set at the moment the answer is recorded. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
--- name: name-what-is-missing description: Sets what exists against what the standard or the plan asks for, and names what is missing, which of the misses matter, and which sit inside the noise. Use it when running `ref/mkt/brand-positioning` and 3 other reference processes. license: CC-BY-4.0 metadata: agent: decision-coordinator agent-version: "1" --- # Name what is missing ## What it does Sets what exists against what the standard or the plan asks for, and names what is missing, which of the misses matter, and which sit inside the noise. ## Where it happens The agent does this in four activities across four reference processes. Each one names the activity as that process words it. - **Audit What the Company Says Now** - `ref/mkt/brand-positioning`, activity 4 - [Define Brand Positioning](../../../../processes/marketing/brand-positioning.md) - **Find the Gaps** - `ref/mkt/map-buyer-journey`, activity 13 - [Map Buyer Journey](../../../../processes/marketing/map-buyer-journey.md) - **Name the Gaps Worth Acting On** - `ref/mkt/quarterly-business-review`, activity 7 - [Conduct Quarterly Business Review](../../../../processes/marketing/quarterly-business-review.md) - **Name the Gaps that Remain** - `ref/mkt/plan-marketing-capacity`, activity 13 - [Plan Marketing Capacity](../../../../processes/marketing/plan-marketing-capacity.md) ## What to record The decision written down as a question before any evidence is gathered: what it has to settle, who decides it, what evidence it needs and from which agent, and the date it is due. The evidence as it came in, each line attributed to the agent and the source behind it. The candidate answers, each written out with what it would cost and what it would rule out. The answer at a version, naming who decided it, on what date, for what reasons, and anyone who disagreed with what that person said. A handover line for each agent that has to act on the answer, naming the agent and what it was given. The review date, set at the moment the answer is recorded. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
--- name: name-what-it-will-be-judged-by description: Names the numbers the answer will be reported against and says where each one is read from. Use it when running `ref/mkt/annual-marketing-plan`, `ref/mkt/brand-health` and `ref/mkt/develop-marketing-strategy`. license: CC-BY-4.0 metadata: agent: decision-coordinator agent-version: "1" --- # Name what it will be judged by ## What it does Names the numbers the answer will be reported against and says where each one is read from. ## Where it happens The agent does this in four activities across three reference processes. Each one names the activity as that process words it. - **Name What Will Be Measured** - `ref/mkt/annual-marketing-plan`, activity 12 - [Build Annual Marketing Plan](../../../../processes/marketing/annual-marketing-plan.md) - **Name What the Strategy Will Be Judged By** - `ref/mkt/develop-marketing-strategy`, activity 12 - [Develop Marketing Strategy](../../../../processes/marketing/develop-marketing-strategy.md) - **Set the Goals for the Year** - `ref/mkt/annual-marketing-plan`, activity 5 - [Build Annual Marketing Plan](../../../../processes/marketing/annual-marketing-plan.md) - **Settle What the Wave Measures** - `ref/mkt/brand-health`, activity 3 - [Measure Brand Health](../../../../processes/marketing/brand-health.md) ## What to record The decision written down as a question before any evidence is gathered: what it has to settle, who decides it, what evidence it needs and from which agent, and the date it is due. The evidence as it came in, each line attributed to the agent and the source behind it. The candidate answers, each written out with what it would cost and what it would rule out. The answer at a version, naming who decided it, on what date, for what reasons, and anyone who disagreed with what that person said. A handover line for each agent that has to act on the answer, naming the agent and what it was given. The review date, set at the moment the answer is recorded. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
--- name: narrow-the-candidates-to-a-shortlist description: Takes candidates off the list when they break the criteria, and leaves a short list worth spending time and money on. Use it when running `ref/mkt/name-product`. license: CC-BY-4.0 metadata: agent: decision-coordinator agent-version: "1" --- # Narrow the candidates to a shortlist ## What it does Takes candidates off the list when they break the criteria, and leaves a short list worth spending time and money on. ## Where it happens The agent does this in two activities across one reference process. Each one names the activity as that process words it. - **Cut to a Shortlist** - `ref/mkt/name-product`, activity 8 - [Name Product or Company](../../../../processes/marketing/name-product.md) - **Screen the Long List** - `ref/mkt/name-product`, activity 5 - [Name Product or Company](../../../../processes/marketing/name-product.md) ## What to record The decision written down as a question before any evidence is gathered: what it has to settle, who decides it, what evidence it needs and from which agent, and the date it is due. The evidence as it came in, each line attributed to the agent and the source behind it. The candidate answers, each written out with what it would cost and what it would rule out. The answer at a version, naming who decided it, on what date, for what reasons, and anyone who disagreed with what that person said. A handover line for each agent that has to act on the answer, naming the agent and what it was given. The review date, set at the moment the answer is recorded. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
--- name: prepare-the-decision-pack description: Settles what will be asked of the room and what the department will say, and gets the pack to everyone with time to read it before they walk in. Use it when running `ref/mkt/brief-executive-leadership`. license: CC-BY-4.0 metadata: agent: decision-coordinator agent-version: "1" --- # Prepare the decision pack ## What it does Settles what will be asked of the room and what the department will say, and gets the pack to everyone with time to read it before they walk in. ## Where it happens The agent does this in two activities across one reference process. Each one names the activity as that process words it. - **Send the Pack Ahead** - `ref/mkt/brief-executive-leadership`, activity 14 - [Brief Executive Leadership](../../../../processes/marketing/brief-executive-leadership.md) - **Settle Marketing's Position** - `ref/mkt/brief-executive-leadership`, activity 10 - [Brief Executive Leadership](../../../../processes/marketing/brief-executive-leadership.md) ## What to record The decision written down as a question before any evidence is gathered: what it has to settle, who decides it, what evidence it needs and from which agent, and the date it is due. The evidence as it came in, each line attributed to the agent and the source behind it. The candidate answers, each written out with what it would cost and what it would rule out. The answer at a version, naming who decided it, on what date, for what reasons, and anyone who disagreed with what that person said. A handover line for each agent that has to act on the answer, naming the agent and what it was given. The review date, set at the moment the answer is recorded. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
--- name: read-what-is-already-settled description: Reads what is already in force before a new decision opens, which means the standards at the versions they are held at, and the questions and commitments the last meeting left standing. Use it when running `ref/mkt/brief-executive-leadership` and `ref/mkt/product-positioning`. license: CC-BY-4.0 metadata: agent: decision-coordinator agent-version: "1" --- # Read what is already settled ## What it does Reads what is already in force before a new decision opens, which means the standards at the versions they are held at, and the questions and commitments the last meeting left standing. ## Where it happens The agent does this in two activities across two reference processes. Each one names the activity as that process words it. - **Read the Last Meeting's Record** - `ref/mkt/brief-executive-leadership`, activity 2 - [Brief Executive Leadership](../../../../processes/marketing/brief-executive-leadership.md) - **Read the Standards in Force** - `ref/mkt/product-positioning`, activity 2 - [Develop Product Positioning](../../../../processes/marketing/product-positioning.md) ## What to record The decision written down as a question before any evidence is gathered: what it has to settle, who decides it, what evidence it needs and from which agent, and the date it is due. The evidence as it came in, each line attributed to the agent and the source behind it. The candidate answers, each written out with what it would cost and what it would rule out. The answer at a version, naming who decided it, on what date, for what reasons, and anyone who disagreed with what that person said. A handover line for each agent that has to act on the answer, naming the agent and what it was given. The review date, set at the moment the answer is recorded. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
--- name: record-the-choice-that-was-made description: Takes the answer the named deciders picked and writes it down with the reasons they gave and the names of anyone who disagreed. Use it when running `ref/mkt/annual-marketing-plan` and 21 other reference processes. license: CC-BY-4.0 metadata: agent: decision-coordinator agent-version: "1" --- # Record the choice that was made ## What it does Takes the answer the named deciders picked and writes it down with the reasons they gave and the names of anyone who disagreed. This agent picks none of it itself, which is what makes the record worth trusting later. ## Where it happens The agent does this in 25 activities across 22 reference processes. Each one names the activity as that process words it. - **Agree Who the Company Is For** - `ref/mkt/brand-positioning`, activity 5 - [Define Brand Positioning](../../../../processes/marketing/brand-positioning.md) - **Agree the Calendar** - `ref/mkt/content-calendar`, activity 11 - [Plan Content Calendar](../../../../processes/marketing/content-calendar.md) - **Choose What Gets Committed** - `ref/mkt/prioritize-initiatives`, activity 10 - [Prioritize Marketing Initiatives](../../../../processes/marketing/prioritize-initiatives.md) - **Choose Where to Play and How to Win** - `ref/mkt/develop-marketing-strategy`, activity 10 - [Develop Marketing Strategy](../../../../processes/marketing/develop-marketing-strategy.md) - **Choose the Agency** - `ref/mkt/engage-marketing-agency`, activity 12 - [Engage Marketing Agency](../../../../processes/marketing/engage-marketing-agency.md) - **Choose the Identity** - `ref/mkt/brand-identity`, activity 9 - [Develop Brand Identity](../../../../processes/marketing/brand-identity.md) - **Choose the Initiatives** - `ref/mkt/annual-marketing-plan`, activity 9 - [Build Annual Marketing Plan](../../../../processes/marketing/annual-marketing-plan.md) - **Choose the Mix** - `ref/mkt/media-plan`, activity 8 - [Develop Media Plan](../../../../processes/marketing/media-plan.md) - **Choose the Model** - `ref/mkt/attribution-model`, activity 10 - [Maintain Attribution Model](../../../../processes/marketing/attribution-model.md) - `ref/mkt/lead-scoring-model`, activity 11 - [Maintain Lead Scoring Model](../../../../processes/marketing/lead-scoring-model.md) - **Choose the Name** - `ref/mkt/name-product`, activity 12 - [Name Product or Company](../../../../processes/marketing/name-product.md) - **Choose the Position** - `ref/mkt/brand-positioning`, activity 9 - [Define Brand Positioning](../../../../processes/marketing/brand-positioning.md) - `ref/mkt/product-positioning`, activity 11 - [Develop Product Positioning](../../../../processes/marketing/product-positioning.md) - **Choose the Route** - `ref/mkt/engage-marketing-agency`, activity 2 - [Engage Marketing Agency](../../../../processes/marketing/engage-marketing-agency.md) - **Choose the Tool** - `ref/mkt/select-marketing-technology`, activity 17 - [Select Marketing Technology](../../../../processes/marketing/select-marketing-technology.md) - **Decide What Happens to Each Surface** - `ref/mkt/brand-refresh`, activity 8 - [Roll Out Brand Refresh](../../../../processes/marketing/brand-refresh.md) - **Decide What Happens to Published Reports** - `ref/mkt/attribution-model`, activity 11 - [Maintain Attribution Model](../../../../processes/marketing/attribution-model.md) - **Decide What Is Handed Over** - `ref/mkt/engage-marketing-agency`, activity 3 - [Engage Marketing Agency](../../../../processes/marketing/engage-marketing-agency.md) - **Decide the Mix** - `ref/mkt/plan-marketing-capacity`, activity 11 - [Plan Marketing Capacity](../../../../processes/marketing/plan-marketing-capacity.md) - **Reset the Commitments** - `ref/mkt/quarterly-business-review`, activity 11 - [Conduct Quarterly Business Review](../../../../processes/marketing/quarterly-business-review.md) - **Set the Switch Date and the Order** - `ref/mkt/brand-refresh`, activity 10 - [Roll Out Brand Refresh](../../../../processes/marketing/brand-refresh.md) - **Settle What May Be Said** - `ref/mkt/competitive-battlecard`, activity 6 - [Refresh Competitive Battlecard](../../../../processes/marketing/competitive-battlecard.md) - **Settle on One Division** - `ref/mkt/segment-the-market`, activity 12 - [Segment the Market](../../../../processes/marketing/segment-the-market.md) - **Settle on One Profile** - `ref/mkt/ideal-customer-profile`, activity 12 - [Define Ideal Customer Profile](../../../../processes/marketing/ideal-customer-profile.md) - **Settle on the Number** - `ref/mkt/size-market-opportunity`, activity 12 - [Size Market Opportunity](../../../../processes/marketing/size-market-opportunity.md) - **Settle the Map** - `ref/mkt/map-buyer-journey`, activity 14 - [Map Buyer Journey](../../../../processes/marketing/map-buyer-journey.md) - **Settle the Tiers and the Terms** - `ref/mkt/channel-program`, activity 2 - [Launch Channel Program](../../../../processes/marketing/channel-program.md) ## What to record The decision written down as a question before any evidence is gathered: what it has to settle, who decides it, what evidence it needs and from which agent, and the date it is due. The evidence as it came in, each line attributed to the agent and the source behind it. The candidate answers, each written out with what it would cost and what it would rule out. The answer at a version, naming who decided it, on what date, for what reasons, and anyone who disagreed with what that person said. A handover line for each agent that has to act on the answer, naming the agent and what it was given. The review date, set at the moment the answer is recorded. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
--- name: record-what-the-answer-rests-on description: Writes down what the answer rests on and what would reopen it, including the assumptions, the figures behind a change, and the date the answer gets looked at again. Use it when running `ref/mkt/annual-marketing-plan` and 13 other reference processes. license: CC-BY-4.0 metadata: agent: decision-coordinator agent-version: "1" --- # Record what the answer rests on ## What it does Writes down what the answer rests on and what would reopen it, including the assumptions, the figures behind a change, and the date the answer gets looked at again. ## Where it happens The agent does this in six activities across fourteen reference processes. Each one names the activity as that process words it. - **Record What the Budget Rests On** - `ref/mkt/set-marketing-budget`, activity 15 - [Set Marketing Budget](../../../../processes/marketing/set-marketing-budget.md) - **Record What the Plan Rests On** - `ref/mkt/annual-marketing-plan`, activity 16 - [Build Annual Marketing Plan](../../../../processes/marketing/annual-marketing-plan.md) - `ref/mkt/content-calendar`, activity 15 - [Plan Content Calendar](../../../../processes/marketing/content-calendar.md) - **Record What the Review Rests On** - `ref/mkt/quarterly-business-review`, activity 16 - [Conduct Quarterly Business Review](../../../../processes/marketing/quarterly-business-review.md) - **Record What the Round Rests On** - `ref/mkt/prioritize-initiatives`, activity 16 - [Prioritize Marketing Initiatives](../../../../processes/marketing/prioritize-initiatives.md) - **Record Why the Money Moved** - `ref/mkt/reallocate-media-spend`, activity 14 - [Reallocate Media Spend](../../../../processes/marketing/reallocate-media-spend.md) - **Set the Review Conditions** - `ref/mkt/attribution-model`, activity 15 - [Maintain Attribution Model](../../../../processes/marketing/attribution-model.md) - `ref/mkt/develop-marketing-strategy`, activity 16 - [Develop Marketing Strategy](../../../../processes/marketing/develop-marketing-strategy.md) - `ref/mkt/ideal-customer-profile`, activity 16 - [Define Ideal Customer Profile](../../../../processes/marketing/ideal-customer-profile.md) - `ref/mkt/lead-scoring-model`, activity 17 - [Maintain Lead Scoring Model](../../../../processes/marketing/lead-scoring-model.md) - `ref/mkt/map-buyer-journey`, activity 18 - [Map Buyer Journey](../../../../processes/marketing/map-buyer-journey.md) - `ref/mkt/product-positioning`, activity 16 - [Develop Product Positioning](../../../../processes/marketing/product-positioning.md) - `ref/mkt/segment-the-market`, activity 17 - [Segment the Market](../../../../processes/marketing/segment-the-market.md) - `ref/mkt/size-market-opportunity`, activity 15 - [Size Market Opportunity](../../../../processes/marketing/size-market-opportunity.md) ## What to record The decision written down as a question before any evidence is gathered: what it has to settle, who decides it, what evidence it needs and from which agent, and the date it is due. The evidence as it came in, each line attributed to the agent and the source behind it. The candidate answers, each written out with what it would cost and what it would rule out. The answer at a version, naming who decided it, on what date, for what reasons, and anyone who disagreed with what that person said. A handover line for each agent that has to act on the answer, naming the agent and what it was given. The review date, set at the moment the answer is recorded. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
--- name: record-what-was-learned description: Writes down what is worth repeating next time and what to avoid, so the next run starts from it. Use it when running `ref/mkt/brand-identity` and 14 other reference processes. license: CC-BY-4.0 metadata: agent: decision-coordinator agent-version: "1" --- # Record what was learned ## What it does Writes down what is worth repeating next time and what to avoid, so the next run starts from it. ## Where it happens The agent does this in one activity across fifteen reference processes. Each one names the activity as that process words it. - **Record What Was Learned** - `ref/mkt/brand-identity`, activity 16 - [Develop Brand Identity](../../../../processes/marketing/brand-identity.md) - `ref/mkt/brand-positioning`, activity 16 - [Define Brand Positioning](../../../../processes/marketing/brand-positioning.md) - `ref/mkt/brand-voice`, activity 19 - [Define Brand Voice and Messaging](../../../../processes/marketing/brand-voice.md) - `ref/mkt/brief-executive-leadership`, activity 20 - [Brief Executive Leadership](../../../../processes/marketing/brief-executive-leadership.md) - `ref/mkt/develop-marketing-strategy`, activity 17 - [Develop Marketing Strategy](../../../../processes/marketing/develop-marketing-strategy.md) - `ref/mkt/engage-marketing-agency`, activity 16 - [Engage Marketing Agency](../../../../processes/marketing/engage-marketing-agency.md) - `ref/mkt/ideal-customer-profile`, activity 17 - [Define Ideal Customer Profile](../../../../processes/marketing/ideal-customer-profile.md) - `ref/mkt/lead-scoring-model`, activity 18 - [Maintain Lead Scoring Model](../../../../processes/marketing/lead-scoring-model.md) - `ref/mkt/map-buyer-journey`, activity 19 - [Map Buyer Journey](../../../../processes/marketing/map-buyer-journey.md) - `ref/mkt/name-product`, activity 16 - [Name Product or Company](../../../../processes/marketing/name-product.md) - `ref/mkt/plan-marketing-capacity`, activity 15 - [Plan Marketing Capacity](../../../../processes/marketing/plan-marketing-capacity.md) - `ref/mkt/product-positioning`, activity 17 - [Develop Product Positioning](../../../../processes/marketing/product-positioning.md) - `ref/mkt/segment-the-market`, activity 18 - [Segment the Market](../../../../processes/marketing/segment-the-market.md) - `ref/mkt/select-marketing-technology`, activity 21 - [Select Marketing Technology](../../../../processes/marketing/select-marketing-technology.md) - `ref/mkt/size-market-opportunity`, activity 16 - [Size Market Opportunity](../../../../processes/marketing/size-market-opportunity.md) ## What to record The decision written down as a question before any evidence is gathered: what it has to settle, who decides it, what evidence it needs and from which agent, and the date it is due. The evidence as it came in, each line attributed to the agent and the source behind it. The candidate answers, each written out with what it would cost and what it would rule out. The answer at a version, naming who decided it, on what date, for what reasons, and anyone who disagreed with what that person said. A handover line for each agent that has to act on the answer, naming the agent and what it was given. The review date, set at the moment the answer is recorded. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
--- name: return-the-verdict-on-a-submission description: Pulls every finding into one list with the rule each one broke, sends the failures back to whoever submitted them, records in writing any failure that is knowingly accepted and the reasons for it, and releases the cleared version to the requester. Use it when running `ref/mkt/approve-marketing-material`. license: CC-BY-4.0 metadata: agent: decision-coordinator agent-version: "1" --- # Return the verdict on a submission ## What it does Pulls every finding into one list with the rule each one broke, sends the failures back to whoever submitted them, records in writing any failure that is knowingly accepted and the reasons for it, and releases the cleared version to the requester. ## Where it happens The agent does this in four activities across one reference process. Each one names the activity as that process words it. - **Gather the Findings into One List** - `ref/mkt/approve-marketing-material`, activity 9 - [Approve Marketing Material](../../../../processes/marketing/approve-marketing-material.md) - **Record an Accepted Exception** - `ref/mkt/approve-marketing-material`, activity 11 - [Approve Marketing Material](../../../../processes/marketing/approve-marketing-material.md) - **Release the Cleared Version** - `ref/mkt/approve-marketing-material`, activity 13 - [Approve Marketing Material](../../../../processes/marketing/approve-marketing-material.md) - **Return the Failures to the Submitter** - `ref/mkt/approve-marketing-material`, activity 10 - [Approve Marketing Material](../../../../processes/marketing/approve-marketing-material.md) ## What to record The decision written down as a question before any evidence is gathered: what it has to settle, who decides it, what evidence it needs and from which agent, and the date it is due. The evidence as it came in, each line attributed to the agent and the source behind it. The candidate answers, each written out with what it would cost and what it would rule out. The answer at a version, naming who decided it, on what date, for what reasons, and anyone who disagreed with what that person said. A handover line for each agent that has to act on the answer, naming the agent and what it was given. The review date, set at the moment the answer is recorded. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
--- name: run-a-submission-through-sign-off description: Records what was submitted and at which version, checks that the material, its claims and its sources are all there, names which standards apply and who has to sign, and gets those signatures against that one version. Use it when running `ref/mkt/approve-marketing-material`. license: CC-BY-4.0 metadata: agent: decision-coordinator agent-version: "1" --- # Run a submission through sign off ## What it does Records what was submitted and at which version, checks that the material, its claims and its sources are all there, names which standards apply and who has to sign, and gets those signatures against that one version. ## Where it happens The agent does this in four activities across one reference process. Each one names the activity as that process words it. - **Check the Submission Is Complete** - `ref/mkt/approve-marketing-material`, activity 3 - [Approve Marketing Material](../../../../processes/marketing/approve-marketing-material.md) - **Get the Signatures** - `ref/mkt/approve-marketing-material`, activity 12 - [Approve Marketing Material](../../../../processes/marketing/approve-marketing-material.md) - **Name the Standards and the Signers** - `ref/mkt/approve-marketing-material`, activity 2 - [Approve Marketing Material](../../../../processes/marketing/approve-marketing-material.md) - **Take in the Submission** - `ref/mkt/approve-marketing-material`, activity 1 - [Approve Marketing Material](../../../../processes/marketing/approve-marketing-material.md) ## What to record The decision written down as a question before any evidence is gathered: what it has to settle, who decides it, what evidence it needs and from which agent, and the date it is due. The evidence as it came in, each line attributed to the agent and the source behind it. The candidate answers, each written out with what it would cost and what it would rule out. The answer at a version, naming who decided it, on what date, for what reasons, and anyone who disagreed with what that person said. A handover line for each agent that has to act on the answer, naming the agent and what it was given. The review date, set at the moment the answer is recorded. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
--- name: score-and-rank-the-candidates description: Scores each candidate against the criteria already fixed and puts them in one order, with the reason for every place and the evidence it rests on. Use it when running `ref/mkt/content-calendar` and 3 other reference processes. license: CC-BY-4.0 metadata: agent: decision-coordinator agent-version: "1" --- # Score and rank the candidates ## What it does Scores each candidate against the criteria already fixed and puts them in one order, with the reason for every place and the evidence it rests on. ## Where it happens The agent does this in five activities across four reference processes. Each one names the activity as that process words it. - **Compare the Finalists** - `ref/mkt/select-marketing-technology`, activity 16 - [Select Marketing Technology](../../../../processes/marketing/select-marketing-technology.md) - **Rank the Requests** - `ref/mkt/prioritize-initiatives`, activity 9 - [Prioritize Marketing Initiatives](../../../../processes/marketing/prioritize-initiatives.md) - **Rank the Segments** - `ref/mkt/segment-the-market`, activity 13 - [Segment the Market](../../../../processes/marketing/segment-the-market.md) - **Score the Candidates** - `ref/mkt/content-calendar`, activity 8 - [Plan Content Calendar](../../../../processes/marketing/content-calendar.md) - **Weigh the Requests against the Goals** - `ref/mkt/prioritize-initiatives`, activity 6 - [Prioritize Marketing Initiatives](../../../../processes/marketing/prioritize-initiatives.md) ## What to record The decision written down as a question before any evidence is gathered: what it has to settle, who decides it, what evidence it needs and from which agent, and the date it is due. The evidence as it came in, each line attributed to the agent and the source behind it. The candidate answers, each written out with what it would cost and what it would rule out. The answer at a version, naming who decided it, on what date, for what reasons, and anyone who disagreed with what that person said. A handover line for each agent that has to act on the answer, naming the agent and what it was given. The review date, set at the moment the answer is recorded. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
--- name: set-the-boundary-of-the-question description: Says what is inside the question and what sits outside it, which covers where the market ends, what the round or the review takes in, the date it has to decide by, and what a buyer would pick instead. Use it when running `ref/mkt/prioritize-initiatives` and 4 other reference processes. license: CC-BY-4.0 metadata: agent: decision-coordinator agent-version: "1" --- # Set the boundary of the question ## What it does Says what is inside the question and what sits outside it, which covers where the market ends, what the round or the review takes in, the date it has to decide by, and what a buyer would pick instead. ## Where it happens The agent does this in five activities across five reference processes. Each one names the activity as that process words it. - **Draw the Market Boundary** - `ref/mkt/size-market-opportunity`, activity 2 - [Size Market Opportunity](../../../../processes/marketing/size-market-opportunity.md) - **Name the Competing Choices** - `ref/mkt/product-positioning`, activity 7 - [Develop Product Positioning](../../../../processes/marketing/product-positioning.md) - **Open the Round** - `ref/mkt/prioritize-initiatives`, activity 1 - [Prioritize Marketing Initiatives](../../../../processes/marketing/prioritize-initiatives.md) - **Set What the Review Covers** - `ref/mkt/quarterly-business-review`, activity 1 - [Conduct Quarterly Business Review](../../../../processes/marketing/quarterly-business-review.md) - **Set the Market Boundary** - `ref/mkt/segment-the-market`, activity 2 - [Segment the Market](../../../../processes/marketing/segment-the-market.md) ## What to record The decision written down as a question before any evidence is gathered: what it has to settle, who decides it, what evidence it needs and from which agent, and the date it is due. The evidence as it came in, each line attributed to the agent and the source behind it. The candidate answers, each written out with what it would cost and what it would rule out. The answer at a version, naming who decided it, on what date, for what reasons, and anyone who disagreed with what that person said. A handover line for each agent that has to act on the answer, naming the agent and what it was given. The review date, set at the moment the answer is recorded. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
--- name: settle-how-the-money-is-split description: Records how the money is divided and moved, which covers the split across functions and initiatives, when each part becomes available, how much is held back, who may move money and when, and each move the person who owns the money agrees to. Use it when running `ref/mkt/annual-marketing-plan` and 3 other reference processes. license: CC-BY-4.0 metadata: agent: decision-coordinator agent-version: "1" --- # Settle how the money is split ## What it does Records how the money is divided and moved, which covers the split across functions and initiatives, when each part becomes available, how much is held back, who may move money and when, and each move the person who owns the money agrees to. ## Where it happens The agent does this in seven activities across four reference processes. Each one names the activity as that process words it. - **Allocate the Budget** - `ref/mkt/annual-marketing-plan`, activity 10 - [Build Annual Marketing Plan](../../../../processes/marketing/annual-marketing-plan.md) - **Decide the Move** - `ref/mkt/reallocate-media-spend`, activity 8 - [Reallocate Media Spend](../../../../processes/marketing/reallocate-media-spend.md) - **Move the Money** - `ref/mkt/quarterly-business-review`, activity 12 - [Conduct Quarterly Business Review](../../../../processes/marketing/quarterly-business-review.md) - **Phase the Money across the Year** - `ref/mkt/set-marketing-budget`, activity 10 - [Set Marketing Budget](../../../../processes/marketing/set-marketing-budget.md) - **Set the Rules for Moving Money** - `ref/mkt/set-marketing-budget`, activity 9 - [Set Marketing Budget](../../../../processes/marketing/set-marketing-budget.md) - **Settle the Split across Functions** - `ref/mkt/set-marketing-budget`, activity 8 - [Set Marketing Budget](../../../../processes/marketing/set-marketing-budget.md) - **Size the Reserve** - `ref/mkt/set-marketing-budget`, activity 7 - [Set Marketing Budget](../../../../processes/marketing/set-marketing-budget.md) ## What to record The decision written down as a question before any evidence is gathered: what it has to settle, who decides it, what evidence it needs and from which agent, and the date it is due. The evidence as it came in, each line attributed to the agent and the source behind it. The candidate answers, each written out with what it would cost and what it would rule out. The answer at a version, naming who decided it, on what date, for what reasons, and anyone who disagreed with what that person said. A handover line for each agent that has to act on the answer, naming the agent and what it was given. The review date, set at the moment the answer is recorded. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
--- name: settle-the-criteria-before-the-work-runs description: Fixes the rules the work will be held to before any candidate arrives, so that nothing is scored against a standard invented after the fact. Use it when running `ref/mkt/engage-marketing-agency` and 4 other reference processes. license: CC-BY-4.0 metadata: agent: decision-coordinator agent-version: "1" --- # Settle the criteria before the work runs ## What it does Fixes the rules the work will be held to before any candidate arrives, so that nothing is scored against a standard invented after the fact. ## Where it happens The agent does this in five activities across five reference processes. Each one names the activity as that process words it. - **Choose the Dividing Traits** - `ref/mkt/segment-the-market`, activity 6 - [Segment the Market](../../../../processes/marketing/segment-the-market.md) - **Choose the Sizing Method** - `ref/mkt/size-market-opportunity`, activity 3 - [Size Market Opportunity](../../../../processes/marketing/size-market-opportunity.md) - **Name the Qualifying Signals** - `ref/mkt/ideal-customer-profile`, activity 7 - [Define Ideal Customer Profile](../../../../processes/marketing/ideal-customer-profile.md) - **Set the Naming Criteria** - `ref/mkt/name-product`, activity 2 - [Name Product or Company](../../../../processes/marketing/name-product.md) - **Set the Selection Criteria** - `ref/mkt/engage-marketing-agency`, activity 6 - [Engage Marketing Agency](../../../../processes/marketing/engage-marketing-agency.md) ## What to record The decision written down as a question before any evidence is gathered: what it has to settle, who decides it, what evidence it needs and from which agent, and the date it is due. The evidence as it came in, each line attributed to the agent and the source behind it. The candidate answers, each written out with what it would cost and what it would rule out. The answer at a version, naming who decided it, on what date, for what reasons, and anyone who disagreed with what that person said. A handover line for each agent that has to act on the answer, naming the agent and what it was given. The review date, set at the moment the answer is recorded. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
--- name: take-in-the-question description: Takes in whatever opened the decision, whether that is a change, a target, a gap, a request or a scheduled cycle, and works out what the decision has to settle and by when. Use it when running `ref/mkt/annual-marketing-plan` and 15 other reference processes. license: CC-BY-4.0 metadata: agent: decision-coordinator agent-version: "1" --- # Take in the question ## What it does Takes in whatever opened the decision, whether that is a change, a target, a gap, a request or a scheduled cycle, and works out what the decision has to settle and by when. ## Where it happens The agent does this in fourteen activities across sixteen reference processes. Each one names the activity as that process words it. - **Take in the Approved Positioning** - `ref/mkt/brand-voice`, activity 1 - [Define Brand Voice and Messaging](../../../../processes/marketing/brand-voice.md) - **Take in the Change** - `ref/mkt/brand-positioning`, activity 1 - [Define Brand Positioning](../../../../processes/marketing/brand-positioning.md) - **Take in the Company Targets** - `ref/mkt/annual-marketing-plan`, activity 1 - [Build Annual Marketing Plan](../../../../processes/marketing/annual-marketing-plan.md) - **Take in the Cycle** - `ref/mkt/brief-executive-leadership`, activity 1 - [Brief Executive Leadership](../../../../processes/marketing/brief-executive-leadership.md) - **Take in the Drift or the Signal** - `ref/mkt/lead-scoring-model`, activity 1 - [Maintain Lead Scoring Model](../../../../processes/marketing/lead-scoring-model.md) - **Take in the Gap** - `ref/mkt/engage-marketing-agency`, activity 1 - [Engage Marketing Agency](../../../../processes/marketing/engage-marketing-agency.md) - **Take in the Naming Request** - `ref/mkt/name-product`, activity 1 - [Name Product or Company](../../../../processes/marketing/name-product.md) - **Take in the Objectives** - `ref/mkt/develop-marketing-strategy`, activity 1 - [Develop Marketing Strategy](../../../../processes/marketing/develop-marketing-strategy.md) - **Take in the Period's Goals** - `ref/mkt/content-calendar`, activity 1 - [Plan Content Calendar](../../../../processes/marketing/content-calendar.md) - **Take in the Persona** - `ref/mkt/map-buyer-journey`, activity 1 - [Map Buyer Journey](../../../../processes/marketing/map-buyer-journey.md) - **Take in the Planning Guidance** - `ref/mkt/set-marketing-budget`, activity 1 - [Set Marketing Budget](../../../../processes/marketing/set-marketing-budget.md) - **Take in the Planning Trigger** - `ref/mkt/plan-marketing-capacity`, activity 1 - [Plan Marketing Capacity](../../../../processes/marketing/plan-marketing-capacity.md) - **Take in the Question** - `ref/mkt/ideal-customer-profile`, activity 1 - [Define Ideal Customer Profile](../../../../processes/marketing/ideal-customer-profile.md) - `ref/mkt/product-positioning`, activity 1 - [Develop Product Positioning](../../../../processes/marketing/product-positioning.md) - `ref/mkt/segment-the-market`, activity 1 - [Segment the Market](../../../../processes/marketing/segment-the-market.md) - `ref/mkt/size-market-opportunity`, activity 1 - [Size Market Opportunity](../../../../processes/marketing/size-market-opportunity.md) - **Work out What Has to Be Decided** - `ref/mkt/brief-executive-leadership`, activity 3 - [Brief Executive Leadership](../../../../processes/marketing/brief-executive-leadership.md) ## What to record The decision written down as a question before any evidence is gathered: what it has to settle, who decides it, what evidence it needs and from which agent, and the date it is due. The evidence as it came in, each line attributed to the agent and the source behind it. The candidate answers, each written out with what it would cost and what it would rule out. The answer at a version, naming who decided it, on what date, for what reasons, and anyone who disagreed with what that person said. A handover line for each agent that has to act on the answer, naming the agent and what it was given. The review date, set at the moment the answer is recorded. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
--- name: write-down-what-was-agreed description: Writes the settled answer down in full, holding what was decided, what was turned down and why, and who disagreed with it. Use it when running `ref/mkt/brief-executive-leadership` and 6 other reference processes. license: CC-BY-4.0 metadata: agent: decision-coordinator agent-version: "1" --- # Write down what was agreed ## What it does Writes the settled answer down in full, holding what was decided, what was turned down and why, and who disagreed with it. ## Where it happens The agent does this in seven activities across seven reference processes. Each one names the activity as that process words it. - **Record the Decisions** - `ref/mkt/brief-executive-leadership`, activity 17 - [Brief Executive Leadership](../../../../processes/marketing/brief-executive-leadership.md) - **Record the Declines** - `ref/mkt/prioritize-initiatives`, activity 13 - [Prioritize Marketing Initiatives](../../../../processes/marketing/prioritize-initiatives.md) - **Write down the Agreed Map** - `ref/mkt/map-buyer-journey`, activity 15 - [Map Buyer Journey](../../../../processes/marketing/map-buyer-journey.md) - **Write down the Agreed Profile** - `ref/mkt/ideal-customer-profile`, activity 13 - [Define Ideal Customer Profile](../../../../processes/marketing/ideal-customer-profile.md) - **Write down the Agreed Segments** - `ref/mkt/segment-the-market`, activity 14 - [Segment the Market](../../../../processes/marketing/segment-the-market.md) - **Write down the Agreed Strategy** - `ref/mkt/develop-marketing-strategy`, activity 11 - [Develop Marketing Strategy](../../../../processes/marketing/develop-marketing-strategy.md) - **Write down the Sizing** - `ref/mkt/size-market-opportunity`, activity 13 - [Size Market Opportunity](../../../../processes/marketing/size-market-opportunity.md) ## What to record The decision written down as a question before any evidence is gathered: what it has to settle, who decides it, what evidence it needs and from which agent, and the date it is due. The evidence as it came in, each line attributed to the agent and the source behind it. The candidate answers, each written out with what it would cost and what it would rule out. The answer at a version, naming who decided it, on what date, for what reasons, and anyone who disagreed with what that person said. A handover line for each agent that has to act on the answer, naming the agent and what it was given. The review date, set at the moment the answer is recorded. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
--- name: write-the-readout description: Writes the readout for whoever asked for the work, with the evidence under every line and what each finding asks somebody to change. Use it when running `ref/mkt/brand-health` and `ref/mkt/win-loss-analysis`. license: CC-BY-4.0 metadata: agent: decision-coordinator agent-version: "1" --- # Write the readout ## What it does Writes the readout for whoever asked for the work, with the evidence under every line and what each finding asks somebody to change. ## Where it happens The agent does this in two activities across two reference processes. Each one names the activity as that process words it. - **Report Awareness, Perception and Preference** - `ref/mkt/brand-health`, activity 22 - [Measure Brand Health](../../../../processes/marketing/brand-health.md) - **Write the Findings** - `ref/mkt/win-loss-analysis`, activity 18 - [Conduct Win/Loss Analysis](../../../../processes/marketing/win-loss-analysis.md) ## What to record The decision written down as a question before any evidence is gathered: what it has to settle, who decides it, what evidence it needs and from which agent, and the date it is due. The evidence as it came in, each line attributed to the agent and the source behind it. The candidate answers, each written out with what it would cost and what it would rule out. The answer at a version, naming who decided it, on what date, for what reasons, and anyone who disagreed with what that person said. A handover line for each agent that has to act on the answer, naming the agent and what it was given. The review date, set at the moment the answer is recorded. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
--- name: write-the-words-the-company-will-use description: Writes the statement the organization stands behind, the pillars and proof points under it, and the version each audience gets. Use it when running `ref/mkt/brand-positioning`, `ref/mkt/brand-voice` and `ref/mkt/product-positioning`. license: CC-BY-4.0 metadata: agent: decision-coordinator agent-version: "1" --- # Write the words the company will use ## What it does Writes the statement the organization stands behind, the pillars and proof points under it, and the version each audience gets. ## Where it happens The agent does this in three activities across three reference processes. Each one names the activity as that process words it. - **Build the Messaging Architecture** - `ref/mkt/brand-voice`, activity 7 - [Define Brand Voice and Messaging](../../../../processes/marketing/brand-voice.md) - **Write the Messaging** - `ref/mkt/product-positioning`, activity 12 - [Develop Product Positioning](../../../../processes/marketing/product-positioning.md) - **Write the Positioning and the Promise** - `ref/mkt/brand-positioning`, activity 10 - [Define Brand Positioning](../../../../processes/marketing/brand-positioning.md) ## What to record The decision written down as a question before any evidence is gathered: what it has to settle, who decides it, what evidence it needs and from which agent, and the date it is due. The evidence as it came in, each line attributed to the agent and the source behind it. The candidate answers, each written out with what it would cost and what it would rule out. The answer at a version, naming who decided it, on what date, for what reasons, and anyone who disagreed with what that person said. A handover line for each agent that has to act on the answer, naming the agent and what it was given. The review date, set at the moment the answer is recorded. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
Every server entry in an mcp.json needs either a command to run or a url to connect to, and the package cannot know either of those until somebody points it at their own systems. So the file is left out, the systems the agent needs are named by role in plugin.json, and you write the mcp.json when you set it up.
Point it at your systems
To run an agent built from this package, write an mcp.json that says which of your systems fills each role. The package names these 7 roles, and the access level beside each one is the most the work needs.
{
"$schema": "https://agent-plugins.org/schemas/1.1.0/mcp.schema.json",
"mcpServers": {
"decision-record": {
"type": "streamable-http",
"url": "https://mcp.yourcompany.com/decision-record"
},
"evidence-store": {
"type": "streamable-http",
"url": "https://mcp.yourcompany.com/evidence-store"
},
"marketing-standards-at-their-versions": {
"type": "streamable-http",
"url": "https://mcp.yourcompany.com/marketing-standards-at-their-versions"
},
"plans-and-commitments-the-decision-has-to-sit-inside": {
"type": "streamable-http",
"url": "https://mcp.yourcompany.com/plans-and-commitments-the-decision-has-to-sit-inside"
},
"meeting-calendar": {
"type": "streamable-http",
"url": "https://mcp.yourcompany.com/meeting-calendar"
},
"notification-channel": {
"type": "streamable-http",
"url": "https://mcp.yourcompany.com/notification-channel"
},
"review-schedule": {
"type": "streamable-http",
"url": "https://mcp.yourcompany.com/review-schedule"
}
}
}
The hostnames here are a placeholder for your own. Whichever product holds each of these systems, the agent you build is yours and nobody else has to be involved in running it.
35 processes, 185 activities
The highlighted activities are the ones this abstract agent does. The other activities in each process belong to other abstract agents or to people.
Take in the Company Targets · Set the Goals for the Year · Collect the Candidate Initiatives · Check What the Department Can Carry · Choose the Initiatives · Allocate the Budget · Build the Calendar · Name What Will Be Measured · Publish the Plan · Brief the Department · Record What the Plan Rests On
Take in the Submission · Name the Standards and the Signers · Check the Submission Is Complete · Gather the Findings into One List · Return the Failures to the Submitter · Record an Accepted Exception · Get the Signatures · Release the Cleared Version
Choose the Model · Decide What Happens to Published Reports · Set the Review Conditions
Settle What the Wave Measures · Report Awareness, Perception and Preference
Choose the Identity · Record What Was Learned
Take in the Change · Audit What the Company Says Now · Agree Who the Company Is For · Draft the Candidate Positions · Choose the Position · Write the Positioning and the Promise · Tell the Processes that Read It · Record What Was Learned
Decide What Happens to Each Surface · Set the Switch Date and the Order
Take in the Approved Positioning · Brief the Makers · Build the Messaging Architecture · Tell the Processes that Read It · Record What Was Learned
Take in the Cycle · Read the Last Meeting's Record · Work out What Has to Be Decided · Settle Marketing's Position · Send the Pack Ahead · Deliver the Briefing · Record the Decisions · Answer What Was Left Open · Hand the Decisions On · Record What Was Learned
Settle the Tiers and the Terms
Settle What May Be Said
Take in the Period's Goals · Collect the Topic Candidates · Score the Candidates · Agree the Calendar · Brief the Department · Record What the Plan Rests On
Deliver the Findings
Take in the Objectives · Draft the Strategic Options · Check What Each Option Would Take · Check the Options against What Is Agreed · Choose Where to Play and How to Win · Write down the Agreed Strategy · Name What the Strategy Will Be Judged By · Hand the Strategy to the Work that Follows · Set the Review Conditions · Record What Was Learned
Take in the Gap · Choose the Route · Decide What Is Handed Over · Set the Selection Criteria · Choose the Agency · Record What Was Learned
Take in the Question · Draft the Candidate Profiles · Name the Qualifying Signals · Settle on One Profile · Write down the Agreed Profile · Hand over the Profile · Set the Review Conditions · Record What Was Learned
Take in the Drift or the Signal · Choose the Model · Hand over the Model · Set the Review Conditions · Record What Was Learned
Take in the Persona · Draft the Stages · Find the Gaps · Settle the Map · Write down the Agreed Map · Hand over the Map · Set the Review Conditions · Record What Was Learned
Choose the Mix
Take in the Naming Request · Set the Naming Criteria · Generate the Candidate Names · Screen the Long List · Cut to a Shortlist · Choose the Name · Tell the Processes that Read It · Record What Was Learned
Take in the Planning Trigger · List the Committed Work · Put the Options to the People Who Decide · Decide the Mix · Name the Gaps that Remain · Record What Was Learned
Open the Round · Weigh the Requests against the Goals · Rank the Requests · Choose What Gets Committed · Resource the Commitments · Settle What Gets Displaced · Record the Declines · Tell the Requesters · Hand over the Commitments · Record What the Round Rests On
Take in the Question · Read the Standards in Force · Name the Competing Choices · Draft the Candidate Positions · Choose the Position · Write the Messaging · Issue the Positioning at a Version · Set the Review Conditions · Record What Was Learned
Set What the Review Covers · Name the Gaps Worth Acting On · Ask Each Area What It Would Change · Hold the Review · Reset the Commitments · Move the Money · Publish the Reset Commitments · Brief the Department · Record What the Review Rests On
Decide the Move · Record Why the Money Moved
Take in the Question · Set the Market Boundary · Choose the Dividing Traits · Draw the Candidate Divisions · Settle on One Division · Rank the Segments · Write down the Agreed Segments · Hand over the Segments · Set the Review Conditions · Record What Was Learned
Compare the Finalists · Choose the Tool · Record What Was Learned
Take in the Planning Guidance · Collect What Each Function Asks For · Test the Asks against the Goals · Size the Reserve · Settle the Split across Functions · Set the Rules for Moving Money · Phase the Money across the Year · Tell Every Function What It Has · Record What the Budget Rests On
Take in the Question · Draw the Market Boundary · Choose the Sizing Method · Reconcile the Methods · Settle on the Number · Write down the Sizing · Set the Review Conditions · Record What Was Learned
Write the Findings · Deliver the Themes and Recommendations
Settle the Disputes
Set the Thresholds
Draft the Options · Convene the Review · Record the Decision and Its Owner · Set the Next Review
Hold the Review · Decide Each Plan · Tell the Readers
Choose the Plan · Issue the Plan and Tell the Readers
What it writes down
The decision written down as a question before any evidence is gathered: what it has to settle, who decides it, what evidence it needs and from which agent, and the date it is due. The evidence as it came in, each line attributed to the agent and the source behind it. The candidate answers, each written out with what it would cost and what it would rule out. The answer at a version, naming who decided it, on what date, for what reasons, and anyone who disagreed with what that person said. A handover line for each agent that has to act on the answer, naming the agent and what it was given. The review date, set at the moment the answer is recorded.
What it will not do
Does not decide anything. It runs the decision and named people make it, which is what keeps the answer theirs. Does not gather the evidence itself: the researcher agent finds what is true outside the organization, the analytics agent reads the organization's own numbers and reports them with their sources, and the forecaster agent says what a model predicts. Does not run a campaign, a launch or a published piece, which are the campaign-manager, launch-coordinator and content-manager agents, and those agents run work that has already been decided on. Does not hold the standards a decision changes, which is the standards-keeper agent, and it hands the agreed change to that agent to be versioned. Does not report how the department performed over a reporting period, which is the reporting-manager agent. Does not sign anything.
These limits are written into the job on purpose, so that everyone adopting the process knows which decisions stay with a person.
Who has built one, and how far each one got
Nobody has built one yet. The catalog says so rather than leaving the section off, because an empty list is a fact about the document.
implements: decision-coordinator v1
One line in your agent's manifest. The catalog checks it against the records your runs actually leave.
The closest things in the catalog, by description
Nobody above has claimed any of these. This is the nearest match by wording between the job written above and what publishers wrote about their own listings, closest first, and wording is not evidence: some of these will be wrong, and a job with nothing suitable still gets whatever was nearest. The publishers have never heard of this abstract agent and have promised nothing about it. What a claim looks like is in the table above, and it is signed.
Not workers. These are capability that whatever does the job would use, which is a different relationship and kept in its own column for that reason.
- CHAP Coordinator MCP server · brightbeamai.github.io · run it yourself · mirrored from the MCP registry Auditable records of human decisions over AI agent work. Approvals, edits, overrides, escalations.
- nodedex MCP server · nodedex.github.io · run it yourself · mirrored from the MCP registry Your project's decision history for agents: decisions, dead-ends, constraints - queryable, local.
- Warrant MCP server · s0fractal.github.io · run it yourself · mirrored from the MCP registry Record an agent's decisions with reasons anyone can re-execute offline — verify recomputes them.