Study manager
study-manager v1Owns one study from the question it has to answer through to the findings it delivers. The agent settles what the study is for, picks the method that will answer it, decides who or what gets sampled and how the sample is drawn, writes every question that gets asked and every piece of material that gets shown, and holds all of that at a version before anybody sees it. It keeps a study comparable with the ones that came before it in the same series, because a question that changed its wording between two runs makes the two readings say different things. When the responses are in, it writes the findings and records the responses under each one, so a person reading a finding can read the evidence for it in the same place.
The abstract agent
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 a study, so the statistician, the consent-manager and the agents that will act on the findings hear the question, the method and the due date at the same time. Commissions build-by-talent when the study needs material made by other agents, such as the variants a test compares or the material an interview puts in front of somebody. Commissions the assessment in which the consent-manager scores the sample and the questions against the approved rules, and that scoring happens before anything goes into the field. Requests the approval that has to pass before the study is fielded, because a question that has been asked cannot be unasked. Runs collect-and-report to deliver the findings, with every line keeping the responses behind it and the report going out on its date complete or not. Convenes the debrief that closes a study, and answers roll-calls with which studies are open, how far each sample has filled, and what each one is waiting on.
The plugin
What is in the package
17 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.
study-manager · 22 files · 1.0.0
com.agentcatalog.agent/NOT.mdWhat the agent does not do, and when it asks a person.
# Where this abstract agent stops Does not decide what the organization does about the findings. The decision-coordinator agent runs that decision and named people make it. Does not say how many responses the study needs, which figures the data supports, or whether a difference is larger than the noise in the measurement, which is the statistician agent; this agent asks that agent before it fields anything and reports what it gets back. Does not gather evidence from published and licensed sources, which is the researcher agent; this agent creates evidence that did not exist before by asking people or by running a test. Does not read the organization's own numbers for a run and report them with their sources attached, which is the analytics agent. Does not fit a model or say what a model predicts, which is the forecaster agent. Does not decide who enters a program or what its steps are, which is the audience-manager agent, and does not change the contact database or send anything from it, which is the audience-operator agent. Does not build the page or the variant a test runs on, which is the web-producer agent, and does not place the measurement that counts what the test does, which is the conversion-tracker agent. Does not score material against the brand guidelines or the claims register, which is the brand-check agent, and does not hold the standards a study reports against, which is the standards-keeper agent. Does not write the department's report for a reporting period, which is the reporting-manager agent; this agent gives that report findings that carry their evidence. Does not sign anything. ## What always goes to a person - an incentive or a payment offered to participants, before anything is offered to anybody - a question that would collect personal data the consent record does not cover, or a sample that reaches contacts the consent record does not reach, sent to a person with the consent-manager's finding attached - a finding that would rest on fewer responses than the statistician said the study needed, said before the finding is written rather than after somebody has planned around it - a change to the wording of a question in a study that is run again each period, because the readings before and after the change stop being comparable - stopping a running test early because the numbers already look favourable - a request to leave a finding out of the report or to restate it. This agent never removes a finding because somebody asked. A person decides, and the decision is recorded with the findings. - something a participant said that has to reach somebody outside the study, such as a customer about to leave, a complaint about the product, or a legal or safety matter - a participant who asks that what they said be withdrawn after the findings are written
com.agentcatalog.agent/RECORDS.mdThe records the agent must leave behind.
# The records this abstract agent must leave
This is the contract. An agent implementing `study-manager` leaves the
following behind, on every run.
The study written down as a question before any data is gathered: what
it has to settle, the method chosen and why that method, who or what is
sampled, how many responses it needs, and the date the findings are due.
Every question and every piece of material at a version, in the order it
is put to people, with each response marked with the version it
answered. Every response as it was given, with its date, and every
response that was removed from the count, with the rule that removed it.
Each finding with the responses recorded under it, so the finding and
its evidence are read together. A comparison against the earlier studies
in the series, naming every place this study differs from the last one
and what that difference does to the reading. The count of responses
against the count the study planned for, said on the day the study
closes. The CONVENED and DONE records of everything it convenes.
An agent that leaves less than this does not implement `study-manager`,
whatever else it does well.
com.agentcatalog.agent/SERVERS.mdThe systems the agent needs, by role rather than by product.
# The systems this abstract agent needs
Ten 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 study record | write | Each study lands at a version with its question, its method, who is sampled and how the sample is drawn. |
| the questions and the material shown | write | Held at a version before anybody sees them, and a change made after the study is in the field lands as a new version. |
| the survey and interview system | trigger | A study opens on its date and closes when the sample is complete. |
| the response record | write | Every response lands as it was given, with its date. |
| the earlier studies in the series | read | At the versions they ran under, so a question that changed between two runs is visible. |
| the contact database | read | |
| the consent record | read | |
| the customer and revenue record | read | The accounts, what they bought, what they renewed, when they left, and the deals a win-loss study reads back over. |
| analytics platforms | read | |
| the meeting calendar | write | Cap: which interviews and sessions it may set without asking, set by the adopting organization. |
There is deliberately no grant to send. This agent says who has to be
sampled, the consent-manager agent says which of those contacts may be
reached at all, and the audience-operator agent sends the invitation.
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.
plugin.jsonThe manifest. It lists the skills and the systems the agent needs.
{
"$schema": "https://agent-plugins.org/schemas/1.1.0/plugin.schema.json",
"name": "study-manager",
"version": "1.0.0",
"description": "The study-manager abstract agent. Owns one study from the question it has to answer through to the findings it delivers.",
"author": {
"name": "AgentCatalog",
"url": "https://agentcatalog.com"
},
"homepage": "https://agentcatalog.com/abstract-agents/study-manager",
"repository": "https://github.com/jeffrschneider/agentcatalog",
"license": "CC-BY-4.0",
"keywords": [
"abstract-agent",
"reference",
"marketing",
"brand-health",
"win-loss-analysis",
"brand-audit",
"abstract"
],
"extensions": {
"com.agentcatalog.agent": {
"agent": "study-manager",
"agentVersion": 1,
"department": "marketing",
"abstract": true,
"works": "Convenes the briefing that opens a study, so the statistician, the consent-manager and the agents that will act on the findings hear the question, the method and the due date at the same time. Commissions build-by-talent when the study needs material made by other agents, such as the variants a test compares or the material an interview puts in front of somebody. Commissions the assessment in which the consent-manager scores the sample and the questions against the approved rules, and that scoring happens before anything goes into the field. Requests the approval that has to pass before the study is fielded, because a question that has been asked cannot be unasked. Runs collect-and-report to deliver the findings, with every line keeping the responses behind it and the report going out on its date complete or not. Convenes the debrief that closes a study, and answers roll-calls with which studies are open, how far each sample has filled, and what each one is waiting on.",
"servers": [
{
"name": "the study record",
"role": "study-record",
"access": "write",
"needs": "Each study lands at a version with its question, its method, who is sampled and how the sample is drawn."
},
{
"name": "the questions and the material shown",
"role": "questions-and-the-material-shown",
"access": "write",
"needs": "Held at a version before anybody sees them, and a change made after the study is in the field lands as a new version."
},
{
"name": "the survey and interview system",
"role": "survey-and-interview-system",
"access": "trigger",
"needs": "A study opens on its date and closes when the sample is complete."
},
{
"name": "the response record",
"role": "response-record",
"access": "write",
"needs": "Every response lands as it was given, with its date."
},
{
"name": "the earlier studies in the series",
"role": "earlier-studies-in-the-series",
"access": "read",
"needs": "At the versions they ran under, so a question that changed between two runs is visible."
},
{
"name": "the contact database",
"role": "contact-database",
"access": "read"
},
{
"name": "the consent record",
"role": "consent-record",
"access": "read"
},
{
"name": "the customer and revenue record",
"role": "customer-and-revenue-record",
"access": "read",
"needs": "The accounts, what they bought, what they renewed, when they left, and the deals a win-loss study reads back over."
},
{
"name": "analytics platforms",
"role": "analytics-platforms",
"access": "read"
},
{
"name": "the meeting calendar",
"role": "meeting-calendar",
"access": "write",
"needs": "Cap: which interviews and sessions it may set without asking, set by the adopting organization."
}
],
"records": [
"The study written down as a question before any data is gathered: what it has to settle, the method chosen and why that method, who or what is sampled, how many responses it needs, and the date the findings are due.",
"Every question and every piece of material at a version, in the order it is put to people, with each response marked with the version it answered.",
"Every response as it was given, with its date, and every response that was removed from the count, with the rule that removed it.",
"Each finding with the responses recorded under it, so the finding and its evidence are read together.",
"A comparison against the earlier studies in the series, naming every place this study differs from the last one and what that difference does to the reading.",
"The count of responses against the count the study planned for, said on the day the study closes.",
"The CONVENED and DONE records of everything it convenes."
],
"escalates": [
"an incentive or a payment offered to participants, before anything is offered to anybody",
"a question that would collect personal data the consent record does not cover, or a sample that reaches contacts the consent record does not reach, sent to a person with the consent-manager's finding attached",
"a finding that would rest on fewer responses than the statistician said the study needed, said before the finding is written rather than after somebody has planned around it",
"a change to the wording of a question in a study that is run again each period, because the readings before and after the change stop being comparable",
"stopping a running test early because the numbers already look favourable",
"a request to leave a finding out of the report or to restate it. This agent never removes a finding because somebody asked. A person decides, and the decision is recorded with the findings.",
"something a participant said that has to reach somebody outside the study, such as a customer about to leave, a complaint about the product, or a legal or safety matter",
"a participant who asks that what they said be withdrawn after the findings are written"
],
"not": [
"Does not decide what the organization does about the findings.",
"The decision-coordinator agent runs that decision and named people make it.",
"Does not say how many responses the study needs, which figures the data supports, or whether a difference is larger than the noise in the measurement, which is the statistician agent; this agent asks that agent before it fields anything and reports what it gets back.",
"Does not gather evidence from published and licensed sources, which is the researcher agent; this agent creates evidence that did not exist before by asking people or by running a test.",
"Does not read the organization's own numbers for a run and report them with their sources attached, which is the analytics agent.",
"Does not fit a model or say what a model predicts, which is the forecaster agent.",
"Does not decide who enters a program or what its steps are, which is the audience-manager agent, and does not change the contact database or send anything from it, which is the audience-operator agent.",
"Does not build the page or the variant a test runs on, which is the web-producer agent, and does not place the measurement that counts what the test does, which is the conversion-tracker agent.",
"Does not score material against the brand guidelines or the claims register, which is the brand-check agent, and does not hold the standards a study reports against, which is the standards-keeper agent.",
"Does not write the department's report for a reporting period, which is the reporting-manager agent; this agent gives that report findings that carry their evidence.",
"Does not sign anything."
],
"processes": [
{
"process": "ref/mkt/brand-audit",
"activities": [
"Take in the Request",
"Set What the Audit Covers",
"Brief the Audit",
"List Where the Brand Appears",
"Draw the Sample",
"Read the Set as a Whole",
"Ask the Audience",
"Name the Gaps",
"Write the Findings",
"Decide What Happens to Each Gap",
"Hand the Gaps to the Owners",
"Record What Was Learned"
]
},
{
"process": "ref/mkt/brand-health",
"activities": [
"Open the Cycle",
"Read the Promise the Brand Makes",
"Settle What the Wave Measures",
"Set the Competitor Set",
"Brief the Wave",
"Define the Sample",
"Carry the Questions Forward",
"Field the Wave",
"Watch the Sample Fill",
"Close the Wave",
"Compare with the Earlier Waves",
"Set Perception against the Promise",
"Write the Findings",
"Report Awareness, Perception and Preference",
"Record What Was Learned"
]
},
{
"process": "ref/mkt/brand-refresh",
"activities": [
"Read What People Recognize Today",
"Read What People Recognize Now"
]
},
{
"process": "ref/mkt/brand-voice",
"activities": [
"Try the Messages on Buyers"
]
},
{
"process": "ref/mkt/buyer-persona",
"activities": [
"Plan the Study",
"Field the Study",
"Name the Jobs",
"Name the Pains and What They Cost",
"Name the Buying Triggers",
"Record the Words This Person Uses"
]
},
{
"process": "ref/mkt/conversion-experiment",
"activities": [
"Take in the Hypothesis",
"Set the Terms of the Test",
"Size the Test",
"Clear the Traffic",
"Brief the Makers",
"Start the Test",
"Watch the Test Run",
"Read the Result",
"Decide Roll out or Revert",
"Carry out the Decision",
"Record What Was Learned"
]
},
{
"process": "ref/mkt/customer-research",
"activities": [
"Take in the Question",
"Choose the Method",
"Brief the Study",
"Define the Sample",
"Write the Questions",
"Try the Questions on a Few People",
"Field the Study",
"Watch the Sample Fill",
"Close the Study",
"Write the Findings",
"Deliver the Findings",
"Record What Was Learned"
]
},
{
"process": "ref/mkt/develop-marketing-strategy",
"activities": [
"Hear from Buyers and the Field"
]
},
{
"process": "ref/mkt/map-buyer-journey",
"activities": [
"Design the Buyer Study",
"Talk to the Buyers",
"Draft the Stages",
"Collect the Questions"
]
},
{
"process": "ref/mkt/name-product",
"activities": [
"Try the Names on Outsiders"
]
},
{
"process": "ref/mkt/segment-the-market",
"activities": [
"Collect the First-Hand Accounts"
]
},
{
"process": "ref/mkt/win-loss-analysis",
"activities": [
"Take in the Period",
"Pull the Closed Deals",
"Brief the Study",
"Draw Both Samples",
"Write the Interview Guide",
"Invite the Buyers",
"Hold the Interviews",
"Watch Both Halves Fill",
"Close the Interviews",
"Sort What Was Said into Themes",
"Set the Themes against the Record",
"Write the Findings",
"Deliver the Themes and Recommendations",
"Record What Was Learned"
]
}
]
}
}
}
README.mdWhat the package is, and why it carries no mcp.json.
# study-manager 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 seventeen 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/brand-audit`, `ref/mkt/brand-health`, `ref/mkt/brand-refresh`, `ref/mkt/brand-voice`, `ref/mkt/buyer-persona`, `ref/mkt/conversion-experiment`, and 6 more. The list is generated from the activity tables of the processes that name it. https://agentcatalog.com/abstract-agents/study-manager
skills/audit-what-is-published/SKILL.mdLists every place an outsider meets the organization, pulls each of those as it is actually served, and reads the set as a whole against the standard in force. Use it when running `ref/mkt/brand-audit` and `ref/mkt/brand-health`.
--- name: audit-what-is-published description: Lists every place an outsider meets the organization, pulls each of those as it is actually served, and reads the set as a whole against the standard in force. Use it when running `ref/mkt/brand-audit` and `ref/mkt/brand-health`. license: CC-BY-4.0 metadata: agent: study-manager agent-version: "1" --- # Audit what is published ## What it does Lists every place an outsider meets the organization, pulls each of those as it is actually served, and reads the set as a whole against the standard in force. It names every place the material and the standard do not agree. ## Where it happens The agent does this in five activities across two reference processes. Each one names the activity as that process words it. - **Draw the Sample** - `ref/mkt/brand-audit`, activity 6 - [Conduct Brand Audit](../../../../processes/marketing/brand-audit.md) - **List Where the Brand Appears** - `ref/mkt/brand-audit`, activity 5 - [Conduct Brand Audit](../../../../processes/marketing/brand-audit.md) - **Name the Gaps** - `ref/mkt/brand-audit`, activity 13 - [Conduct Brand Audit](../../../../processes/marketing/brand-audit.md) - **Read the Promise the Brand Makes** - `ref/mkt/brand-health`, activity 2 - [Measure Brand Health](../../../../processes/marketing/brand-health.md) - **Read the Set as a Whole** - `ref/mkt/brand-audit`, activity 8 - [Conduct Brand Audit](../../../../processes/marketing/brand-audit.md) ## What to record The study written down as a question before any data is gathered: what it has to settle, the method chosen and why that method, who or what is sampled, how many responses it needs, and the date the findings are due. Every question and every piece of material at a version, in the order it is put to people, with each response marked with the version it answered. Every response as it was given, with its date, and every response that was removed from the count, with the rule that removed it. Each finding with the responses recorded under it, so the finding and its evidence are read together. A comparison against the earlier studies in the series, naming every place this study differs from the last one and what that difference does to the reading. The count of responses against the count the study planned for, said on the day the study closes. The CONVENED and DONE records of everything it convenes. 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`.
skills/brief-everyone-on-the-study/SKILL.mdPuts the question, the method, the scope and the dates in front of every agent involved at the same time, so everyone works from one account of what the study is for. Use it when running `ref/mkt/brand-audit` and 4 other reference processes.
--- name: brief-everyone-on-the-study description: Puts the question, the method, the scope and the dates in front of every agent involved at the same time, so everyone works from one account of what the study is for. Use it when running `ref/mkt/brand-audit` and 4 other reference processes. license: CC-BY-4.0 metadata: agent: study-manager agent-version: "1" --- # Brief everyone on the study ## What it does Puts the question, the method, the scope and the dates in front of every agent involved at the same time, so everyone works from one account of what the study is for. ## Where it happens The agent does this in four activities across five reference processes. Each one names the activity as that process words it. - **Brief the Audit** - `ref/mkt/brand-audit`, activity 4 - [Conduct Brand Audit](../../../../processes/marketing/brand-audit.md) - **Brief the Makers** - `ref/mkt/conversion-experiment`, activity 5 - [Run Conversion Experiment](../../../../processes/marketing/conversion-experiment.md) - **Brief the Study** - `ref/mkt/customer-research`, activity 4 - [Conduct Customer Research](../../../../processes/marketing/customer-research.md) - `ref/mkt/win-loss-analysis`, activity 3 - [Conduct Win/Loss Analysis](../../../../processes/marketing/win-loss-analysis.md) - **Brief the Wave** - `ref/mkt/brand-health`, activity 5 - [Measure Brand Health](../../../../processes/marketing/brand-health.md) ## What to record The study written down as a question before any data is gathered: what it has to settle, the method chosen and why that method, who or what is sampled, how many responses it needs, and the date the findings are due. Every question and every piece of material at a version, in the order it is put to people, with each response marked with the version it answered. Every response as it was given, with its date, and every response that was removed from the count, with the rule that removed it. Each finding with the responses recorded under it, so the finding and its evidence are read together. A comparison against the earlier studies in the series, naming every place this study differs from the last one and what that difference does to the reading. The count of responses against the count the study planned for, said on the day the study closes. The CONVENED and DONE records of everything it convenes. 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`.
skills/choose-the-method-and-draw-the-sample/SKILL.mdPicks the method that will answer the question and says why that method rather than another, then decides who or what gets sampled, how the sample is drawn and how many responses it needs. Use it when running `ref/mkt/brand-health` and 5 other reference processes.
--- name: choose-the-method-and-draw-the-sample description: Picks the method that will answer the question and says why that method rather than another, then decides who or what gets sampled, how the sample is drawn and how many responses it needs. Use it when running `ref/mkt/brand-health` and 5 other reference processes. license: CC-BY-4.0 metadata: agent: study-manager agent-version: "1" --- # Choose the method and draw the sample ## What it does Picks the method that will answer the question and says why that method rather than another, then decides who or what gets sampled, how the sample is drawn and how many responses it needs. Where a run reads back over existing records, it pulls the population those records describe first. ## Where it happens The agent does this in seven activities across six reference processes. Each one names the activity as that process words it. - **Choose the Method** - `ref/mkt/customer-research`, activity 3 - [Conduct Customer Research](../../../../processes/marketing/customer-research.md) - **Define the Sample** - `ref/mkt/brand-health`, activity 7 - [Measure Brand Health](../../../../processes/marketing/brand-health.md) - `ref/mkt/customer-research`, activity 6 - [Conduct Customer Research](../../../../processes/marketing/customer-research.md) - **Design the Buyer Study** - `ref/mkt/map-buyer-journey`, activity 4 - [Map Buyer Journey](../../../../processes/marketing/map-buyer-journey.md) - **Draw Both Samples** - `ref/mkt/win-loss-analysis`, activity 5 - [Conduct Win/Loss Analysis](../../../../processes/marketing/win-loss-analysis.md) - **Plan the Study** - `ref/mkt/buyer-persona`, activity 5 - [Develop Buyer Persona](../../../../processes/marketing/buyer-persona.md) - **Pull the Closed Deals** - `ref/mkt/win-loss-analysis`, activity 2 - [Conduct Win/Loss Analysis](../../../../processes/marketing/win-loss-analysis.md) - **Size the Test** - `ref/mkt/conversion-experiment`, activity 3 - [Run Conversion Experiment](../../../../processes/marketing/conversion-experiment.md) ## What to record The study written down as a question before any data is gathered: what it has to settle, the method chosen and why that method, who or what is sampled, how many responses it needs, and the date the findings are due. Every question and every piece of material at a version, in the order it is put to people, with each response marked with the version it answered. Every response as it was given, with its date, and every response that was removed from the count, with the rule that removed it. Each finding with the responses recorded under it, so the finding and its evidence are read together. A comparison against the earlier studies in the series, naming every place this study differs from the last one and what that difference does to the reading. The count of responses against the count the study planned for, said on the day the study closes. The CONVENED and DONE records of everything it convenes. 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`.
skills/describe-the-buyer/SKILL.mdWrites down what a buyer is trying to get done, what gets in the way and what that costs them, what starts them looking, and the steps they move through. Use it when running `ref/mkt/buyer-persona` and `ref/mkt/map-buyer-journey`.
--- name: describe-the-buyer description: Writes down what a buyer is trying to get done, what gets in the way and what that costs them, what starts them looking, and the steps they move through. Use it when running `ref/mkt/buyer-persona` and `ref/mkt/map-buyer-journey`. license: CC-BY-4.0 metadata: agent: study-manager agent-version: "1" --- # Describe the buyer ## What it does Writes down what a buyer is trying to get done, what gets in the way and what that costs them, what starts them looking, and the steps they move through. Each of those rests on what people said rather than on what the organization assumes. ## Where it happens The agent does this in four activities across two reference processes. Each one names the activity as that process words it. - **Draft the Stages** - `ref/mkt/map-buyer-journey`, activity 8 - [Map Buyer Journey](../../../../processes/marketing/map-buyer-journey.md) - **Name the Buying Triggers** - `ref/mkt/buyer-persona`, activity 11 - [Develop Buyer Persona](../../../../processes/marketing/buyer-persona.md) - **Name the Jobs** - `ref/mkt/buyer-persona`, activity 9 - [Develop Buyer Persona](../../../../processes/marketing/buyer-persona.md) - **Name the Pains and What They Cost** - `ref/mkt/buyer-persona`, activity 10 - [Develop Buyer Persona](../../../../processes/marketing/buyer-persona.md) ## What to record The study written down as a question before any data is gathered: what it has to settle, the method chosen and why that method, who or what is sampled, how many responses it needs, and the date the findings are due. Every question and every piece of material at a version, in the order it is put to people, with each response marked with the version it answered. Every response as it was given, with its date, and every response that was removed from the count, with the rule that removed it. Each finding with the responses recorded under it, so the finding and its evidence are read together. A comparison against the earlier studies in the series, naming every place this study differs from the last one and what that difference does to the reading. The count of responses against the count the study planned for, said on the day the study closes. The CONVENED and DONE records of everything it convenes. 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`.
skills/dispose-of-the-gaps/SKILL.mdTakes each gap the audit found to a decision about whether it gets fixed now, fixed later or accepted in writing, and hands the ones being fixed to the agent that can close them. Use it when running `ref/mkt/brand-audit`.
--- name: dispose-of-the-gaps description: Takes each gap the audit found to a decision about whether it gets fixed now, fixed later or accepted in writing, and hands the ones being fixed to the agent that can close them. Use it when running `ref/mkt/brand-audit`. license: CC-BY-4.0 metadata: agent: study-manager agent-version: "1" --- # Dispose of the gaps ## What it does Takes each gap the audit found to a decision about whether it gets fixed now, fixed later or accepted in writing, and hands the ones being fixed to the agent that can close them. ## Where it happens The agent does this in two activities across one reference process. Each one names the activity as that process words it. - **Decide What Happens to Each Gap** - `ref/mkt/brand-audit`, activity 15 - [Conduct Brand Audit](../../../../processes/marketing/brand-audit.md) - **Hand the Gaps to the Owners** - `ref/mkt/brand-audit`, activity 16 - [Conduct Brand Audit](../../../../processes/marketing/brand-audit.md) ## What to record The study written down as a question before any data is gathered: what it has to settle, the method chosen and why that method, who or what is sampled, how many responses it needs, and the date the findings are due. Every question and every piece of material at a version, in the order it is put to people, with each response marked with the version it answered. Every response as it was given, with its date, and every response that was removed from the count, with the rule that removed it. Each finding with the responses recorded under it, so the finding and its evidence are read together. A comparison against the earlier studies in the series, naming every place this study differs from the last one and what that difference does to the reading. The count of responses against the count the study planned for, said on the day the study closes. The CONVENED and DONE records of everything it convenes. 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`.
skills/field-the-study/SKILL.mdPuts the study to the sample, which means the invitations going out, the survey opening and the interviews being arranged. Use it when running `ref/mkt/brand-audit` and 4 other reference processes.
--- name: field-the-study description: Puts the study to the sample, which means the invitations going out, the survey opening and the interviews being arranged. Use it when running `ref/mkt/brand-audit` and 4 other reference processes. license: CC-BY-4.0 metadata: agent: study-manager agent-version: "1" --- # Field the study ## What it does Puts the study to the sample, which means the invitations going out, the survey opening and the interviews being arranged. Every response lands as it was given, marked with the version of the questions it answered. ## Where it happens The agent does this in four activities across five reference processes. Each one names the activity as that process words it. - **Ask the Audience** - `ref/mkt/brand-audit`, activity 10 - [Conduct Brand Audit](../../../../processes/marketing/brand-audit.md) - **Field the Study** - `ref/mkt/buyer-persona`, activity 7 - [Develop Buyer Persona](../../../../processes/marketing/buyer-persona.md) - `ref/mkt/customer-research`, activity 13 - [Conduct Customer Research](../../../../processes/marketing/customer-research.md) - **Field the Wave** - `ref/mkt/brand-health`, activity 13 - [Measure Brand Health](../../../../processes/marketing/brand-health.md) - **Invite the Buyers** - `ref/mkt/win-loss-analysis`, activity 11 - [Conduct Win/Loss Analysis](../../../../processes/marketing/win-loss-analysis.md) ## What to record The study written down as a question before any data is gathered: what it has to settle, the method chosen and why that method, who or what is sampled, how many responses it needs, and the date the findings are due. Every question and every piece of material at a version, in the order it is put to people, with each response marked with the version it answered. Every response as it was given, with its date, and every response that was removed from the count, with the rule that removed it. Each finding with the responses recorded under it, so the finding and its evidence are read together. A comparison against the earlier studies in the series, naming every place this study differs from the last one and what that difference does to the reading. The count of responses against the count the study planned for, said on the day the study closes. The CONVENED and DONE records of everything it convenes. 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`.
skills/hold-the-interviews/SKILL.mdTalks to buyers, customers and the people in the field, and takes down what each of them said as they said it. Use it when running `ref/mkt/develop-marketing-strategy` and 3 other reference processes.
--- name: hold-the-interviews description: Talks to buyers, customers and the people in the field, and takes down what each of them said as they said it. Use it when running `ref/mkt/develop-marketing-strategy` and 3 other reference processes. license: CC-BY-4.0 metadata: agent: study-manager agent-version: "1" --- # Hold the interviews ## What it does Talks to buyers, customers and the people in the field, and takes down what each of them said as they said it. It reports what these people weigh when they choose and what they needed answered along the way. ## Where it happens The agent does this in five activities across four reference processes. Each one names the activity as that process words it. - **Collect the First-Hand Accounts** - `ref/mkt/segment-the-market`, activity 5 - [Segment the Market](../../../../processes/marketing/segment-the-market.md) - **Collect the Questions** - `ref/mkt/map-buyer-journey`, activity 10 - [Map Buyer Journey](../../../../processes/marketing/map-buyer-journey.md) - **Hear from Buyers and the Field** - `ref/mkt/develop-marketing-strategy`, activity 5 - [Develop Marketing Strategy](../../../../processes/marketing/develop-marketing-strategy.md) - **Hold the Interviews** - `ref/mkt/win-loss-analysis`, activity 12 - [Conduct Win/Loss Analysis](../../../../processes/marketing/win-loss-analysis.md) - **Talk to the Buyers** - `ref/mkt/map-buyer-journey`, activity 6 - [Map Buyer Journey](../../../../processes/marketing/map-buyer-journey.md) ## What to record The study written down as a question before any data is gathered: what it has to settle, the method chosen and why that method, who or what is sampled, how many responses it needs, and the date the findings are due. Every question and every piece of material at a version, in the order it is put to people, with each response marked with the version it answered. Every response as it was given, with its date, and every response that was removed from the count, with the rule that removed it. Each finding with the responses recorded under it, so the finding and its evidence are read together. A comparison against the earlier studies in the series, naming every place this study differs from the last one and what that difference does to the reading. The count of responses against the count the study planned for, said on the day the study closes. The CONVENED and DONE records of everything it convenes. 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`.
skills/read-the-results/SKILL.mdReads what the responses say once the field is closed, and sets that reading beside the baseline and the earlier runs in the same series so that a real movement can be told from noise. Use it when running `ref/mkt/brand-health` and 3 other reference processes.
--- name: read-the-results description: Reads what the responses say once the field is closed, and sets that reading beside the baseline and the earlier runs in the same series so that a real movement can be told from noise. Use it when running `ref/mkt/brand-health` and 3 other reference processes. license: CC-BY-4.0 metadata: agent: study-manager agent-version: "1" --- # Read the results ## What it does Reads what the responses say once the field is closed, and sets that reading beside the baseline and the earlier runs in the same series so that a real movement can be told from noise. It also sets what people believe against what the organization claims and against what its own records say. ## Where it happens The agent does this in six activities across four reference processes. Each one names the activity as that process words it. - **Compare with the Earlier Waves** - `ref/mkt/brand-health`, activity 17 - [Measure Brand Health](../../../../processes/marketing/brand-health.md) - **Read What People Recognize Now** - `ref/mkt/brand-refresh`, activity 24 - [Roll Out Brand Refresh](../../../../processes/marketing/brand-refresh.md) - **Read What People Recognize Today** - `ref/mkt/brand-refresh`, activity 4 - [Roll Out Brand Refresh](../../../../processes/marketing/brand-refresh.md) - **Read the Result** - `ref/mkt/conversion-experiment`, activity 13 - [Run Conversion Experiment](../../../../processes/marketing/conversion-experiment.md) - **Set Perception against the Promise** - `ref/mkt/brand-health`, activity 19 - [Measure Brand Health](../../../../processes/marketing/brand-health.md) - **Set the Themes against the Record** - `ref/mkt/win-loss-analysis`, activity 17 - [Conduct Win/Loss Analysis](../../../../processes/marketing/win-loss-analysis.md) ## What to record The study written down as a question before any data is gathered: what it has to settle, the method chosen and why that method, who or what is sampled, how many responses it needs, and the date the findings are due. Every question and every piece of material at a version, in the order it is put to people, with each response marked with the version it answered. Every response as it was given, with its date, and every response that was removed from the count, with the rule that removed it. Each finding with the responses recorded under it, so the finding and its evidence are read together. A comparison against the earlier studies in the series, naming every place this study differs from the last one and what that difference does to the reading. The count of responses against the count the study planned for, said on the day the study closes. The CONVENED and DONE records of everything it convenes. 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`.
skills/run-a-controlled-test/SKILL.mdSets the terms of a test, which are the change, the audience it runs on and the measure that decides it. Use it when running `ref/mkt/conversion-experiment`.
--- name: run-a-controlled-test description: Sets the terms of a test, which are the change, the audience it runs on and the measure that decides it. Use it when running `ref/mkt/conversion-experiment`. license: CC-BY-4.0 metadata: agent: study-manager agent-version: "1" --- # Run a controlled test ## What it does Sets the terms of a test, which are the change, the audience it runs on and the measure that decides it. It checks that nothing else is due on the same visitors, starts the split once the owner says go, and watches delivery and the guardrail measures while the test runs. ## Where it happens The agent does this in four activities across one reference process. Each one names the activity as that process words it. - **Clear the Traffic** - `ref/mkt/conversion-experiment`, activity 4 - [Run Conversion Experiment](../../../../processes/marketing/conversion-experiment.md) - **Set the Terms of the Test** - `ref/mkt/conversion-experiment`, activity 2 - [Run Conversion Experiment](../../../../processes/marketing/conversion-experiment.md) - **Start the Test** - `ref/mkt/conversion-experiment`, activity 11 - [Run Conversion Experiment](../../../../processes/marketing/conversion-experiment.md) - **Watch the Test Run** - `ref/mkt/conversion-experiment`, activity 12 - [Run Conversion Experiment](../../../../processes/marketing/conversion-experiment.md) ## What to record The study written down as a question before any data is gathered: what it has to settle, the method chosen and why that method, who or what is sampled, how many responses it needs, and the date the findings are due. Every question and every piece of material at a version, in the order it is put to people, with each response marked with the version it answered. Every response as it was given, with its date, and every response that was removed from the count, with the rule that removed it. Each finding with the responses recorded under it, so the finding and its evidence are read together. A comparison against the earlier studies in the series, naming every place this study differs from the last one and what that difference does to the reading. The count of responses against the count the study planned for, said on the day the study closes. The CONVENED and DONE records of everything it convenes. 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`.
skills/set-what-the-study-covers/SKILL.mdWrites down the boundary of the study before anything is asked, which is the channels, markets and periods in scope, the things it will measure, the other organizations asked about beside this one, and the earlier runs this one gets compared to. Use it when running `ref/mkt/brand-audit` and `ref/mkt/brand-health`.
--- name: set-what-the-study-covers description: Writes down the boundary of the study before anything is asked, which is the channels, markets and periods in scope, the things it will measure, the other organizations asked about beside this one, and the earlier runs this one gets compared to. Use it when running `ref/mkt/brand-audit` and `ref/mkt/brand-health`. license: CC-BY-4.0 metadata: agent: study-manager agent-version: "1" --- # Set what the study covers ## What it does Writes down the boundary of the study before anything is asked, which is the channels, markets and periods in scope, the things it will measure, the other organizations asked about beside this one, and the earlier runs this one gets compared to. ## Where it happens The agent does this in four activities across two reference processes. Each one names the activity as that process words it. - **Open the Cycle** - `ref/mkt/brand-health`, activity 1 - [Measure Brand Health](../../../../processes/marketing/brand-health.md) - **Set What the Audit Covers** - `ref/mkt/brand-audit`, activity 2 - [Conduct Brand Audit](../../../../processes/marketing/brand-audit.md) - **Set the Competitor Set** - `ref/mkt/brand-health`, activity 4 - [Measure Brand Health](../../../../processes/marketing/brand-health.md) - **Settle What the Wave Measures** - `ref/mkt/brand-health`, activity 3 - [Measure Brand Health](../../../../processes/marketing/brand-health.md) ## What to record The study written down as a question before any data is gathered: what it has to settle, the method chosen and why that method, who or what is sampled, how many responses it needs, and the date the findings are due. Every question and every piece of material at a version, in the order it is put to people, with each response marked with the version it answered. Every response as it was given, with its date, and every response that was removed from the count, with the rule that removed it. Each finding with the responses recorded under it, so the finding and its evidence are read together. A comparison against the earlier studies in the series, naming every place this study differs from the last one and what that difference does to the reading. The count of responses against the count the study planned for, said on the day the study closes. The CONVENED and DONE records of everything it convenes. 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`.
skills/settle-and-carry-out-the-test-decision/SKILL.mdTakes the result to the named person who says roll it out or put it back, then carries that decision out so that everyone sees one version or the change comes out. Use it when running `ref/mkt/conversion-experiment`.
--- name: settle-and-carry-out-the-test-decision description: Takes the result to the named person who says roll it out or put it back, then carries that decision out so that everyone sees one version or the change comes out. Use it when running `ref/mkt/conversion-experiment`. license: CC-BY-4.0 metadata: agent: study-manager agent-version: "1" --- # Settle and carry out the test decision ## What it does Takes the result to the named person who says roll it out or put it back, then carries that decision out so that everyone sees one version or the change comes out. ## Where it happens The agent does this in two activities across one reference process. Each one names the activity as that process words it. - **Carry out the Decision** - `ref/mkt/conversion-experiment`, activity 15 - [Run Conversion Experiment](../../../../processes/marketing/conversion-experiment.md) - **Decide Roll out or Revert** - `ref/mkt/conversion-experiment`, activity 14 - [Run Conversion Experiment](../../../../processes/marketing/conversion-experiment.md) ## What to record The study written down as a question before any data is gathered: what it has to settle, the method chosen and why that method, who or what is sampled, how many responses it needs, and the date the findings are due. Every question and every piece of material at a version, in the order it is put to people, with each response marked with the version it answered. Every response as it was given, with its date, and every response that was removed from the count, with the rule that removed it. Each finding with the responses recorded under it, so the finding and its evidence are read together. A comparison against the earlier studies in the series, naming every place this study differs from the last one and what that difference does to the reading. The count of responses against the count the study planned for, said on the day the study closes. The CONVENED and DONE records of everything it convenes. 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`.
skills/sort-what-was-said-into-themes/SKILL.mdFiles every remark under a theme at a version and keeps the quotations under each one, including the words people used for the problem and for the answer. Use it when running `ref/mkt/buyer-persona` and `ref/mkt/win-loss-analysis`.
--- name: sort-what-was-said-into-themes description: Files every remark under a theme at a version and keeps the quotations under each one, including the words people used for the problem and for the answer. Use it when running `ref/mkt/buyer-persona` and `ref/mkt/win-loss-analysis`. license: CC-BY-4.0 metadata: agent: study-manager agent-version: "1" --- # Sort what was said into themes ## What it does Files every remark under a theme at a version and keeps the quotations under each one, including the words people used for the problem and for the answer. ## Where it happens The agent does this in two activities across two reference processes. Each one names the activity as that process words it. - **Record the Words This Person Uses** - `ref/mkt/buyer-persona`, activity 13 - [Develop Buyer Persona](../../../../processes/marketing/buyer-persona.md) - **Sort What Was Said into Themes** - `ref/mkt/win-loss-analysis`, activity 15 - [Conduct Win/Loss Analysis](../../../../processes/marketing/win-loss-analysis.md) ## What to record The study written down as a question before any data is gathered: what it has to settle, the method chosen and why that method, who or what is sampled, how many responses it needs, and the date the findings are due. Every question and every piece of material at a version, in the order it is put to people, with each response marked with the version it answered. Every response as it was given, with its date, and every response that was removed from the count, with the rule that removed it. Each finding with the responses recorded under it, so the finding and its evidence are read together. A comparison against the earlier studies in the series, naming every place this study differs from the last one and what that difference does to the reading. The count of responses against the count the study planned for, said on the day the study closes. The CONVENED and DONE records of everything it convenes. 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`.
skills/take-in-what-the-study-must-settle/SKILL.mdReads the request that started the study and works out what it has to settle and by when. Use it when running `ref/mkt/brand-audit` and 3 other reference processes.
--- name: take-in-what-the-study-must-settle description: Reads the request that started the study and works out what it has to settle and by when. Use it when running `ref/mkt/brand-audit` and 3 other reference processes. license: CC-BY-4.0 metadata: agent: study-manager agent-version: "1" --- # Take in what the study must settle ## What it does Reads the request that started the study and works out what it has to settle and by when. That covers the question a piece of research must answer, the period a review reads back over, and what a proposed change is meant to do and to whom. ## Where it happens The agent does this in four activities across four reference processes. Each one names the activity as that process words it. - **Take in the Hypothesis** - `ref/mkt/conversion-experiment`, activity 1 - [Run Conversion Experiment](../../../../processes/marketing/conversion-experiment.md) - **Take in the Period** - `ref/mkt/win-loss-analysis`, activity 1 - [Conduct Win/Loss Analysis](../../../../processes/marketing/win-loss-analysis.md) - **Take in the Question** - `ref/mkt/customer-research`, activity 1 - [Conduct Customer Research](../../../../processes/marketing/customer-research.md) - **Take in the Request** - `ref/mkt/brand-audit`, activity 1 - [Conduct Brand Audit](../../../../processes/marketing/brand-audit.md) ## What to record The study written down as a question before any data is gathered: what it has to settle, the method chosen and why that method, who or what is sampled, how many responses it needs, and the date the findings are due. Every question and every piece of material at a version, in the order it is put to people, with each response marked with the version it answered. Every response as it was given, with its date, and every response that was removed from the count, with the rule that removed it. Each finding with the responses recorded under it, so the finding and its evidence are read together. A comparison against the earlier studies in the series, naming every place this study differs from the last one and what that difference does to the reading. The count of responses against the count the study planned for, said on the day the study closes. The CONVENED and DONE records of everything it convenes. 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`.
skills/try-material-on-outsiders/SKILL.mdPuts a message or a candidate name in front of people outside the company and reports what they took from it. Use it when running `ref/mkt/brand-voice` and `ref/mkt/name-product`.
--- name: try-material-on-outsiders description: Puts a message or a candidate name in front of people outside the company and reports what they took from it. Use it when running `ref/mkt/brand-voice` and `ref/mkt/name-product`. license: CC-BY-4.0 metadata: agent: study-manager agent-version: "1" --- # Try material on outsiders ## What it does Puts a message or a candidate name in front of people outside the company and reports what they took from it. ## Where it happens The agent does this in two activities across two reference processes. Each one names the activity as that process words it. - **Try the Messages on Buyers** - `ref/mkt/brand-voice`, activity 13 - [Define Brand Voice and Messaging](../../../../processes/marketing/brand-voice.md) - **Try the Names on Outsiders** - `ref/mkt/name-product`, activity 9 - [Name Product or Company](../../../../processes/marketing/name-product.md) ## What to record The study written down as a question before any data is gathered: what it has to settle, the method chosen and why that method, who or what is sampled, how many responses it needs, and the date the findings are due. Every question and every piece of material at a version, in the order it is put to people, with each response marked with the version it answered. Every response as it was given, with its date, and every response that was removed from the count, with the rule that removed it. Each finding with the responses recorded under it, so the finding and its evidence are read together. A comparison against the earlier studies in the series, naming every place this study differs from the last one and what that difference does to the reading. The count of responses against the count the study planned for, said on the day the study closes. The CONVENED and DONE records of everything it convenes. 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`.
skills/watch-the-responses-and-close-the-field/SKILL.mdTracks how many responses have come in against how many the study needs, half by half where the design has more than one half. Use it when running `ref/mkt/brand-health`, `ref/mkt/customer-research` and `ref/mkt/win-loss-analysis`.
--- name: watch-the-responses-and-close-the-field description: Tracks how many responses have come in against how many the study needs, half by half where the design has more than one half. Use it when running `ref/mkt/brand-health`, `ref/mkt/customer-research` and `ref/mkt/win-loss-analysis`. license: CC-BY-4.0 metadata: agent: study-manager agent-version: "1" --- # Watch the responses and close the field ## What it does Tracks how many responses have come in against how many the study needs, half by half where the design has more than one half. When the sample is complete or the date arrives, it stops the asking and fixes the responses. ## Where it happens The agent does this in five activities across three reference processes. Each one names the activity as that process words it. - **Close the Interviews** - `ref/mkt/win-loss-analysis`, activity 14 - [Conduct Win/Loss Analysis](../../../../processes/marketing/win-loss-analysis.md) - **Close the Study** - `ref/mkt/customer-research`, activity 15 - [Conduct Customer Research](../../../../processes/marketing/customer-research.md) - **Close the Wave** - `ref/mkt/brand-health`, activity 15 - [Measure Brand Health](../../../../processes/marketing/brand-health.md) - **Watch Both Halves Fill** - `ref/mkt/win-loss-analysis`, activity 13 - [Conduct Win/Loss Analysis](../../../../processes/marketing/win-loss-analysis.md) - **Watch the Sample Fill** - `ref/mkt/brand-health`, activity 14 - [Measure Brand Health](../../../../processes/marketing/brand-health.md) - `ref/mkt/customer-research`, activity 14 - [Conduct Customer Research](../../../../processes/marketing/customer-research.md) ## What to record The study written down as a question before any data is gathered: what it has to settle, the method chosen and why that method, who or what is sampled, how many responses it needs, and the date the findings are due. Every question and every piece of material at a version, in the order it is put to people, with each response marked with the version it answered. Every response as it was given, with its date, and every response that was removed from the count, with the rule that removed it. Each finding with the responses recorded under it, so the finding and its evidence are read together. A comparison against the earlier studies in the series, naming every place this study differs from the last one and what that difference does to the reading. The count of responses against the count the study planned for, said on the day the study closes. The CONVENED and DONE records of everything it convenes. 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`.
skills/write-and-deliver-the-findings/SKILL.mdWrites each finding with the responses recorded under it, so the finding and its evidence are read in one place, and delivers the report to whoever asked for it and to the people who have to act on it. Use it when running `ref/mkt/brand-audit` and 4 other reference processes.
--- name: write-and-deliver-the-findings description: Writes each finding with the responses recorded under it, so the finding and its evidence are read in one place, and delivers the report to whoever asked for it and to the people who have to act on it. Use it when running `ref/mkt/brand-audit` and 4 other reference processes. license: CC-BY-4.0 metadata: agent: study-manager agent-version: "1" --- # Write and deliver the findings ## What it does Writes each finding with the responses recorded under it, so the finding and its evidence are read in one place, and delivers the report to whoever asked for it and to the people who have to act on it. It records what worked in the run and what should change next time. ## Where it happens The agent does this in five activities across five reference processes. Each one names the activity as that process words it. - **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) - **Record What Was Learned** - `ref/mkt/brand-audit`, activity 17 - [Conduct Brand Audit](../../../../processes/marketing/brand-audit.md) - `ref/mkt/brand-health`, activity 23 - [Measure Brand Health](../../../../processes/marketing/brand-health.md) - `ref/mkt/conversion-experiment`, activity 16 - [Run Conversion Experiment](../../../../processes/marketing/conversion-experiment.md) - `ref/mkt/customer-research`, activity 20 - [Conduct Customer Research](../../../../processes/marketing/customer-research.md) - `ref/mkt/win-loss-analysis`, activity 21 - [Conduct Win/Loss Analysis](../../../../processes/marketing/win-loss-analysis.md) - **Report Awareness, Perception and Preference** - `ref/mkt/brand-health`, activity 22 - [Measure Brand Health](../../../../processes/marketing/brand-health.md) - **Write the Findings** - `ref/mkt/brand-audit`, activity 14 - [Conduct Brand Audit](../../../../processes/marketing/brand-audit.md) - `ref/mkt/brand-health`, activity 20 - [Measure Brand Health](../../../../processes/marketing/brand-health.md) - `ref/mkt/customer-research`, activity 17 - [Conduct Customer Research](../../../../processes/marketing/customer-research.md) - `ref/mkt/win-loss-analysis`, activity 18 - [Conduct Win/Loss Analysis](../../../../processes/marketing/win-loss-analysis.md) ## What to record The study written down as a question before any data is gathered: what it has to settle, the method chosen and why that method, who or what is sampled, how many responses it needs, and the date the findings are due. Every question and every piece of material at a version, in the order it is put to people, with each response marked with the version it answered. Every response as it was given, with its date, and every response that was removed from the count, with the rule that removed it. Each finding with the responses recorded under it, so the finding and its evidence are read together. A comparison against the earlier studies in the series, naming every place this study differs from the last one and what that difference does to the reading. The count of responses against the count the study planned for, said on the day the study closes. The CONVENED and DONE records of everything it convenes. 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`.
skills/write-the-questions/SKILL.mdWrites every question that gets asked and every piece of material that gets shown, and holds them at a version before anybody sees them. Use it when running `ref/mkt/brand-health`, `ref/mkt/customer-research` and `ref/mkt/win-loss-analysis`.
--- name: write-the-questions description: Writes every question that gets asked and every piece of material that gets shown, and holds them at a version before anybody sees them. Use it when running `ref/mkt/brand-health`, `ref/mkt/customer-research` and `ref/mkt/win-loss-analysis`. license: CC-BY-4.0 metadata: agent: study-manager agent-version: "1" --- # Write the questions ## What it does Writes every question that gets asked and every piece of material that gets shown, and holds them at a version before anybody sees them. It tries the wording on a handful of people first, and keeps a question that has run before word for word so the two readings stay comparable. ## Where it happens The agent does this in four activities across three reference processes. Each one names the activity as that process words it. - **Carry the Questions Forward** - `ref/mkt/brand-health`, activity 11 - [Measure Brand Health](../../../../processes/marketing/brand-health.md) - **Try the Questions on a Few People** - `ref/mkt/customer-research`, activity 11 - [Conduct Customer Research](../../../../processes/marketing/customer-research.md) - **Write the Interview Guide** - `ref/mkt/win-loss-analysis`, activity 9 - [Conduct Win/Loss Analysis](../../../../processes/marketing/win-loss-analysis.md) - **Write the Questions** - `ref/mkt/customer-research`, activity 10 - [Conduct Customer Research](../../../../processes/marketing/customer-research.md) ## What to record The study written down as a question before any data is gathered: what it has to settle, the method chosen and why that method, who or what is sampled, how many responses it needs, and the date the findings are due. Every question and every piece of material at a version, in the order it is put to people, with each response marked with the version it answered. Every response as it was given, with its date, and every response that was removed from the count, with the rule that removed it. Each finding with the responses recorded under it, so the finding and its evidence are read together. A comparison against the earlier studies in the series, naming every place this study differs from the last one and what that difference does to the reading. The count of responses against the count the study planned for, said on the day the study closes. The CONVENED and DONE records of everything it convenes. 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`.
mcp.jsonNot in the package.
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.
Setting 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 10 roles, and the access level beside each one is the most the work needs.
study-record · writequestions-and-the-material-shown · writesurvey-and-interview-system · triggerresponse-record · writeearlier-studies-in-the-series · readcontact-database · readconsent-record · readcustomer-and-revenue-record · readanalytics-platforms · readmeeting-calendar · write
mcp.json
You write this file. It is not part of the package.
{
"$schema": "https://agent-plugins.org/schemas/1.1.0/mcp.schema.json",
"mcpServers": {
"study-record": {
"type": "streamable-http",
"url": "https://mcp.yourcompany.com/study-record"
},
"questions-and-the-material-shown": {
"type": "streamable-http",
"url": "https://mcp.yourcompany.com/questions-and-the-material-shown"
},
"survey-and-interview-system": {
"type": "streamable-http",
"url": "https://mcp.yourcompany.com/survey-and-interview-system"
},
"response-record": {
"type": "streamable-http",
"url": "https://mcp.yourcompany.com/response-record"
},
"earlier-studies-in-the-series": {
"type": "streamable-http",
"url": "https://mcp.yourcompany.com/earlier-studies-in-the-series"
},
"contact-database": {
"type": "streamable-http",
"url": "https://mcp.yourcompany.com/contact-database"
},
"consent-record": {
"type": "streamable-http",
"url": "https://mcp.yourcompany.com/consent-record"
},
"customer-and-revenue-record": {
"type": "streamable-http",
"url": "https://mcp.yourcompany.com/customer-and-revenue-record"
},
"analytics-platforms": {
"type": "streamable-http",
"url": "https://mcp.yourcompany.com/analytics-platforms"
},
"meeting-calendar": {
"type": "streamable-http",
"url": "https://mcp.yourcompany.com/meeting-calendar"
}
}
}
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.
Where it works
12 processes, 80 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.
Conduct Brand Auditref/mkt/brand-audit · 17 activities
Take in the Request · Set What the Audit Covers · Brief the Audit · List Where the Brand Appears · Draw the Sample · Read the Set as a Whole · Ask the Audience · Name the Gaps · Write the Findings · Decide What Happens to Each Gap · Hand the Gaps to the Owners · Record What Was Learned
Measure Brand Healthref/mkt/brand-health · 23 activities
Open the Cycle · Read the Promise the Brand Makes · Settle What the Wave Measures · Set the Competitor Set · Brief the Wave · Define the Sample · Carry the Questions Forward · Field the Wave · Watch the Sample Fill · Close the Wave · Compare with the Earlier Waves · Set Perception against the Promise · Write the Findings · Report Awareness, Perception and Preference · Record What Was Learned
Roll Out Brand Refreshref/mkt/brand-refresh · 26 activities
Read What People Recognize Today · Read What People Recognize Now
Define Brand Voice and Messagingref/mkt/brand-voice · 19 activities
Try the Messages on Buyers
Develop Buyer Personaref/mkt/buyer-persona · 20 activities
Plan the Study · Field the Study · Name the Jobs · Name the Pains and What They Cost · Name the Buying Triggers · Record the Words This Person Uses
Run Conversion Experimentref/mkt/conversion-experiment · 16 activities
Take in the Hypothesis · Set the Terms of the Test · Size the Test · Clear the Traffic · Brief the Makers · Start the Test · Watch the Test Run · Read the Result · Decide Roll out or Revert · Carry out the Decision · Record What Was Learned
Conduct Customer Researchref/mkt/customer-research · 20 activities
Take in the Question · Choose the Method · Brief the Study · Define the Sample · Write the Questions · Try the Questions on a Few People · Field the Study · Watch the Sample Fill · Close the Study · Write the Findings · Deliver the Findings · Record What Was Learned
Develop Marketing Strategyref/mkt/develop-marketing-strategy · 17 activities
Hear from Buyers and the Field
Map Buyer Journeyref/mkt/map-buyer-journey · 19 activities
Design the Buyer Study · Talk to the Buyers · Draft the Stages · Collect the Questions
Name Product or Companyref/mkt/name-product · 16 activities
Try the Names on Outsiders
Segment the Marketref/mkt/segment-the-market · 18 activities
Collect the First-Hand Accounts
Conduct Win/Loss Analysisref/mkt/win-loss-analysis · 21 activities
Take in the Period · Pull the Closed Deals · Brief the Study · Draw Both Samples · Write the Interview Guide · Invite the Buyers · Hold the Interviews · Watch Both Halves Fill · Close the Interviews · Sort What Was Said into Themes · Set the Themes against the Record · Write the Findings · Deliver the Themes and Recommendations · Record What Was Learned
The records it leaves
What it writes down
The study written down as a question before any data is gathered: what it has to settle, the method chosen and why that method, who or what is sampled, how many responses it needs, and the date the findings are due. Every question and every piece of material at a version, in the order it is put to people, with each response marked with the version it answered. Every response as it was given, with its date, and every response that was removed from the count, with the rule that removed it. Each finding with the responses recorded under it, so the finding and its evidence are read together. A comparison against the earlier studies in the series, naming every place this study differs from the last one and what that difference does to the reading. The count of responses against the count the study planned for, said on the day the study closes. The CONVENED and DONE records of everything it convenes.
Where it stops
What it will not do
Does not decide what the organization does about the findings. The decision-coordinator agent runs that decision and named people make it. Does not say how many responses the study needs, which figures the data supports, or whether a difference is larger than the noise in the measurement, which is the statistician agent; this agent asks that agent before it fields anything and reports what it gets back. Does not gather evidence from published and licensed sources, which is the researcher agent; this agent creates evidence that did not exist before by asking people or by running a test. Does not read the organization's own numbers for a run and report them with their sources attached, which is the analytics agent. Does not fit a model or say what a model predicts, which is the forecaster agent. Does not decide who enters a program or what its steps are, which is the audience-manager agent, and does not change the contact database or send anything from it, which is the audience-operator agent. Does not build the page or the variant a test runs on, which is the web-producer agent, and does not place the measurement that counts what the test does, which is the conversion-tracker agent. Does not score material against the brand guidelines or the claims register, which is the brand-check agent, and does not hold the standards a study reports against, which is the standards-keeper agent. Does not write the department's report for a reporting period, which is the reporting-manager agent; this agent gives that report findings that carry their evidence. 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.
Agents built from this plugin
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.
declare it
implements: study-manager v1
One line in your agent's manifest. The catalog checks it against the records your runs actually leave.
A guess, not a claim
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.
Might do the job
Things that could be the worker: an agent, a packaged product, a plugin.
- The Website Specification — A2A agent Agent · specification.website Read-only A2A agent that answers natural-language questions about The Website Specification and returns matching topics with status, canonical URL,…
Might be reached for
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.
- 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.
- proof MCP server · toremlabs.github.io · run it yourself · mirrored from the MCP registry Govern your AI coding agent: frame the work, review the changes, keep a signed decision record.