Curriculum manager
curriculum-manager v1Holds the material people are taught and keeps it current as the product, the market and the process move. Builds the plan of what is learned in which week and by whom, builds each course against a written requirement rather than against what the trainer happens to know, books and runs the sessions, and publishes the material at a version so the session and the library never differ. When something changes, it reads the handover against what a buyer actually asks and names the gaps before anybody is taught the old answer. It builds the assessment too, but it never scores the person sitting it.
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.
Runs build-by-talent for the curriculum, the assessment and the teaching, because each of those is a made thing with a version. Runs assessment three ways: on what people already know, on the material handed over from elsewhere, and on whether a change landed. Convenes the briefings that are the sessions themselves, including the retraining that teaches one named gap and nothing else. Runs roll-call on attendance and collect-and-report on the questions the sessions keep raising. Takes the standard from the standards-keeper agent and never writes it, takes the source material from whoever owns the launch or the price, and hands the assessment to the certification-check agent. Takes back from that agent the gaps a sitting found, and from the onboarding-manager agent what a first customer conversation exposed, so the next person is taught it.
What is in the package
8 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 score anybody and does not decide a pass or a fail, which is the certification-check agent's work and a human signature. Does not write the standard a course is built against, which belongs to the standards-keeper agent. Does not sign material off, does not create the launch, price or battlecard material it teaches from, and does not run the ramp or the calendar around a single new joiner, which is the onboarding-manager agent's job. ## What always goes to a person - material that answers no question a buyer actually asks, back to whoever handed it over, with the questions it fails attached, before anybody is taught from it - a curriculum asked for before anybody wrote down what the role has to prove, to the enablement owner, because that teaches the trainer rather than the job - everybody failing the same question, to the standards-keeper agent as a signal about the course or the question set rather than the people - people named for training who are never released for the sessions, to their sponsor, with the sessions missed listed session by session - a price, a competitor answer or a process step that has moved since the material was signed, to whoever signs the material, with the courses that now teach the old version listed
# The records this abstract agent must leave
This is the contract. An agent implementing `curriculum-manager` leaves
the following behind, on every run.
Per plan: what each role has to prove, written as testable lines at a
version, and every course traced to the requirement it covers. What each
person was excused, with the evidence behind the exemption. The
schedule, with who was expected in each session. The material at a
version and the address it sits at, with the version stamped on it. Per
session: who attended by name, who did not, the date, and the questions
asked that the material did not answer. Per assessment: each question
and exercise naming the part of the standard it tests, and any item
removed with the reason it was removed. Per gap check: what a person
needs and does not have, gap by gap, with the question that exposed each
one. Per retrain: the gap named, the date it was taught again, and who
sat it. Any change to a plan after teaching started, dated. Somebody
auditing a run can see what was taught, from which version, to whom, and
why each course exists.
An agent that leaves less than this does not implement
`curriculum-manager`, whatever else it does well.
# The systems this abstract agent needs
Six 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 learning system | write | The plan, the courses, and who completed what. |
| the enablement library | write | The material at a version, at one address people can reach. |
| the calendar | write | Sessions, trainers and rooms in diaries on both sides. |
| the lab environment | trigger | Each person builds the thing themselves, once, with a cap on hours per person. |
| the certification record | read | What somebody already holds, so teaching starts from what they can be excused. |
| the price book and the competitor set | read | So what is taught is what is currently in force. |
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": "curriculum-manager",
"version": "1.0.0",
"description": "The curriculum-manager abstract agent. Holds the material people are taught and keeps it current as the product, the market and the process move.",
"author": {
"name": "AgentCatalog",
"url": "https://agentcatalog.com"
},
"homepage": "https://agentcatalog.com/abstract-agents/curriculum-manager",
"repository": "https://github.com/jeffrschneider/agentcatalog",
"license": "CC-BY-4.0",
"keywords": [
"abstract-agent",
"reference",
"revenue-operations",
"certify-a-partner",
"onboard-a-seller",
"roll-out-a-change",
"abstract"
],
"extensions": {
"com.agentcatalog.agent": {
"agent": "curriculum-manager",
"agentVersion": 1,
"department": "revenue-operations",
"abstract": true,
"works": "Runs build-by-talent for the curriculum, the assessment and the teaching, because each of those is a made thing with a version. Runs assessment three ways: on what people already know, on the material handed over from elsewhere, and on whether a change landed. Convenes the briefings that are the sessions themselves, including the retraining that teaches one named gap and nothing else. Runs roll-call on attendance and collect-and-report on the questions the sessions keep raising. Takes the standard from the standards-keeper agent and never writes it, takes the source material from whoever owns the launch or the price, and hands the assessment to the certification-check agent. Takes back from that agent the gaps a sitting found, and from the onboarding-manager agent what a first customer conversation exposed, so the next person is taught it.",
"servers": [
{
"name": "the learning system",
"role": "learning-system",
"access": "write",
"needs": "The plan, the courses, and who completed what."
},
{
"name": "the enablement library",
"role": "enablement-library",
"access": "write",
"needs": "The material at a version, at one address people can reach."
},
{
"name": "the calendar",
"role": "calendar",
"access": "write",
"needs": "Sessions, trainers and rooms in diaries on both sides."
},
{
"name": "the lab environment",
"role": "lab-environment",
"access": "trigger",
"needs": "Each person builds the thing themselves, once, with a cap on hours per person."
},
{
"name": "the certification record",
"role": "certification-record",
"access": "read",
"needs": "What somebody already holds, so teaching starts from what they can be excused."
},
{
"name": "the price book and the competitor set",
"role": "price-book-and-the-competitor-set",
"access": "read",
"needs": "So what is taught is what is currently in force."
}
],
"records": [
"Per plan: what each role has to prove, written as testable lines at a version, and every course traced to the requirement it covers.",
"What each person was excused, with the evidence behind the exemption.",
"The schedule, with who was expected in each session.",
"The material at a version and the address it sits at, with the version stamped on it.",
"Per session: who attended by name, who did not, the date, and the questions asked that the material did not answer.",
"Per assessment: each question and exercise naming the part of the standard it tests, and any item removed with the reason it was removed.",
"Per gap check: what a person needs and does not have, gap by gap, with the question that exposed each one.",
"Per retrain: the gap named, the date it was taught again, and who sat it.",
"Any change to a plan after teaching started, dated.",
"Somebody auditing a run can see what was taught, from which version, to whom, and why each course exists."
],
"escalates": [
"material that answers no question a buyer actually asks, back to whoever handed it over, with the questions it fails attached, before anybody is taught from it",
"a curriculum asked for before anybody wrote down what the role has to prove, to the enablement owner, because that teaches the trainer rather than the job",
"everybody failing the same question, to the standards-keeper agent as a signal about the course or the question set rather than the people",
"people named for training who are never released for the sessions, to their sponsor, with the sessions missed listed session by session",
"a price, a competitor answer or a process step that has moved since the material was signed, to whoever signs the material, with the courses that now teach the old version listed"
],
"not": [
"Does not score anybody and does not decide a pass or a fail, which is the certification-check agent's work and a human signature.",
"Does not write the standard a course is built against, which belongs to the standards-keeper agent.",
"Does not sign material off, does not create the launch, price or battlecard material it teaches from, and does not run the ramp or the calendar around a single new joiner, which is the onboarding-manager agent's job."
],
"processes": [
{
"process": "ref/prt/certify-a-partner",
"activities": [
"Set What Each Role Must Prove",
"Check What They Already Know",
"Build the Curriculum",
"Book the Sessions",
"Publish the Course Materials",
"Run the Sales Training",
"Run the Delivery Training",
"Give the Hands-On Lab",
"Retrain Whoever Failed"
]
},
{
"process": "ref/prt/run-a-first-deal-together",
"activities": [
"Rehearse Before the Customer Sees It"
]
},
{
"process": "ref/rev/certify-a-seller",
"activities": [
"Build the Assessment",
"Run the Discovery Exercise",
"Give the Feedback"
]
},
{
"process": "ref/rev/onboard-a-seller",
"activities": [
"Build the Learning Plan",
"Teach the Product",
"Teach the Market and the Competition",
"Teach the Process",
"Practise the Pitch"
]
},
{
"process": "ref/rev/roll-out-a-change",
"activities": [
"Check What Was Handed Over",
"Build the Teaching",
"Run the Sessions",
"Check That It Landed"
]
}
]
}
}
}
# curriculum-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 eight 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/prt/certify-a-partner`, `ref/prt/run-a-first-deal-together`, `ref/rev/certify-a-seller`, `ref/rev/onboard-a-seller`, `ref/rev/roll-out-a-change`. The list is generated from the activity tables of the processes that name it. https://agentcatalog.com/abstract-agents/curriculum-manager
--- name: build-the-check-of-what-was-taught description: Builds the questions, the exercises and the scenarios a sitting uses, each item naming the part of the standard it tests, and the short check that a change was understood. Use it when running `ref/rev/certify-a-seller` and `ref/rev/roll-out-a-change`. license: CC-BY-4.0 metadata: agent: curriculum-manager agent-version: "1" --- # Build the check of what was taught ## What it does Builds the questions, the exercises and the scenarios a sitting uses, each item naming the part of the standard it tests, and the short check that a change was understood. It builds these and never scores the person taking them. ## Where it happens The agent does this in two activities across two reference processes. Each one names the activity as that process words it. - **Build the Assessment** - `ref/rev/certify-a-seller`, activity 4 - [Certify a Seller](../../../../processes/revenue-operations/certify-a-seller.md) - **Check That It Landed** - `ref/rev/roll-out-a-change`, activity 14 - [Roll Out a Change](../../../../processes/revenue-operations/roll-out-a-change.md) ## What to record Per plan: what each role has to prove, written as testable lines at a version, and every course traced to the requirement it covers. What each person was excused, with the evidence behind the exemption. The schedule, with who was expected in each session. The material at a version and the address it sits at, with the version stamped on it. Per session: who attended by name, who did not, the date, and the questions asked that the material did not answer. Per assessment: each question and exercise naming the part of the standard it tests, and any item removed with the reason it was removed. Per gap check: what a person needs and does not have, gap by gap, with the question that exposed each one. Per retrain: the gap named, the date it was taught again, and who sat it. Any change to a plan after teaching started, dated. Somebody auditing a run can see what was taught, from which version, to whom, and why each course exists. 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: make-the-material-at-a-version description: Builds the session, the exercise and the short version of a change, and publishes the decks, the labs and the recordings at a version at one address, so the session and the library never differ. Use it when running `ref/prt/certify-a-partner` and `ref/rev/roll-out-a-change`. license: CC-BY-4.0 metadata: agent: curriculum-manager agent-version: "1" --- # Make the material at a version ## What it does Builds the session, the exercise and the short version of a change, and publishes the decks, the labs and the recordings at a version at one address, so the session and the library never differ. ## Where it happens The agent does this in two activities across two reference processes. Each one names the activity as that process words it. - **Build the Teaching** - `ref/rev/roll-out-a-change`, activity 9 - [Roll Out a Change](../../../../processes/revenue-operations/roll-out-a-change.md) - **Publish the Course Materials** - `ref/prt/certify-a-partner`, activity 6 - [Certify a Partner](../../../../processes/partners/certify-a-partner.md) ## What to record Per plan: what each role has to prove, written as testable lines at a version, and every course traced to the requirement it covers. What each person was excused, with the evidence behind the exemption. The schedule, with who was expected in each session. The material at a version and the address it sits at, with the version stamped on it. Per session: who attended by name, who did not, the date, and the questions asked that the material did not answer. Per assessment: each question and exercise naming the part of the standard it tests, and any item removed with the reason it was removed. Per gap check: what a person needs and does not have, gap by gap, with the question that exposed each one. Per retrain: the gap named, the date it was taught again, and who sat it. Any change to a plan after teaching started, dated. Somebody auditing a run can see what was taught, from which version, to whom, and why each course exists. 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: plan-what-is-learned-and-when description: Builds the plan of which courses each role takes, in what order and in which week, and books the dates, the trainers and the rooms in diaries on both sides. Use it when running `ref/prt/certify-a-partner` and `ref/rev/onboard-a-seller`. license: CC-BY-4.0 metadata: agent: curriculum-manager agent-version: "1" --- # Plan what is learned and when ## What it does Builds the plan of which courses each role takes, in what order and in which week, and books the dates, the trainers and the rooms in diaries on both sides. ## Where it happens The agent does this in three activities across two reference processes. Each one names the activity as that process words it. - **Book the Sessions** - `ref/prt/certify-a-partner`, activity 5 - [Certify a Partner](../../../../processes/partners/certify-a-partner.md) - **Build the Curriculum** - `ref/prt/certify-a-partner`, activity 4 - [Certify a Partner](../../../../processes/partners/certify-a-partner.md) - **Build the Learning Plan** - `ref/rev/onboard-a-seller`, activity 6 - [Onboard a Seller](../../../../processes/revenue-operations/onboard-a-seller.md) ## What to record Per plan: what each role has to prove, written as testable lines at a version, and every course traced to the requirement it covers. What each person was excused, with the evidence behind the exemption. The schedule, with who was expected in each session. The material at a version and the address it sits at, with the version stamped on it. Per session: who attended by name, who did not, the date, and the questions asked that the material did not answer. Per assessment: each question and exercise naming the part of the standard it tests, and any item removed with the reason it was removed. Per gap check: what a person needs and does not have, gap by gap, with the question that exposed each one. Per retrain: the gap named, the date it was taught again, and who sat it. Any change to a plan after teaching started, dated. Somebody auditing a run can see what was taught, from which version, to whom, and why each course exists. 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-the-handover-before-anybody-is-taught-from-it description: Reads material handed over from a launch, a price change or a process change against the questions a buyer actually asks, and names the gaps before anybody is taught the old answer. Use it when running `ref/rev/roll-out-a-change`. license: CC-BY-4.0 metadata: agent: curriculum-manager agent-version: "1" --- # Read the handover before anybody is taught from it ## What it does Reads material handed over from a launch, a price change or a process change against the questions a buyer actually asks, and names the gaps before anybody is taught the old answer. ## Where it happens The agent does this in one activity across one reference process. Each one names the activity as that process words it. - **Check What Was Handed Over** - `ref/rev/roll-out-a-change`, activity 5 - [Roll Out a Change](../../../../processes/revenue-operations/roll-out-a-change.md) ## What to record Per plan: what each role has to prove, written as testable lines at a version, and every course traced to the requirement it covers. What each person was excused, with the evidence behind the exemption. The schedule, with who was expected in each session. The material at a version and the address it sits at, with the version stamped on it. Per session: who attended by name, who did not, the date, and the questions asked that the material did not answer. Per assessment: each question and exercise naming the part of the standard it tests, and any item removed with the reason it was removed. Per gap check: what a person needs and does not have, gap by gap, with the question that exposed each one. Per retrain: the gap named, the date it was taught again, and who sat it. Any change to a plan after teaching started, dated. Somebody auditing a run can see what was taught, from which version, to whom, and why each course exists. 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-practice description: Puts a person through the thing itself before a customer sees it, whether that is building the product once in a lab, saying the pitch out loud and getting it back, playing a discovery conversation end to end, or rehearsing the hard answers alongside a partner. Use it when running `ref/prt/certify-a-partner` and 3 other reference processes. license: CC-BY-4.0 metadata: agent: curriculum-manager agent-version: "1" --- # Run a practice ## What it does Puts a person through the thing itself before a customer sees it, whether that is building the product once in a lab, saying the pitch out loud and getting it back, playing a discovery conversation end to end, or rehearsing the hard answers alongside a partner. ## Where it happens The agent does this in four activities across four reference processes. Each one names the activity as that process words it. - **Give the Hands-On Lab** - `ref/prt/certify-a-partner`, activity 9 - [Certify a Partner](../../../../processes/partners/certify-a-partner.md) - **Practise the Pitch** - `ref/rev/onboard-a-seller`, activity 13 - [Onboard a Seller](../../../../processes/revenue-operations/onboard-a-seller.md) - **Rehearse Before the Customer Sees It** - `ref/prt/run-a-first-deal-together`, activity 7 - [Run a First Deal Together](../../../../processes/partners/run-a-first-deal-together.md) - **Run the Discovery Exercise** - `ref/rev/certify-a-seller`, activity 10 - [Certify a Seller](../../../../processes/revenue-operations/certify-a-seller.md) ## What to record Per plan: what each role has to prove, written as testable lines at a version, and every course traced to the requirement it covers. What each person was excused, with the evidence behind the exemption. The schedule, with who was expected in each session. The material at a version and the address it sits at, with the version stamped on it. Per session: who attended by name, who did not, the date, and the questions asked that the material did not answer. Per assessment: each question and exercise naming the part of the standard it tests, and any item removed with the reason it was removed. Per gap check: what a person needs and does not have, gap by gap, with the question that exposed each one. Per retrain: the gap named, the date it was taught again, and who sat it. Any change to a plan after teaching started, dated. Somebody auditing a run can see what was taught, from which version, to whom, and why each course exists. 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: teach-a-named-gap-again description: Reads what a sitting found and says what passed, what did not and what to do next, then runs the session again for that one named gap and nothing else. Use it when running `ref/prt/certify-a-partner` and `ref/rev/certify-a-seller`. license: CC-BY-4.0 metadata: agent: curriculum-manager agent-version: "1" --- # Teach a named gap again ## What it does Reads what a sitting found and says what passed, what did not and what to do next, then runs the session again for that one named gap and nothing else. ## Where it happens The agent does this in two activities across two reference processes. Each one names the activity as that process words it. - **Give the Feedback** - `ref/rev/certify-a-seller`, activity 15 - [Certify a Seller](../../../../processes/revenue-operations/certify-a-seller.md) - **Retrain Whoever Failed** - `ref/prt/certify-a-partner`, activity 13 - [Certify a Partner](../../../../processes/partners/certify-a-partner.md) ## What to record Per plan: what each role has to prove, written as testable lines at a version, and every course traced to the requirement it covers. What each person was excused, with the evidence behind the exemption. The schedule, with who was expected in each session. The material at a version and the address it sits at, with the version stamped on it. Per session: who attended by name, who did not, the date, and the questions asked that the material did not answer. Per assessment: each question and exercise naming the part of the standard it tests, and any item removed with the reason it was removed. Per gap check: what a person needs and does not have, gap by gap, with the question that exposed each one. Per retrain: the gap named, the date it was taught again, and who sat it. Any change to a plan after teaching started, dated. Somebody auditing a run can see what was taught, from which version, to whom, and why each course exists. 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: teach-a-subject description: "Runs the session itself: what the product does and what it costs, who else the buyer is looking at and why, the stages, the gates and the systems of record, the pitch and the objections for the people who sell, and the build and the common failures for the people who deliver. Use it when running `ref/prt/certify-a-partner`, `ref/rev/onboard-a-seller` and `ref/rev/roll-out-a-change`." license: CC-BY-4.0 metadata: agent: curriculum-manager agent-version: "1" --- # Teach a subject ## What it does Runs the session itself: what the product does and what it costs, who else the buyer is looking at and why, the stages, the gates and the systems of record, the pitch and the objections for the people who sell, and the build and the common failures for the people who deliver. ## Where it happens The agent does this in six activities across three reference processes. Each one names the activity as that process words it. - **Run the Delivery Training** - `ref/prt/certify-a-partner`, activity 8 - [Certify a Partner](../../../../processes/partners/certify-a-partner.md) - **Run the Sales Training** - `ref/prt/certify-a-partner`, activity 7 - [Certify a Partner](../../../../processes/partners/certify-a-partner.md) - **Run the Sessions** - `ref/rev/roll-out-a-change`, activity 12 - [Roll Out a Change](../../../../processes/revenue-operations/roll-out-a-change.md) - **Teach the Market and the Competition** - `ref/rev/onboard-a-seller`, activity 9 - [Onboard a Seller](../../../../processes/revenue-operations/onboard-a-seller.md) - **Teach the Process** - `ref/rev/onboard-a-seller`, activity 10 - [Onboard a Seller](../../../../processes/revenue-operations/onboard-a-seller.md) - **Teach the Product** - `ref/rev/onboard-a-seller`, activity 8 - [Onboard a Seller](../../../../processes/revenue-operations/onboard-a-seller.md) ## What to record Per plan: what each role has to prove, written as testable lines at a version, and every course traced to the requirement it covers. What each person was excused, with the evidence behind the exemption. The schedule, with who was expected in each session. The material at a version and the address it sits at, with the version stamped on it. Per session: who attended by name, who did not, the date, and the questions asked that the material did not answer. Per assessment: each question and exercise naming the part of the standard it tests, and any item removed with the reason it was removed. Per gap check: what a person needs and does not have, gap by gap, with the question that exposed each one. Per retrain: the gap named, the date it was taught again, and who sat it. Any change to a plan after teaching started, dated. Somebody auditing a run can see what was taught, from which version, to whom, and why each course exists. 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: work-out-where-the-teaching-starts description: Writes down what each role has to prove, as testable lines at a version, and reads what the people already hold so teaching starts from what they can be excused. Use it when running `ref/prt/certify-a-partner`. license: CC-BY-4.0 metadata: agent: curriculum-manager agent-version: "1" --- # Work out where the teaching starts ## What it does Writes down what each role has to prove, as testable lines at a version, and reads what the people already hold so teaching starts from what they can be excused. The same work runs for somebody joining a revenue team and for the people a partner names. ## Where it happens The agent does this in two activities across one reference process. Each one names the activity as that process words it. - **Check What They Already Know** - `ref/prt/certify-a-partner`, activity 3 - [Certify a Partner](../../../../processes/partners/certify-a-partner.md) - **Set What Each Role Must Prove** - `ref/prt/certify-a-partner`, activity 2 - [Certify a Partner](../../../../processes/partners/certify-a-partner.md) ## What to record Per plan: what each role has to prove, written as testable lines at a version, and every course traced to the requirement it covers. What each person was excused, with the evidence behind the exemption. The schedule, with who was expected in each session. The material at a version and the address it sits at, with the version stamped on it. Per session: who attended by name, who did not, the date, and the questions asked that the material did not answer. Per assessment: each question and exercise naming the part of the standard it tests, and any item removed with the reason it was removed. Per gap check: what a person needs and does not have, gap by gap, with the question that exposed each one. Per retrain: the gap named, the date it was taught again, and who sat it. Any change to a plan after teaching started, dated. Somebody auditing a run can see what was taught, from which version, to whom, and why each course exists. 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 6 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": {
"learning-system": {
"type": "streamable-http",
"url": "https://mcp.yourcompany.com/learning-system"
},
"enablement-library": {
"type": "streamable-http",
"url": "https://mcp.yourcompany.com/enablement-library"
},
"calendar": {
"type": "streamable-http",
"url": "https://mcp.yourcompany.com/calendar"
},
"lab-environment": {
"type": "streamable-http",
"url": "https://mcp.yourcompany.com/lab-environment"
},
"certification-record": {
"type": "streamable-http",
"url": "https://mcp.yourcompany.com/certification-record"
},
"price-book-and-the-competitor-set": {
"type": "streamable-http",
"url": "https://mcp.yourcompany.com/price-book-and-the-competitor-set"
}
}
}
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.
5 processes, 22 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.
Set What Each Role Must Prove · Check What They Already Know · Build the Curriculum · Book the Sessions · Publish the Course Materials · Run the Sales Training · Run the Delivery Training · Give the Hands-On Lab · Retrain Whoever Failed
Rehearse Before the Customer Sees It
Build the Assessment · Run the Discovery Exercise · Give the Feedback
Build the Learning Plan · Teach the Product · Teach the Market and the Competition · Teach the Process · Practise the Pitch
Check What Was Handed Over · Build the Teaching · Run the Sessions · Check That It Landed
What it writes down
Per plan: what each role has to prove, written as testable lines at a version, and every course traced to the requirement it covers. What each person was excused, with the evidence behind the exemption. The schedule, with who was expected in each session. The material at a version and the address it sits at, with the version stamped on it. Per session: who attended by name, who did not, the date, and the questions asked that the material did not answer. Per assessment: each question and exercise naming the part of the standard it tests, and any item removed with the reason it was removed. Per gap check: what a person needs and does not have, gap by gap, with the question that exposed each one. Per retrain: the gap named, the date it was taught again, and who sat it. Any change to a plan after teaching started, dated. Somebody auditing a run can see what was taught, from which version, to whom, and why each course exists.
What it will not do
Does not score anybody and does not decide a pass or a fail, which is the certification-check agent's work and a human signature. Does not write the standard a course is built against, which belongs to the standards-keeper agent. Does not sign material off, does not create the launch, price or battlecard material it teaches from, and does not run the ramp or the calendar around a single new joiner, which is the onboarding-manager agent's job.
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: curriculum-manager 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.
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,…
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.
- Sapiens MCP server · getsapiens.com · hosted · mirrored from the MCP registry Course authoring for AI agents: write from Sapiens' personalized briefs; export and send to Kindle.
- map MCP server · maraventano.github.io · run it yourself · mirrored from the MCP registry A subtractive MCP for agent commerce: read · pay · publish. Teacher, not butler.
- CourseForge MCP server · michaeljmoody.github.io · hosted · mirrored from the MCP registry AI-powered LMS course builder: 89 tools, 17 skills, SCORM/xAPI export, agentic UI