Skip to content

Agent builder and manifests ​

The agent builder turns a proposed agent into a saved manifest. It opens already filled from the Company Repo. The advisor reviews it, can only make it tighter, and saves a version.

The workspace ​

Select Agents. The builder opens on the last agent you opened, or the first proposed agent.

AreaWhat it holds
Top barYour team (each person with a proposed agent, and their agents), the draft's version and freshness, Save draft and Download .zip
Authority lineActs for, owner, limit, the steps where it pauses, and the authority check
LeftSeven sections you open and close: Agent config, Instructions, Tools and connectors, Context, Human gates, Tests and Handoffs.
RightThe export files, with your unsaved changes applied, one tab per format, and Copy
Before it can runThe readiness checks and gaps (none blocks the draft), Governed access and Share the plan with <person>

Where each value comes from ​

Every filled field has a provenance chip, such as "from check-supplier-packet/task.md › Rule". Select it to open the Repo file.

  • A field you changed and did not save reads "Edited by you · was: …".
  • A saved change reads "Edited by <name> · Repo value: …". It has no Repo chip, because a person wrote it.
  • Use the Repo value puts the Repo value back. Save to keep it.
  • In Agent config, Raw shows the exact Repo file, read only. Rendered goes back.

Acts for, Owner, Proposed and Limit by rule come from the Repo and cannot be changed here. DutyGraph does not choose a model: it shows "Not set · the client chooses" until you pick one.

Steps and markers ​

Instructions lists the Task Card steps, word for word. Code gives each step a marker:

MarkerMeaning
[A]The agent may do the step.
[S]The step needs a recorded approval from a person.
[H]A person does the step.

A step code cannot classify is [H]. You can tighten a marker (A → S → H), never loosen it. To change a step's text, edit the Task Card. Notes for the agent adds your own words; the steps and markers still win.

Limit by rule ​

Code caps the AI mode. Risk lowers the mode. It never raises it.

When a step…The limit is at most
contacts someone outside the companyAI drafts for review
handles money or bank details, or changes accessAI recommends, a person decides
needs an approval ([S])AI acts after a person approves

Tools and access ​

Tools and connectors has one card per system the Repo records. Each card shows what the steps need, the person's recorded access and one state: Within access, Outside access or Access: Not found.

Each tool operation has a policy: Allow, Auto within set limits, Ask first or Off. "Auto within set limits" exists only when the limit is "AI acts within set limits". A looser policy than code allows is not offered. Its tooltip says why, for example "The limit is set by the person's access."

  • Access editor: record the role's access to the system (No access, Read, Write or Admin) and its source. Reported is the default. Client confirmed needs the client's answer to the access ask. DutyGraph records the level only. It does not change access in the system.
  • Request access drafts an ask to the person who grants access to that system. On Access: Not found, the button reads Ask and that person's name. Nothing is sent automatically.
  • DutyGraph holds no credential. The card names the person who provides it.

Human gates names the person at each [H] or [S] step. Tests holds cases code makes from stop conditions, labelled "Case from a stop condition · not a past case". Context lists only Repo files the person's role may read. Handoffs are context only.

Save a draft ​

Save draft makes a new version when the manifest changes: "Saved as v2 · 8 Oct 2026. The draft gives no access." If nothing changed, the version stays.

DutyGraph saves nothing when:

  • a marker or policy is looser than code allows;
  • another person saved after you opened it (reload first);
  • a Task Card holds an email address, a phone number or a value that looks like a secret. The message names the Task Card and field.

A save never writes over a draft agent a person made by hand. It makes a new draft and lists the other as Related draft.

Freshness ​

Agents › Saved agents compares each cited Repo file on every read. Freshness is about the manifest's sources. It does not change any issued authorization.

StateMeaningWhat to do
FreshNo cited file changed.Nothing.
Out of dateA cited file changed, or an edit no longer matches a step.Show changes, review each field, save again.
BrokenA cited file was removed or withdrawn, a cited person left, or the person's access dropped.Review and save again. Until then, only the sheet and JSON export.

A draft is not an authorization ​

A saved manifest is the agent's definition and the source of its implementation files. It is not its authorization. "The draft gives no access" holds for every version.

  • Authority comes only from a governed request that the approval chain approves and IAM issues.
  • Within access on a tool card means the recorded access level covers what the steps need. It is a ceiling check, not proof that the access is needed or approved.
  • A material change to the manifest after issue should be checked again against the issued authorization. Freshness flags source changes today. Linking a changed manifest to its issued agent for revalidation is Planned.

Not proposed ​

Opportunities › Proposed agents lists what code did not turn into an agent, with one reason and an ask.

ReasonMeaning
No accountable ownerNobody owns the work.
Conflicting accountsPeople describe the work differently.
People onlyThe Task Card has no proposed AI mode.
AI not allowedThe Task Card does not allow AI.
Route: a change that is not an agentRoute chose a cheaper change first.

Draft the ask opens the ask in the Discovery composer. Nothing is sent until you send it.

The manifest schema in plain English
FieldWhat it holds
schema, id, versiondutygraph.agent-manifest.v1, the AGT-… id, and the version (+1 on every saved change)
actsFor, ownerThe person the agent acts for, and the accountable owner, with their roles
duties, taskCardsThe duties and Task Cards, each pinned by record version and content hash
systemsAccessEach system and the role's access level and source
proposedMode, autonomyCeiling, ceilingReasonsThe proposed AI mode, the limit by rule, and why
steps, humanGatesEach step with its marker and system; who acts at each gate
toolsEach system's operations, their policies, the authority check and who provides the credential
instructions, notesForAgentThe compiled instructions; a person's added notes
stopConditions, deniedWhen to stop; what it must never do
context, handoffsRepo files the role may read; handoffs as context
tests, pastCasesCases from stop conditions; past cases found of 3 needed
notFoundEvery gap, with the person to ask. Never filled in.
provenanceThe Repo fingerprint, each cited file and hash, and manifestHash. approval is always empty.
lifecycleAlways proposed

INFO

Status. Built: the workspace, provenance chips, markers, limit rules, tool policies, the access editor, versioned saves, freshness and Not proposed reasons. Simulated: access values on the sample companies, labelled "Reported · sample". Planned: describing an agent in words, past cases from people, recorded approvals inside the manifest, and revalidating an issued authorization when its manifest changes.

Source: gitbook/product/agents/agent-builder.md in the DutyGraph repository.

DutyGraph. Pages label each feature Built, In review or Planned.