Use cases/Release notes with proof

Release notes with proof

ProposedNo plan row yetRepoOpsCommitOpsPromptReportsAI Source of Truth

Named in the research as later work.

Use case

Release notes with proof: a workflow across RepoOps, CommitOps, PromptReports, AI Source of Truth that starts from each release.

Who would use it

Product teams that ship every week.

What value it provides

Notes built from shipped work, each line linked to its change, with the customers who were promised that work told in the same run.

Why it matters to the user

Customers see their promise kept in writing, and the notes never claim work that did not ship.

The problem

Release notes are written from memory and skip what customers were promised.

Expected outcomes

Lines in the notes with a source change: target 100%
Promised customers told within a day of release

Each run records its outcome as met, not met or not measured.

How it runs

1. List shipped changesRepoOpsBuilt

2. Match them to promises (shipped_not_told)CommitOpsBuilt

3. Draft the notesPromptReportsProposed

4. A person approvesPromptComputeBuilt

5. Record each lineAI Source of TruthBuilt

Products and connections

Product	Role in this workflow	Docs
RepoOps	List shipped changes	Reference · RepoOps docs
CommitOps	Match them to promises (shipped_not_told)	Reference · CommitOps docs
PromptReports	Draft the notes	Reference · PromptReports docs
AI Source of Truth	Record each line	Reference · AI Source of Truth docs

Outside the family: GitHub, Your blog or changelog.

What a person approves

Action	Default risk
`product.release_notes.publish`	medium
`commitops.customer.notify`	high

Action keys are from the PromptCompute catalog.

How to access it from an agent

An agent will run this workflow through the PromptReports MCP server or API, with an ID agent token. The runner will then call each product for it. Proposed

// MCP: https://mcp.promptreports.ai/mcp (Proposed)
start_run({
  workflow: "release-notes-with-proof",
  inputs: { "range": "Since the last release", "destination": "/changelog" },
  dry_run: false
})
// returns { run_id, status: "running", approvals_url }
get_run({ run_id })   // poll, or subscribe to run events

curl -X POST https://api.promptreports.ai/v1/runs \
  -H "Authorization: Bearer $PROMPTREPORTS_AGENT_TOKEN" \
  -d '{"workflow":"release-notes-with-proof"}'

Or call the products yourself, step by step:

Product	Endpoint	Tools
RepoOps	`https://mcp.repoops.ai/mcp`	`search_brain` `get_pre_edit_context` `propose_brain_entry` `get_incident_attribution`
CommitOps	`https://commitops.ai/api/mcp`	`whoami` `list_assertions` `get_assertion` `promised_not_started`
PromptReports	Proposed	through the runner
AI Source of Truth	`https://aisourceoftruth.com/v1/family/facts`	to confirm

Set it up

Sign in at app.promptreports.ai with PromptReports ID, and pick your org.
Connect RepoOps, CommitOps, AI Source of Truth on the Connections page. Link GitHub, Your blog or changelog through the product that uses it.
Register the agent that will run it on the Agents page, and give it a version manifest.
Set the approval policy for product.release_notes.publish, commitops.customer.notify. Start with Require approval; critical actions are never auto.
Fill in the inputs (Range, Destination) and choose the trigger: each release.
Start a dry run. It will count no workflow request, and it shows which steps would record missing evidence.
Start the run. Approve each gate in the approvals inbox, then read the signed record when it ends.