Use cases/Investor update with proof

Investor update with proof

Partly builtLDG-2278Sales as CodeCommitOpsRepoOpsPromptComputeAI Source of Truth

The AI Source of Truth figure check is live. Four parts to go.

Use case

Investor update with proof: a workflow across Sales as Code, CommitOps, RepoOps, PromptCompute, AI Source of Truth that starts from the first Monday of each month.

Who would use it

Founders writing the monthly investor update.

What value it provides

Forecast grades, promises kept, reliability and shipped work, each number linked to its record, checked and approved before it is sent.

Why it matters to the user

Investors trust a number they can click. Each month's update builds on the last instead of starting over.

The problem

Investor updates are assembled by hand from five tools, and the numbers drift from one month to the next.

Expected outcomes

Numbers with a record link: target 100%
Hours to assemble the update
Corrections issued after sending: target 0

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

How it runs

1. Forecast grades for the monthSales as CodePlanned

2. Promises kept and brokenCommitOpsPlanned

3. Reliability and shipped workRepoOpsPlanned

4. Check each figure against its recordAI Source of TruthBuilt

5. A person approves the updatePromptComputeBuilt

6. Send itPromptReportsPlanned

Products and connections

Product	Role in this workflow	Docs
Sales as Code	Forecast grades for the month	Reference · Sales as Code docs
CommitOps	Promises kept and broken	Reference · CommitOps docs
RepoOps	Reliability and shipped work	Reference · RepoOps docs
PromptCompute	A person approves the update	Reference · PromptCompute docs
AI Source of Truth	Check each figure against its record	Reference · AI Source of Truth docs

Outside the family: Your email.

What a person approves

Action	Default risk
`investor.update.send`	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: "investor-update",
  inputs: { "month": "2026-10", "recipients": "Investor list" },
  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":"investor-update"}'

Or call the products yourself, step by step:

Product	Endpoint	Tools
Sales as Code	To confirm	to confirm
CommitOps	`https://commitops.ai/api/mcp`	`whoami` `list_assertions` `get_assertion` `promised_not_started`
RepoOps	`https://mcp.repoops.ai/mcp`	`search_brain` `get_pre_edit_context` `propose_brain_entry` `get_incident_attribution`
PromptCompute	`https://mcp.promptcompute.ai/mcp`	`request_approval` `get_approval` `cancel_approval` `answer_approver`
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 Sales as Code, CommitOps, RepoOps, PromptCompute, AI Source of Truth on the Connections page. Link Your email 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 investor.update.send. Start with Require approval; critical actions are never auto.
Fill in the inputs (Month, Recipients) and choose the trigger: the first Monday of each month.
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.