Use cases/Answer a security questionnaire from the record

Answer a security questionnaire from the record

ProposedNo plan row yetPromptComputeAI Source of TruthRepoOpsCommitOps

Named in the research as later work. Builds on the trust packet.

Use case

Answer a security questionnaire from the record: a workflow across PromptCompute, AI Source of Truth, RepoOps, CommitOps that starts from a person uploads a questionnaire.

Who would use it

Founders and sales engineers facing a security questionnaire.

What value it provides

Each answer is drafted from the trust packet with a link to its evidence. Questions the record cannot answer are flagged for a person, never guessed.

Why it matters to the user

You answer in hours, and every answer holds up when the buyer checks it.

The problem

Questionnaires take days, the answers are copied from last year, and nobody can prove them.

Expected outcomes

Hours from questionnaire received to answered
Answers with an evidence link
Questions flagged as cannot answer

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

How it runs

1. Read approvals evidencePromptComputePlanned

2. Read incident and recovery evidenceRepoOpsPlanned

3. Read promises keptCommitOpsPlanned

4. Check each drafted answer against the recordAI Source of TruthBuilt

5. A person approves sending itPromptComputeBuilt

Products and connections

Product	Role in this workflow	Docs
PromptCompute	Read approvals evidence; A person approves sending it	Reference · PromptCompute docs
AI Source of Truth	Check each drafted answer against the record	Reference · AI Source of Truth docs
RepoOps	Read incident and recovery evidence	Reference · RepoOps docs
CommitOps	Read promises kept	Reference · CommitOps docs

Outside the family: The questionnaire file (spreadsheet or portal export).

What a person approves

Action	Default risk
`file.share.external`	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: "security-questionnaire",
  inputs: { "questionnaire": "contoso-sig-lite.xlsx", "buyer": "Contoso Health" },
  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":"security-questionnaire"}'

Or call the products yourself, step by step:

Product	Endpoint	Tools
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
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`

Set it up

Sign in at app.promptreports.ai with PromptReports ID, and pick your org.
Connect PromptCompute, AI Source of Truth, RepoOps, CommitOps on the Connections page. Link The questionnaire file (spreadsheet or portal export) 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 file.share.external. Start with Require approval; critical actions are never auto.
Fill in the inputs (Questionnaire, Buyer) and choose the trigger: a person uploads a questionnaire.
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.