What your agents did this week
Named in the research as later work. Needs the customer portal (LDG-2259, Planned).
Use case
What your agents did this week: a workflow across PromptCompute, RepoOps, CommitOps, Sales as Code, ContextFile that starts from weekly.
Who would use it
Owners who want one page on what their agents did.
What value it provides
A weekly digest of actions, approvals, incidents, promises and spend, each line linked to its record.
Why it matters to the user
You stay in charge of agents without reading every log.
The problem
Agents act across many tools, and no owner can see the week in one place.
Expected outcomes
- Owners who open the digest weekly
- Issues found in the digest before a customer found them
Each run records its outcome as met, not met or not measured.
How it runs
Products and connections
| Product | Role in this workflow | Docs |
|---|---|---|
| PromptCompute | Approvals and denials | Reference · PromptCompute docs |
| RepoOps | Incidents and recoveries | Reference · RepoOps docs |
| CommitOps | Promises made and kept | Reference · CommitOps docs |
| Sales as Code | Forecast changes | Reference · Sales as Code docs |
| ContextFile | Reference · ContextFile docs |
Outside the family: Slack or email.
What a person approves
| Action | Default risk |
|---|---|
slack.post_message | low |
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: "weekly-agent-digest",
inputs: { "send_to": "Owners and admins", "day": "Monday 08:00" },
dry_run: false
})
// returns { run_id, status: "running", approvals_url }
get_run({ run_id }) // poll, or subscribe to run eventscurl -X POST https://api.promptreports.ai/v1/runs \
-H "Authorization: Bearer $PROMPTREPORTS_AGENT_TOKEN" \
-d '{"workflow":"weekly-agent-digest"}'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 |
| 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 |
| Sales as Code | To confirm | to confirm |
| ContextFile | Built | to confirm |
Set it up
- Sign in at app.promptreports.ai with PromptReports ID, and pick your org.
- Connect PromptCompute, RepoOps, CommitOps, Sales as Code, ContextFile on the Connections page. Link Slack or 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 slack.post_message. Start with Require approval; critical actions are never auto.
- Fill in the inputs (Send to, Day) and choose the trigger: weekly.
- 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.