Plan: Ask across the family
Written for an AI agent to fetch and follow: it says what to connect, which steps to build with which product, what a person must approve, and how to check the result. Steps that depend on a part that is not built say so, and tell the agent to record the gap instead of guessing.
URL pattern: /use-cases/<id>/openspec.md, all plans at /use-cases/index.json. Checkboxes on this page are for reading only.
Why
A simple question, such as did we promise Acme SSO and is it shipped, means opening four products. People and agents stop guessing, and every answer can be traced to its owner.
What Changes
- Add the
ask-the-familyworkflow to the PromptReports workflow library, run by the workflow runner as an agent acting for a person. - RepoOps: Answer from the brain (ask_brain) (today: Built).
- AI Source of Truth: Read the family facts (today: Built).
- RepoOps: Answer from every product's facts, with owners (today: Planned).
- Write a signed record at the end of each run and count one workflow request.
Impact
- Products: RepoOps, PromptCompute, AI Source of Truth.
- Outside the family: None beyond the family.
- State: Planned. This question will go to the family assistant, one chat across every product, instead of a workflow. RepoOps answers from its brain today, and the family fact lookup exists.
- Plan row: LDG-2280.
1. Connect and authorize
- 1.1 Confirm the org has a connection for each of: RepoOps, PromptCompute, AI Source of Truth. Stop and tell the user which is missing.
- 1.2 Get a PromptReports ID agent token for each product the run calls (RFC 8693 exchange). Where a product does not accept ID tokens yet, use its connect key.
- 1.3 Confirm no step writes; this workflow reads only.
2. Build the steps
- 2.1 RepoOps: Answer from the brain (ask_brain).
- 2.2 AI Source of Truth: Read the family facts.
- 2.3 RepoOps: Answer from every product's facts, with owners. Blocked: this part is Planned; until it ships, record the step's evidence as
missingand continue.
3. Verify and record
- 3.1 Run a dry run with the user's inputs: Question = Did we promise Acme SSO, and is it shipped?.
- 3.2 Run it once for real; approve each gate as the user.
- 3.3 Measure the outcomes: Answers with a named source: target 100%; Questions answered without opening a product.
- 3.4 Confirm the run left a signed record with a task id and one workflow request counted.
ADDED Requirements
Requirement: Every answer names its owner
Each answer SHALL name the product it came from and the date of the fact.
Scenario: Every answer names its owner
- WHEN two products disagree
- THEN both answers show, each with its owner, and neither is merged into the other
Requirement: Evidence stays honest
Each step SHALL report what it saw as measured, inferred or missing, and SHALL never report missing as measured.
Scenario: A product part is not built
- WHEN a step depends on a part that is Planned or Proposed
- THEN the step records
missing, names the part, and the approval card shows the gap
Requirement: One run is one workflow request
The runner SHALL count one workflow request when the first step starts, and SHALL NOT count retries, resumes or dry runs.
Scenario: A gated step resumes after two days
- WHEN a person approves a step and the run resumes
- THEN the org's usage does not change