Ask across the family
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.
Use case
Ask across the family: a workflow across RepoOps, PromptCompute, AI Source of Truth that starts from a question from a person or an agent.
Who would use it
Anyone on the team, and the agents that work for them.
What value it provides
One question answered from every product's facts, each answer naming the product it came from and the date.
Why it matters to the user
People and agents stop guessing, and every answer can be traced to its owner.
The problem
A simple question, such as did we promise Acme SSO and is it shipped, means opening four products.
Expected outcomes
- Answers with a named source: target 100%
- Questions answered without opening a product
Each run records its outcome as met, not met or not measured.
How it runs
Products and connections
| Product | Role in this workflow | Docs |
|---|---|---|
| RepoOps | Answer from the brain (ask_brain); Answer from every product's facts, with owners | Reference · RepoOps docs |
| PromptCompute | Reference · PromptCompute docs | |
| AI Source of Truth | Read the family facts | Reference · AI Source of Truth docs |
Outside the family: None beyond the family.
What a person approves
Nothing. This workflow only reads.
How to access it from an agent
No run to start. The family assistant will answer this question, as one chat across every product, in the app and as an ask tool on the family MCP server (Planned). Read Family assistant in Concepts.
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 |
| 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 |