Trust And Readiness
How ShipFoundry explains recommendation safety before a user acts, exports, or hands work to an agent.
Trust and readiness states explain how proven a recommendation is and what action is safe to take next.
When To Use This
Use this page before acting on a relevant update, creating a Linear issue, or asking an agent to implement a change.
The trust state is the difference between "this may matter" and "this is ready for a scoped handoff."
How It Works
ShipFoundry separates match confidence from action readiness. A stack match can be useful before repo proof exists, but it should not be described as repo-proven until repository evidence supports it.
Recommendation Trust Contract
| State | Meaning | Safe Action |
|---|---|---|
| Stack Candidate | The update matches a tracked stack item or product context, but repo proof is not present. | Read and triage. Do not treat as implementation-ready. |
| Needs Repo Check | The update may affect code, but ShipFoundry still needs local or GitHub-backed evidence. | Ask an agent to inspect the named areas. |
| Repo Checked No Proof | A repo check ran but did not find supporting evidence. | Defer, ignore, or run a narrower check if the user knows where to look. |
| Repo Checked Weak | Some possible evidence exists, but it is partial or indirect. | Investigate before implementation. |
| Repo Checked Plausible | Evidence suggests the update may apply to the repo. | Create a focused investigation task. |
| Repo Checked Strong | Evidence directly supports the update's relevance to repo code or config. | Consider a handoff if the suggested path is bounded. |
| Handoff Ready | The brief has enough synthesis, evidence, constraints, and checks for an agent workflow. | Hand to agent, export to Linear, or copy the task packet. |
| Non-Code Relevant | The update matters, but the action is docs, policy, vendor setup, billing, or operations. | Assign human review or update product context. |
| Not Relevant | The update does not apply to this product. | Record the outcome so future matching improves. |
Step-By-Step
- Open the update.
- Read the trust state before the recommendation text.
- Compare source evidence and repo evidence.
- Check whether evidence missing is explicitly named.
- Choose act, investigate, defer, ignore, false positive, adopted, needs review, or waiting.
- Export only when the trust state and brief support the target workflow.
What ShipFoundry Does
- Makes uncertainty visible.
- Separates stack-level relevance from repo-level proof.
- Names safe next actions for each state.
- Keeps handoff readiness stricter than update relevance.
- Lets outcomes teach future matching.
What ShipFoundry Does Not Do
- It does not hide missing repo proof.
- It does not claim "handoff ready" for every relevant update.
- It does not use GitHub evidence as a replacement for authorization, tests, or code review.
- It does not make Linear export automatic.
Troubleshooting
If a state looks too optimistic, inspect the evidence list and record a correction through the outcome flow.
If an update is important but no repo proof exists, use an investigation task rather than an implementation handoff.
If the agent finds stronger or weaker proof than ShipFoundry showed, record the outcome and update the product context if needed.
Related Pages
- Core artifact: Investigation Briefs
- Agent workflow: Agent Workflows
- Example artifact: Sample Engineering Spike
- Per-match repo proof: GitHub Repo Evidence
- MCP integration: MCP
- Product CTA: Start 7-Day Trial
Was This Page Useful?
Send a short note if this page is unclear, overclaims a capability, or is missing the proof you expected.
Send Docs Feedback for Trust And Readiness