Checklist and Probes
The proactive half of the engine — the questions that unlock more suggestions.
Reactive vs. proactive
Matching is reactive: it answers questions about what you have already recorded. The checklist is proactive: it asks what is still unknown.
For every asset, the engine generates a checklist from playbook requirements that are not yet confirmed. Each item is a prompt — a question about the target:
Does this asset expose a password-reset flow?
Prompts and probes
A probe is what you do to answer a prompt: following the flow, checking the surface, actually testing. The checklist is a queue of work, not a form to click through.
How to resolve a prompt:
- Yes — link the capability to the asset. If you discovered the specific value while probing, resolve it to the concrete component rather than a placeholder.
- No — only after tracing the full surface. A negative is a real result, but a wrong one silently suppresses every playbook behind it. Details in Work a Prompt.
- Endpoint — if confirming the capability revealed where it lives, record the endpoint on the link.
What happens after you resolve
The engine re-evaluates the asset immediately: new suggestions appear, others disappear, and the checklist shrinks. Every resolution either unlocks a playbook or prunes the search space — which is why working the checklist is the fastest way to make the vault smarter.
Checklist vs. coverage
The checklist is the open work for one asset. Coverage is the measure of how much of what could apply you have actually confirmed. Both live on the asset, and both move when you resolve prompts with evidence.
What's next
Work a Prompt — the practical discipline.