Readiness statuses
| Status | What it means |
|---|---|
| Ready | Strong evidence: linked pain, accessible data, specific grounding, no unmet prerequisite |
| Needs discovery | Worth building toward, but key evidence (data access, owners, scope) is still missing |
| Prototype only | A product/commercialization idea or thin evidence — explore as a prototype, not a deployed agent |
| Not recommended | The evidence does not justify creating an agent yet (no deployment kit is written) |
What raises readiness
- A linked pain on the workflow, grounding the impact case.
- An accessible data asset the agent would read at decision time.
- Specific, non-generic grounding — a named process or offering, not a category.
- A satisfied prerequisite (e.g. Instrument First done before Automate).
- A named process owner, an approval boundary, and a few past examples to seed an eval set.
What it is not
A blueprint is a specification, not an automated deployment. The hard parts of shipping an agent — connectors, permissions, data quality, approval boundaries, and evaluation — are surfaced honestly rather than hidden.