Evidence
How Workspace Intelligence decides which facts can be trusted.
Evidence is the source of understanding; documentation is an output, not the authority.
This is the most important rule in Workspace Intelligence.
Why evidence exists
Without evidence, a model becomes a story. It may be useful, but it is not operationally safe.
Evidence lets Workspai say:
- this project exists,
- this runtime was observed,
- this command is available,
- this report was generated,
- this gate passed,
- this fact is stale,
- this release is blocked,
- this agent context was refreshed.
Evidence levels
| Level | Meaning |
|---|---|
| Verified | Proven by a current command, report, contract, or gate |
| Observed | Found in workspace files, manifests, scripts, or markers |
| Inferred | Derived from weaker signals and should be treated carefully |
| Stale | Was true before, but inputs changed or freshness expired |
| Unknown | No reliable evidence exists yet |
Evidence artifacts
Common Workspai evidence includes:
- workspace model reports,
- workspace context packs,
- agent customization packs,
- doctor workspace/project evidence,
- analyze reports,
- readiness reports,
- pipeline reports,
- model snapshots,
- model diffs,
- impact reports,
- verify reports,
- explain and trace narratives,
- workspace intelligence history.
Verification
Verification is where evidence becomes a gate.
npx workspai workspace verify --strict --json
npx workspai pipeline --json --strictVerification should evaluate:
- graph integrity,
- changed projects,
- affected dependents,
- policies,
- freshness,
- required reports,
- release readiness.
Agent safety
AI agents should not receive unbounded context. They should receive scoped, fresh, evidence-backed context. That is the difference between a helpful agent and an agent that confidently acts on stale assumptions.