Verification register AI & Agents
Current reading
The readiness gap, in one scan
AI-assisted assembly · derived results
- Claimed
- 85
- Reported
- 84
- Verified
- 77
- Gap
- +8
Public ambition and stated capability
Observed practitioner reporting
Independently supported evidence
Claimed minus verified
Evidence strength Critical
Decision
What the current evidence supports
Human editorial judgment · 2026-06-28
Low-friction candidate
- Why
- Near-zero cost, broad ecosystem support, and we already run an equivalent (CLAUDE.md). But the research split (efficiency gains vs success-rate losses) means treat it as a convenience/efficiency aid, not a correctness lever, and avoid over-stuffing.
- Next
- Keep CLAUDE.md/AGENTS.md lean and command-focused (build/test/style), measure whether it changes agent task outcomes on a few real tasks, and prune aggressively rather than padding — per the conflicting study evidence.
Constraints
Blockers
No named blocker is present in the current public projection.
Evidence summary
Derived counts
AI-assisted assembly
- Total
- 6
- Tier 1
- 0
- Tier 2
- 1
- Tier 3
- 5
- Supports
- 4
- Contradicts
- 1
- Context
- 1
- Latest observed
- 2026-06-24
Counts and dates only. Raw signals, private excerpts, trust records, and internal corpus material are not published here.
Publication record
Revisions
Initial public reading
This is the initial public reading. No earlier readiness change is recorded.