Verification register AI & Agents
Current reading
The readiness gap, in one scan
AI-assisted assembly · derived results
- Claimed
- 90
- Reported
- 78
- Verified
- 67
- Gap
- +23
Public ambition and stated capability
Observed practitioner reporting
Independently supported evidence
Claimed minus verified
Evidence strength Strong
Decision
What the current evidence supports
Human editorial judgment · 2026-06-28
Wait for stronger evidence
- Why
- Spec-driven engineering aligns with our IPRP/spec-first rules, but the metered vibe/spec pricing, consumption bugs, and single-agent rigidity make it cost- and throughput-unpredictable for high-volume autonomous use, where we already rely on Codex (ChatGPT plan) and agy.
- Next
- Trial only via the AWS Startups 1-year Pro+ credit (if still open) to validate spec-driven flow cost vs Codex/agy; do not put Kiro on the per-request metered plan in any autonomous cron loop until consumption-per-request is predictable
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
- 4
- Tier 3
- 2
- Supports
- 1
- Contradicts
- 3
- Context
- 2
- Latest observed
- 2026-06-01
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.