pragma.vision Your technology observatory

Verification register AI & Agents

Comparative expertise

Autonomous AI coding agents

One fixed criteria frame. Every populated cell traces to one dated readiness verdict; missing evidence remains explicit.

Data as of
2026-06-28
Definition pinned
2026-07-17
Revision
1
Definition version
v1.0.0
Method
v1.1.0

Fixed matrix

Verdict fields, side by side

AI-assisted assembly · derived results

Scope: AI Coding & Software Agents · AI & Agents. No average, blend, composite, or estimate is produced.

Comparison of OpenAI Codex (GPT-5.5), AWS Kiro, Devin Desktop
Criterion OpenAI Codex (GPT-5.5) openai-codex-gpt-5-5 AWS Kiro aws-kiro Devin Desktop devin-desktop
Verified readiness verdict.readiness.verified 78 67 64
Hype gap verdict.readiness.gap 12 23 16
Evidence strength verdict.readiness.strength Strong Strong Critical
Recommended stance verdict.decision.answer Adopt with guardrails Wait for stronger evidence Proceed with caution
Latest evidence verdict.evidence_summary.latest_observed_on 2026-05-26 2026-06-01 2026-06-19

Human editorial

Synthesis and caveats

Human editorial · awaiting approval

Synthesis

No approved human synthesis is published for this revision.

Caveats

No approved human caveats are published for this revision.

Your opinion

Tell us anything.

What works, what doesn't, what's missing — especially about our watches, lenses, and the register itself. Anonymous is fine; leave an email if you'd like a reply.