Code review just went agent-to-agent. qodo shipped an adversarial review layer, out september 9,…
code review just went agent-to-agent. qodo shipped an adversarial review layer, out september 9, that audits the code other agents produce and folds it into governance instead of waiting for human reviewers.
the reviewer is now a second agent, not a second person.
Context
Qodo's press release of 9 September 2026, titled Qodo Launches the First Agent-to-Agent Code Review and Governance, announces the Agentic Toolbox, a suite of agent tools and skills for independent adversarial code review inside AI coding workflows, working with Claude Code, Codex and Kiro, reviewing committed and uncommitted work before the pull request, with engineering leaders defining standards, risk boundaries and escalation policies. Qodo's blog of the same day says it is available now through plugins for Claude Code, Codex and Kiro, and any MCP-compatible client, installed by CLI.
The date and shipped scope are supported. First agent-to-agent is the vendor's own headline label and is unverified as a fact: other vendors had agent-callable pre-commit review earlier according to snippets, for example CodeRabbit's CLI, which was not compared. The release says humans define standards and focus on risk control and does not say human reviewers are removed, so instead of waiting for human reviewers is the author's gloss. No benchmark, defect-catch rate or customer result was read. That the reviewer is now a second agent, not a second person, is the author's opinion.
Watch next
- Independent evaluations and customer results.
Sources
- Qodo launches the first agent-to-agent code review and governance (GlobeNewswire, 9 Sep 2026)globenewswire.com
- Introducing Qodo's Agentic Toolbox (Qodo, 9 Sep 2026)qodo.ai
- CodeRabbit CLI docsdocs.coderabbit.ai
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 20 September 2026 at 12:19 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →