--- title: The Last Human Code Review: Building Trust in... description: A conference talk by the CEO of Qodo (formerly Codium) argues that AI code review is bottlenecked not by model quality but by lack of organizational context —... canonical: https://daily.dev/posts/the-last-human-code-review-building-trust-in-ai-generated-code-itamar-friedman-qodo-weitrd4yg twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: The Last Human Code Review: Building Trust in AI-Generated Code — Itamar Friedman, Qodo | daily.dev og:description: A conference talk by the CEO of Qodo (formerly Codium) argues that AI code review is bottlenecked not by model quality but by lack of organizational context —... og:url: https://daily.dev/posts/the-last-human-code-review-building-trust-in-ai-generated-code-itamar-friedman-qodo-weitrd4yg og:image: https://api.daily.dev/og/posts/WEItrD4yg.png og:image:alt: The Last Human Code Review: Building Trust in AI-Generated Code — Itamar Friedman, Qodo og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # The Last Human Code Review: Building Trust in AI-Generated Code — Itamar Friedman, Qodo **[AI Engineer](https://daily.dev/sources/aidotengineer)** · 18 min read · 2 upvotes · 0 comments ## Summary A conference talk by the CEO of Qodo (formerly Codium) argues that AI code review is bottlenecked not by model quality but by lack of organizational context — tribal knowledge, architecture decisions, and past incidents scattered across Slack, docs, and developers' heads. The speaker proposes building a 'context engine' or 'context lake' that codifies rules, standards, and system architecture graphs so both humans and AI agents can trust automated review, gradually enabling auto-approval and auto-blocking of pull requests. The pitch frames Qodo's platform as the tool to get there, with a stated vision of reaching near-zero critical production bugs and outages by 2027. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### Why isn't AI code review accurate even with the best models? Model quality is not the limiting factor for AI code review; missing context is. Without the right context, even top models default to generic suggestions like asking about error handling instead of surfacing real issues. Effective review requires codifying tribal knowledge, team standards, architecture decisions, and past production incidents so the model can reason with the same information a senior developer would have. _Developers weighing AI code review tools can track this kind of context-engineering discussion on daily.dev._ ### What is Qodo's platform for AI code review governance? Qodo (short for quality of development optimization) is a code governance and review platform built by CEO Itamar Friedman that collects an organization's rules, standards, and tribal knowledge into a shared context layer, then uses that context during automated review for both human-readable explanations and agent-to-agent handoffs, including automatic fixes and re-review of pull requests. _Teams comparing AI code review platforms can follow coverage of tools like Qodo on daily.dev._ ## Similar posts on daily.dev - [“Time to clean up human slop”: Why AI now reviews code better than your teammate.](https://daily.dev/posts/time-to-clean-up-human-slop-why-ai-now-reviews-code-better-than-your-teammate--jooa2e9cw) · The New Stack · 10 upvotes · 5 comments - [The New Bottleneck in AI Coding Isn’t Writing Code. It’s Knowing What to Trust.](https://daily.dev/posts/the-new-bottleneck-in-ai-coding-isn-t-writing-code-it-s-knowing-what-to-trust--tf0cfa7o6) · Medium · 0 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#architecture](https://daily.dev/tags/architecture), [#code-review](https://daily.dev/tags/code-review) [View this post on daily.dev](https://daily.dev/posts/the-last-human-code-review-building-trust-in-ai-generated-code-itamar-friedman-qodo-weitrd4yg) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"The Last Human Code Review: Building Trust in AI-Generated Code — Itamar Friedman, Qodo","url":"https://daily.dev/posts/the-last-human-code-review-building-trust-in-ai-generated-code-itamar-friedman-qodo-weitrd4yg","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/the-last-human-code-review-building-trust-in-ai-generated-code-itamar-friedman-qodo-weitrd4yg"},"datePublished":"2026-08-20T13:58:37.810Z","dateModified":"2026-09-14T06:07:03.555Z","description":"A conference talk by the CEO of Qodo (formerly Codium) argues that AI code review is bottlenecked not by model quality but by lack of organizational context —...","image":"https://i.ytimg.com/vi/s-aixZYJG4c/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/s-aixZYJG4c/sddefault.jpg","isAccessibleForFree":true,"articleSection":"AI Engineer","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"AI Engineer","logo":"https://media.daily.dev/image/upload/s--u5PucxNT--/f_auto/v1724338940/logos/aidotengineer","url":"https://daily.dev/sources/aidotengineer"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/the-last-human-code-review-building-trust-in-ai-generated-code-itamar-friedman-qodo-weitrd4yg","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":2},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,architecture,code-review","timeRequired":"PT18M","video":{"@type":"VideoObject","name":"The Last Human Code Review: Building Trust in AI-Generated Code — Itamar Friedman, Qodo","description":"A conference talk by the CEO of Qodo (formerly Codium) argues that AI code review is bottlenecked not by model quality but by lack of organizational context —...","thumbnailUrl":"https://i.ytimg.com/vi/s-aixZYJG4c/sddefault.jpg","uploadDate":"2026-08-20T13:58:37.810Z","duration":"PT18M","url":"https://api.daily.dev/r/WEItrD4yg","embedUrl":"https://www.youtube.com/embed/s-aixZYJG4c"}} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"AI Engineer","item":"https://daily.dev/sources/aidotengineer"},{"@type":"ListItem","position":3,"name":"The Last Human Code Review: Building Trust in AI-Generated Code — Itamar Friedman, Qodo"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/the-last-human-code-review-building-trust-in-ai-generated-code-itamar-friedman-qodo-weitrd4yg#faq","mainEntity":[{"@type":"Question","name":"Why isn't AI code review accurate even with the best models?","acceptedAnswer":{"@type":"Answer","text":"Model quality is not the limiting factor for AI code review; missing context is. Without the right context, even top models default to generic suggestions like asking about error handling instead of surfacing real issues. Effective review requires codifying tribal knowledge, team standards, architecture decisions, and past production incidents so the model can reason with the same information a senior developer would have. Developers weighing AI code review tools can track this kind of context-engineering discussion on daily.dev."}},{"@type":"Question","name":"What is Qodo's platform for AI code review governance?","acceptedAnswer":{"@type":"Answer","text":"Qodo (short for quality of development optimization) is a code governance and review platform built by CEO Itamar Friedman that collects an organization's rules, standards, and tribal knowledge into a shared context layer, then uses that context during automated review for both human-readable explanations and agent-to-agent handoffs, including automatic fixes and re-review of pull requests. Teams comparing AI code review platforms can follow coverage of tools like Qodo on daily.dev."}}]} ```