Markdown source

The Last Human Code Review: Building Trust in AI-Generated Code

Conference Context

Session Description

By the end of 2026, asking a human to review every pull request will be as optional as asking one to run every unit test manually. The tooling will be ready. The question is whether organizations are. In this talk, Itamar Friedman, CEO of Qodo, explains why we are approaching the end of line-by-line human code review as a default requirement and explores what has to be true for teams to get there. The barrier was never agentic AI capability. It was trust. And trust in automated review does not come from smarter models or faster feedback loops. It comes from systems that provide a trustworthy, concise and personalized proof-of-validation report. These systems are built on how engineering teams at specific organizations write their code: their own rules and standards, their PR history, their architecture decisions, their tribal knowledge that lives in comments and conversations and gets lost when engineers leave. Itamar will walk through the shift from PR-by-PR review toward continuous, context-based code review and governance, and share a practical approach to making human code review optional. If your team is shipping AI-generated code faster than humans can read it, join us for the discussion.

Media Evidence

The State of AI Code Quality: Hype vs Reality — Itamar Friedman, Qodo (speaker-match related prior/adjacent AI Engineer video; captions: English auto-captions).

Evidence Graph

This evidence graph is generated from currently linked source material: official schedule text, related video pages, cached transcripts, visible slide text, dense/reconstructed slide pages, and AI slide-classification audits.

Media Signals

Agent Reading Notes

Use these signals to refine the synopsis, topic links, people/company context, and method notes. If a source is a related external video rather than an exact official recording, keep it framed as supporting evidence.

Transcript Status

Related video transcript availability: English auto-captions. Treat this as supporting context, not a recording of this exact scheduled session unless later confirmed. Not fetched yet.

People

Supporting Slides

Synthesis

Synthesized Breakdown

The Last Human Code Review: Building Trust in AI-Generated Code ## Conference Context - Date/time: 2026-06-29 · 11:40am-12:00pm - Track/room: AI Architects: Show my Workflow · Leadership 2 - Speaker(s): Itamar Friedman - Session type/status: session · confirmed - Track: AI Architects: Show my Workflow - Room: Leadership 2 - Session type: session - Status: confirmed ## Session Description By the end of 2026, asking a human to review every pull request will be as optional as asking one to run every unit test manually. The tooling will be ready. The question is whether organizations are. In this talk, Itamar Friedman, CEO of Qodo, explains why we are approaching the end of line-by-line human code review as a default requirement and explores what has to be true for teams to get there.

Speaker And Company Context

Topics Covered

Derived Links And Source Material

Novel Concepts / Clever Methods

Evidence Boundary

This synthesis is based on the official schedule and linked source pages. It should be revisited when exact session recordings or transcript-backed secondary sources are available.