The Bottleneck Moved
Platform engineering when AI writes the code: how a team can know that an AI-written change does what it intended, and stays acceptable in production, without someone reading every line.
Open the slides — arrow keys on a laptop; swipe on a phone (turn it sideways)
Sources
Every number and quote in the talk, all published in 2026. Company posts are self-reported: read them as what they did, not as proof.
Everyone uses it, few trust it
- Stack Overflow Developer Survey 2026 — AI — 30,903 responses. 73% of AI coding-tool users use them daily; 6.6% trust AI for important work decisions; 48% trust it when they can easily verify the output.
The volume is real
- State of AI Impact in Engineering: Q3 Report — DX, Oct 2026, 500+ engineering organizations. PRs per developer per week up 75.5% in a year. Vendor data.
- Octoverse 2026 — GitHub, Oct 2026. Merged pull requests more than tripled; 40%+ of PRs now start with an agent's first draft.
The bottleneck moved
- AI Changed How Spotify Builds — Spotify, Sep 2026. “AI increased the capacity to produce change. The next constraint became our ability to verify it.”
- AI Engineering Report 2026: The Acceleration Whiplash — Faros AI, Apr 2026, 22,000 developers. Median time in review up 441.5%. Vendor data.
- The ROI of AI-assisted Software Development — DORA, Apr 2026. AI volume can end up “overwhelming existing deployment pipelines and manual review gates”.
- When AI builds itself — Anthropic, 2026. “Human code review has become a new bottleneck.”
The platform's new job
- Guardrails, not gates — CNCF blog, Koray Oksay, Oct 2026.
- Many SWE-bench-Passing PRs Would Not Be Merged into Main — METR, Mar 2026. Roughly half of test-passing AI patches would not be merged by maintainers.
- Lauren Tan on agents and constraints — Oct 2026. “every mistake and bad pattern you observe from agents, needs to turn into a constraint”.
The verification loop, step by step
- GitHub Agentic Workflows technical preview — GitHub, Feb 2026. Step 1: read-only by default, writes through pre-approved outputs.
- How we contain Claude across products — Anthropic, May 2026. Step 1.
- Minions: Stripe's one-shot, end-to-end coding agents — Stripe, Feb 2026. Steps 1, 2, 3: a devbox per task, scoped tools, two CI rounds then a human.
- Sandboxing Untrusted AI Agents at Scale — Google, Nov 2026. Step 1: Agent Substrate and gVisor donated to the CNCF.
- The AI engineering stack we built internally — Cloudflare, Apr 2026. Step 2: AGENTS.md across ~3,900 repos.
- Evaluating AGENTS.md — ETH Zurich, ICLR 2026. Step 2: keep context files short, and test them.
- Using AI to Delete Code — Uber, Oct 2026. Step 3: a change “can pass CI and still be wrong”.
- Building an agentic harness that outlasts the model — Shopify, Jul 2026. Step 3: “Tests are the oracle.”
- Trust but verify; or, the correctness ratchet — Niko Matsakis, Oct 2026. Step 3.
- Orchestrating AI Code Review at scale — Cloudflare, Apr 2026. Step 4: three risk tiers.
- Speeding up code review with small-change — Will Larson, Oct 2026. Step 4.
- Catching Bugs Before They Land: JiTTesting — Meta, Oct 2026. Step 5.
- Argo Rollouts — CNCF project. Step 5: canary releases with automatic rollback.
Measure it, and does it work?
- DORA metrics guide — DORA, Jan 2026.
- How the Claude Code team does code review — Anthropic, Oct 2026. 2× merged PRs, −40% reverts.
- How Atlassian cut PR cycle time by 45% with AI code reviews — Atlassian, Jan 2026. Vendor post.
Try it
- agent-pr-gate — a GitHub Action that gates agent-written pull requests on risk tier, evidence and review rounds.