“We absolutely had to get the bots to help us review PR's. … But now, with the repo readiness work that the champions had done, coupled with better models and tools, … we were getting much better results here. So we enabled … on all the repos, and we also created an auto fix loop where if … issues, another agent will automatically fix those issues and commit them to the PR. So now, at least people were no longer complaining about not wanting to review sloppy PR's from bots, right? By time they got to them, they were in pretty good shape.”
Angie JonesLed AI enablement and the agent engineering org at Block, as she describes in the talk; now VP of Developer Experience, Agentic AI Foundation · Leader, Block
Context. Jones is describing how Block handled code review once engineers were running several agents at once.
Angie Jones, Led AI enablement and the agent engineering org at Block (as she describes in the talk); now VP of Developer Experience, Agentic AI Foundation. Describes the program she ran at Block, so first-hand; the figures are her own reporting from a conference talk with no definitions or baselines.
How this was checked
Not yet checked by an independent second reader. The wording, speaker and date come from the source linked above; treat it as a lead until it is confirmed.
Matched against two local whisper passes of the original audio (full-video transcription and a separate re-cut clip with 5 seconds of margin); quoted only words both passes agree on. Cuts marked with …: the words after 'mostly because' (reviewers/review was), the name of the review tool (both passes spell it 'codecs', which looks like a product name misheard), 'having them use them' vs 'having amused them', and 'identified' vs 'identify'. Punctuation and capitalization differ between the passes and are normalized; PR's is written as in the full-video pass. Not yet checked by a blind second reader. Second reader (2026-11-04): dispute. Reviewer saw: Whisper matches the passage: "people were no longer complaining about not wanting to review sloppy PR's from bots". captions.md at 14:07 reads "people would no longer complain about not wanting to review sloppy PRs from bots". The two transcripts disagree on real words ("were … complaining" vs "would … complain"). Neither is plainly a mishearing, so this is a dispute. The rest matches.
How to cite this passage
Angie Jones (Block), “Building an Autonomous Engineering Org”, AI Engineer (YouTube), 2026-06-28, at 13:31. https://www.youtube.com/watch?v=whue9_YquGA Archived at https://the-ai-record.com/passages/block-bots-review-prs-auto-fix-loop-2026
Angie JonesLed AI enablement and the agent engineering org at Block, as she describes in the talk; now VP of Developer Experience, Agentic AI Foundation · Leader, Block
Context. Jones is describing where Block's engineering organization stood before her agent engineering work began.
Angie JonesLed AI enablement and the agent engineering org at Block, as she describes in the talk; now VP of Developer Experience, Agentic AI Foundation · Leader, Block
Context. Jones is describing what happened when Block engineers began assigning tickets to coding agents.
Angie JonesLed AI enablement and the agent engineering org at Block, as she describes in the talk; now VP of Developer Experience, Agentic AI Foundation · Leader, Block
Context. Jones is reporting results about three months after the AI champions program began at Block.
Angie JonesLed AI enablement and the agent engineering org at Block, as she describes in the talk; now VP of Developer Experience, Agentic AI Foundation · Leader, Block
Context. Jones is explaining how she defined an agent engineering organization after being asked to build one.
Angie JonesLed AI enablement and the agent engineering org at Block, as she describes in the talk; now VP of Developer Experience, Agentic AI Foundation · Leader, Block
Context. Jones is describing the shared view of Block's code that its agent orchestrator draws on.
Angie JonesLed AI enablement and the agent engineering org at Block, as she describes in the talk; now VP of Developer Experience, Agentic AI Foundation · Leader, Block
Context. Jones is describing Block's top stage of agent use and who could use it.