Fall Vibes, AI Evals, and Code Review Bots

TJ Miller and Chris Gmyr compare the AI code review bots they are each building at work, from fixture repos of real PRs to requiring a line of code behind every finding. TJ also shares the eval-driven wizard he built to turn source material into learning content, sharing insights on building AI systems you can test and trust.LinksAsk a question or suggest a topicPodcast: Site | Twitter/X | BlueskyChris: Site | Twitter/X | BlueskyTJ: Site | Twitter/X | BlueskyReferences MentionedHive - Chris's orchestration frameworkGorillaz - the show TJ saw in DetroitDeltron 3030 - the opener and TJ's all-time favorite hip hop artistLuma Brighter Learning - where TJ is building the learning content wizard and the PR review botClaude Opus 5.5 - the model TJ wants to move the content wizard to, then rerun the evalsPrism - TJ's Laravel AI package, which needs updates before the model upgradeGitHub Copilot - the reviewer that caught real issues TJ's bot missed, and the inline comment style Chris wants to copyCodeRabbit - one of the review services both teams passed on in favor of building their ownAmazon Bedrock - where Chris's reviewer runs to keep code inside their own infrastructure