Macroscope ads

Here's what we shipped at Macroscope in October. 𝗦𝗺𝗮𝗿𝘁𝗲𝗿 𝗔𝗽𝗽𝗿𝗼𝘃𝗮𝗯𝗶𝗹𝗶𝘁𝘆 & 𝗻𝗲𝘄 𝗺𝗼𝗱𝗲𝘀 Approvability decides whether a PR is safe to merge without a human, and approves it if so. It now runs on an upgraded model that handles longer, more complex policies more reliably. The new Approvability Mode sets how cautious it is: Permissive (the default) leans on the PR's verifiable evidence, and Strict is closer to the previous behavior. 𝗔𝗽𝗽𝗿𝗼𝘃𝗮𝗯𝗶𝗹𝗶𝘁𝘆 𝗗𝗮𝘀𝗵𝗯𝗼𝗮𝗿𝗱 See what Approvability approved, what it didn't, and why. Filter by repo, date or verdict, and export to CSV. 𝗣𝗿𝗲𝘃𝗶𝗲𝘄 𝗠𝗼𝗱𝗲 𝗮𝗻𝗱 𝗿𝘂𝗻 𝗺𝗼𝗱𝗲𝘀 Preview Mode shows which PRs Macroscope would approve, without real approvals. Run modes let each repo pick Always run, Manual only, or Never run. 𝗣𝗼𝗹𝗶𝗰𝘆 𝗥𝗲𝗽𝗼 Write your code review config once and share it across your repos. Any repo can still override a file with its own copy. 𝗙𝗮𝘀𝘁𝗲𝗿, 𝗺𝗼𝗿𝗲 𝗮𝗰𝗰𝘂𝗿𝗮𝘁𝗲 𝗰𝗼𝗱𝗲 𝗿𝗲𝘃𝗶𝗲𝘄 We simplified how the review agents gather context, plus other optimizations. Code review is 14% faster on average, with 5% higher recall on known bugs (MacroscopeBench) and no change in precision. 𝗣𝗹𝘂𝘀: "onlyApprove", Auto Rerun for Approvability, a new "ignoreTests" option, and new Check Run Agent models.

91% of Pydantic's PRs merge without a human reviewer. Book a 30-minute demo to see how Macroscope can review your team's PRs and help your team ship faster.

Your review queue, cleared for a month. Qualified engineering teams who book a demo get 30 days of Macroscope Code Review on their real PRs, free.

91% of Pydantic's PRs merge without a human reviewer. Book a 30-minute demo, set up Macroscope on your codebase, and start with $100 of free usage.

Comparing AI code reviewers? Qualified engineering teams who book a demo get a full month of Macroscope Code Review free.

91% of Pydantic's PRs merge without a human reviewer. Book a 30-minute demo to see how Macroscope reviews your team's PRs and helps you ship faster.