Greptile
869 posts
Greptile
@greptile
AI agents that review and test PRs.
Trusted by Nvidia, Coinbase, Scale, Brex, Substack, Whoop, and 9000+ others.
- Greptile reposted
tried @greptile today for the first time. very cool ui and so are the reviews, 10/10. i wasnt using PR code reviewers before for some reason. - Greptile reposted
While everyone flexes their token usage, here is a lil flex of my @greptile usage. This doesn't even scratch the surface. Big shoutout to Greptile, I used to love CodeRabbit but they started rate limiting me to oblivion, Greptile are the real OGs in the game rn.
- Greptile reposted
Replying to @cwyanggI 10/10 would recommend greptile to friends and family too - Greptile reposted
I do this to get my PRs in good shape: - Run @greptile until 5/5 - Get all CI/CD passing - Construct QA guidelines for human review I let Codex run 10-30m and comeback to a clean PR that follows our repo standardsShow Codex a workflow once. Reuse it as a skill. Record & Replay lets you show Codex a recurring task, like filing an expense report or submitting a time-off request. Codex turns that demo into an inspectable, editable skill. You control when recording starts and stops.
00:00 - Greptile reposted
Been playing around with different harnesses to create loops. Loved /greploop from @greptile for improving code quality checks and resolving issues automatically. Looking at ways in which skills across the spectrum in a specific function could be sub agents to do things in a loopToday we're launching @mastra `Harness` `Harness` gives you a `Session` with plan/build modes. It lets you manage thread lifecycle, spawn or fork subagents, approve tools per-call or session, ask user questions, queue/steer. With skills, sandbox, browser, heartbeat. channels:
00:00 - Greptile reposted
Been evaluating @greptile internally for a few weeks, and we’re doing a full team rollout today. So far, it generates way less noise, and the product feels much more polished than my experience with Coderabbit. It’s crazy to think about a world without AI code review tools.
