Pinned
Tenki Sandbox just landed on Crabbox alongside AWS, Azure, E2B, and Modal as a supported provider. If you're already using Crabbox, you can now spin up Tenki sandboxes directly.
Tenki Cloud
2,075 posts
Tenki Cloud
@TenkiCloud
Ship code faster and cheaper. AI reviewed before production.
- Be honest, when AI writes your code, who catches the most bugs?
- Here's a quick test we did: Opus 4.8 vs Fable 5 This is what Tenki Code Reviewer found: Opus-written PR: 3 high-severity bugs across 22 files and 1,615 lines of code Fable-written PR: zero issues across 22 files and 1,134 lines of code Same repository, same prompts. Small
- Teams treat their CI pipeline like a junk drawer. Every quarter someone adds a step. Nobody ever removes one. Then you wonder why builds take 20 minutes.
- Replying to @TenkiCloud
- PRs over 400 lines get approved, not reviewed. Both humans and AI code reviewers give better feedback on five 100-line PRs than one 500-line PR.
- Tenki Code Reviewer caught a bug and generated a ready to use prompt for the agent to fix it. Re-review came back clean. Merged.
00:00 - Tenki Cloud reposted
Building Jardinero: a control plane for autonomous engineering agents. It's a TypeScript orchestrator living in a long-lived @TenkiCloud sandbox. Three workflows so far. 1) The Log Reviewer runs hourly and post-deploy. It sweeps staging and prod through the Grafana MCP,
- Most code reviewer benchmarks publish a per-PR catch rate: "did the tool flag at least one bug in this PR?" Because of that, the top reviewers look almost identical. It's also the wrong metric. Catch one bug in a nine-bug PR and you score the same as a reviewer that caught all
- Something big is on the way. Migrate your workflows to Tenki now so you can use it the moment it lands.
00:00 - Tenki Cloud repostedAdd Tenki sandboxes to the mix
- Your linter won't flag a function that works but doesn't belong. Neither will your test suite. Practical checklist for catching what agents get wrong.
