Continue
Source-controlled AI checks, enforceable in CI
Details
- External ID
- 47049848
- Source
- HN
- Company
- —
- Product
- Continue
- Website domain
- continue.dev
- Launched
- Feb. 17, 2026
- Cohort
- —
- Upvotes
- 44
- Upvotes percentile
- 0.7978436657681941
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:25 p.m.
- Updated at
- Sept. 7, 2026, 9:25 p.m.
Description
We now write most of our code with agents. For a while, PRs piled up, causing review fatigue, and we had this sinking feeling that standards were slipping. Consistency is tough at this volume. I’m sharing the solution we found, which has become our main product.Continue (https://docs.continue.dev) runs AI checks on every PR. Each check is a source-controlled markdown file in `.continue/checks/` that shows up as a GitHub status check. They run as full agents, not just reading the diff, but able to read/write files, run bash commands, and use a browser. If it finds something, the check fails with one click to accept a diff. Otherwise, it passes silently.Here’s one of ours: .continue/checks/metrics-integrity.md --- name: Metrics Integrity description: Detects changes that could inflate, deflate, or corrupt metrics (session counts, event accuracy, etc.) --- Review this PR for changes that could unintentionally distort metrics. These bugs are insidious because they corrupt dashboards without triggering errors or test failures. Check for: - "Find or create" patterns where the "find" is too narrow, causing entity duplication (e.g. querying only active sessions, missing completed ones, so every new commit creates a duplicate) - Event tracking calls inside loops or retry paths that fire multiple times per logical action - Refactors that accidentally remove or move tracking calls to a path that executes with different frequency Key files: anything containing `posthog.capture` or `trackEvent` This check passed without noise for weeks, but then caught a PR that would have silently deflated our session counts. We added it in the first place because we’d been burned in the past by bad data, only noticing when a dashboard looked off.---To get started, paste this into Claude Code or your coding agent of choice: Help me write checks for this codebase: https://continue.dev/walkthrough It will:- Explore the codebase and use the `gh` CLI to read past review comments- Write checks to `.continue/checks/`- Optionally, show you how to run them locally or in CIWould love your feedback!
Enrichment
- Theme
- AI agent frameworks and developer tools
- Vertical
- Horizontal
- Function
- Compliance & governance
- Audience
- Developer
- AI stance
- AI feature
- Project type
- Commercial product
- Normalized one-liner
- ai checks with source control and ci enforcement
- Manually corrected
- False
Could you build this?
Partial A basic CLI or CI runner running prompt checks on diffs is simple, but building an extensible, source-controlled AI rules engine with IDE integrations and enterprise-grade CI enforcement requires sophisticated developer tooling architecture.
What it would actually take: The system requires a git-aware execution engine integrated into CI/CD pipelines (via GitHub Actions/GitLab CI), parsing unified diffs, running custom AST/rule checks paired with LLM evaluation passes, and caching deterministic results to avoid excessive LLM calls. The difficult challenges are maintaining near-zero false positive rates, managing context windows efficiently across multi-file diffs, and keeping CI execution times fast and cheap. It demands strong knowledge of developer tooling, AST parsing, and CI platform protocols.
Discussion
7 comments analyzed.
Competitors mentioned: GitHub (gh-aw), Generic code review bots, Continue VS Code extension
Concerns raised: Breadth vs consistency tradeoff in checks, Risk of unsolicited opinions from AI, Potential walled garden approach
Feature requests: CSV export for metrics, Demo/Loom video, Other metrics export formats beyond images and public links
Competitors
Other products that read as similar to this one — 355 launches clear the similarity bar, closest 8 shown.
Attention rank: #87 of 356 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 105 days after the earliest competitor.
- Legit, Open source Git-based Version control for AI agents · hn · 2026-01-09 · 9 upvotes · similarity 0.52
- I built a tool to assist AI agents to know when a PR is good to go · hn · 2026-01-17 · 45 upvotes · similarity 0.51
- check-docs · ph · 2026-09-21 · 7 upvotes · similarity 0.50
- git-lrc · hn · 2026-06-16 · 9 upvotes · similarity 0.47
- Instantly get the transcript from the agent that wrote any line of code · hn · 2026-09-03 · 5 upvotes · similarity 0.47
- Multiplayer, a debugging agent to run locally next to your coding agent · hn · 2026-05-28 · 8 upvotes · similarity 0.46
- Mission Control · hn · 2026-02-26 · 45 upvotes · similarity 0.46
- Git for AI Agents · hn · 2026-05-08 · 129 upvotes · similarity 0.46
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a compliance & governance tool for Media & entertainment yet.