{"slug": "show-hn-canary-yc-independent-verification-for-ai-code", "title": "Show HN: Canary (YC) – Independent verification for AI code", "summary": "Y Combinator-backed startup Canary launched an independent verification tool for AI-generated code that deploys agent swarms to test suspected runtime bugs in remote sandboxes, founders Aakash and Viswesh announced on Hacker News. Canary takes a cold snapshot of a codebase when called by coding agents such as Claude or Codex, combines supplied intent and team knowledge with requirements and prior issues from tools like Notion and Linear, and returns findings and supporting evidence for the agents to fix and re-verify. Developers can install the Canary CLI with \"npm i -g @runcanary/cli\" and run \"canary skills\" to onboard a repository.", "body_md": "Hey HN, we are Aakash and Viswesh and we are building Canary ([https://www.runcanary.ai/](https://www.runcanary.ai/)) - independent verification for AI code. Claude/Codex calls Canary with the changesets, intended behaviour and team knowledge. Canary then deploys agent swarms to investigate potential failures and test suspected runtime bugs in remote sandboxes.\n\nTo try it on your repository, paste this into your coding agent:\n\n```\n  Install the Canary CLI with npm i -g @runcanary/cli,\n  then run canary skills and follow its instructions\n  to onboard this repository.\n```\n\nVerification starts with what software is supposed to do and most importantly what it must never allow. This means investigating how inputs, permissions, state, timing, dependencies etc interact with each other. Intent is not always fully declared as well but many expectations are clear: private files should stay private, credentials should not leak, and retries should not create unintended duplicate effects.\nWe believe the future is a unified and independent verification system that starts with all those expectations and then chooses how to investigate each suspected failure. Source-only code reviews catches static issues in the implementation but even a clean review leaves a good chunk of behavioral only issues untested. Unit tests, integrations, E2E, static analysis, runtime experiments and formal verification are all means to establish that behavior thereby generating different kinds of evidence and guarantees.\n\nThis is why we believe a dedicated verification harness that can think and reason through all these modalities and invariants is necessary on top of general intelligence. The harness needs to start with the system’s intended behavior, develop a series of potential failure scenarios and choose how to investigate them. It’s sole functionality is to pressure test and challenge the assumptions behind a change, create the conditions needed to test suspected failures and assess what the resulting evidence establishes\n\nHow Canary works: it takes a cold snapshot of the codebase when called, combining the supplied intent and team knowledge with requirements, decisions, prior issues from tools like Notion, Linear. It can also route questions to you through the coding agents if anything is ambiguous.\n\nCanary’s harness coordinates agent swarms by leveraging the different strengths across model families. It compares the code before and after, traces the effects through callers, dependencies, state transitions etc. and each suspected failure becomes a concrete scenario with an actor, state, trigger, outcomes and many more runtime states.,\n\nFor each suspected failure, Canary chooses the best way to provide evidence through methods like runtime verification, static analysis, unit, integration or sometimes even combination of these as necessary. The agent executes these checks in remote sandboxes by seeding data, configuring permissions, mocking dependencies and third party integrations and much more. Canary then returns these findings and supporting evidence back to the coding agents which then fixes these failures and requests reverifications against the failed scenarios.\n\nTo get started, give your coding agent this setup instruction and tell us what it caught and how we can do better.\n\n```\n  Install the Canary CLI with npm i -g @runcanary/cli,\n  then run canary skills and follow its instructions\n  to onboard this repository.\n```\n\nWe are still pretty early in our journey and would love feedback on the product and how we can do better.\nComments URL: [https://news.ycombinator.com/item?id=49836632](https://news.ycombinator.com/item?id=49836632)\n\nPoints: 4\n\n# Comments: 0", "url": "https://wpnews.pro/news/show-hn-canary-yc-independent-verification-for-ai-code", "canonical_source": "https://www.runcanary.ai/", "published_at": "2026-09-24 20:57:52+00:00", "updated_at": "2026-09-24 21:29:44.977592+00:00", "lang": "en", "topics": ["ai-agents", "developer-tools", "ai-tools", "ai-products", "artificial-intelligence"], "entities": ["Canary", "Y Combinator", "Aakash", "Viswesh", "Claude", "Codex", "Notion", "Linear"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/show-hn-canary-yc-independent-verification-for-ai-code", "markdown": "https://wpnews.pro/news/show-hn-canary-yc-independent-verification-for-ai-code.md", "text": "https://wpnews.pro/news/show-hn-canary-yc-independent-verification-for-ai-code.txt", "jsonld": "https://wpnews.pro/news/show-hn-canary-yc-independent-verification-for-ai-code.jsonld"}}