{"slug": "launch-hn-momentic-yc-w24-agents-that-catch-bugs-by-using-your-app", "title": "Launch HN: Momentic (YC W24) – Agents that catch bugs by using your app", "summary": "Momentic, a Y Combinator W24 company, launched on Hacker News an AI QA product called Mo that runs end-to-end tests of web and hosted Android and iOS apps from plain-English YAML flows, with autonomous cloud sessions that can attach an organization's MCP servers and secrets. Momentic reports one customer cut daily test execution to 30 minutes from 7 hours, replaced more than 500 manual test cases, and created 100% of its critical tests in one month; the company says it is SOC 2 Type 2 certified. The release also moved the knowledge base, classification, triage and AI test selection out of beta, and routes each v5 locator and assertion query to fast, medium or extended effort based on reasoning needs, which sets its credit usage.", "body_md": "### New-device 2FA prompt skipped\n\nAt a consumer fintech app, a login routing change bypassed the new-device verification step.\n\nA security checkpoint was silently skipped.\n\nMo is an AI QA engineer that tests your app end to end. Verify critical flows and find bugs from a prompt.\n\nTrusted by leading engineering teams.\n\nTrusted in production by teams shipping every day.\n\nCode moves faster. Verification has to keep up.\n\nCoding agents have made it dramatically faster to build software. The bottleneck is now knowing it works. Verification belongs in the agent loop. Agents need evidence from the app itself to verify that their changes deliver the intended behavior.\n\nWrite the user flows you need to verify. Momentic runs the tests against your app. Reuse successful AI actions and review proposed repairs as the app changes.\n\n1 of 5\n\nVerification from your editor to CI.\n\n Write steps and assertions in plain-English YAML.\n\nReview and version the tests in your repository. \n\nDescribe a user flow and its expected result in plain English. Keep the steps and assertions in YAML files your team and coding agent can review.\n\n`fileType: momentic/test/v2`` id: standard-user-checkout``url: https://shop.momentic.ai`` description: End-to-end checkout flow``steps:` `- module: ./log-in-username-password.module.yaml` `- act: add the momentic backpack to the cart and go to checkout` `- module: ./fill-out-personal-info.module.yaml` `- assert: the item total matches the amount listed for each item` `- click: Finish button`\nUse the CLI to check the app you're changing. Run the same tests in CI before the next merge or deploy.\n\nSee which step failed and inspect its screenshots and traces. AI triage investigates the cause and proposes a test repair for you to review.\n\n  `- click: Place Order button`\nMomentic finds controls again when the UI changes. Permanent healing proposes test-file edits for review. Apply the diff and rerun to check the result.\n\nDescribe your product’s terminology, business rules, and expected behavior in the Knowledge base. Agents use that context to choose actions and check outcomes.\n\nGive agents the product rules they need to check a flow.\n\nMaps screens and user flows seen during test runs.\n\nReview session suggestions before adding them to the Knowledge base.\n\nLoved by engineering teams.\n\n“Momentic gave us a fast and reliable way to validate Poe.com's AI responses, even when they weren't deterministic.”\n\n30 min\n\ndaily test execution, down from 7 hours\n\n500+\n\nmanual test cases replaced\n\n100%\n\ncritical tests created in one month\n\nTest private apps with SSO and custom data policies. Get dedicated onboarding and priority support. Momentic is SOC 2 Type 2 certified.\n\nEngineering teams using Momentic.\n\nIndependently audited. Compliance reports in the Trust Center.\n\nService scope and uptime commitments are set in your Enterprise agreement.\n\nSAML and OIDC SSO, Admin and Member roles, and audit logs.\n\nPriority support and a dedicated account manager for enterprise accounts.\n\nExamples of application failures found by Momentic, with the affected flow and its impact.\n\nRun your tests on browsers Momentic manages. The knowledge base is generally available too, and classification, triage, and AI test selection dropped their beta labels.\n\nMo runs autonomous QA sessions in the cloud, on web or hosted Android and iOS devices, with your org's MCP servers and secrets attached to the session.\n\nEach v5 locator and assertion query now routes itself to a fast, medium, or extended effort based on how much reasoning it needs, which also sets its credit usage.\n\nGenerated ids are normalized and source-file attributes are left out of the cached selector, so rebuilding your app no longer misses every step.\n\nAn AI action can cache a branch now, so the cookie banner that only shows up half the time replays from cache instead of waking the agent again.\n\nA separate reviewer looks at where the app actually ended up before an AI action passes, and hands the step back with its reasoning when your goal did not happen.\n\nTriage works out what broke each test. It commits the fixes your branch caused, then opens a pull request for every other cause and asks whoever owns it to review.\n\nRun Android tests on hosted emulators without Android Studio, the SDK, or adb installed on your machine.\n\nSay in plain English what should have been true at some point in a run. Momentic checks it against frames from the run video, so a toast that flashes for a second still counts.\n\nCommit what your agents keep getting wrong about your app to .momentic/skills, and the explore, triage, and result-classification agents read it while they run.\n\nmomentic doctor tells you what is wrong with your setup: CLI and Node versions, sign-in, browsers, project config, and the connection to Momentic. --fix clears out deprecated options.\n\nPull your finished runs and run groups over REST with an API key. Page through them by cursor and filter by date, status, or platform.\n\nCapture resolved tests into portable snapshots and replay them in isolation with momentic run --from-snapshot.\n\nmomentic ai explore now supports deeper planning controls, JSON output, and product bug reports with repro steps.\n\nRuns now expose live progress, structured JSON output, and clearer Run Viewer diagnostics for cache status, retries, conditionals, and loops.\n\nThe V3 agent is now the default everywhere. It plans the flow up front, caches the resolved steps, and self-heals on failure.\n\nmomentic ai triage groups failures into labeled buckets, previews the plan with a dry run, and can quarantine what it cannot fix.\n\nNew projects scaffold in the cleaner v2 file format, and momentic upgrade migrates existing projects end to end.\n\nPass --parallel auto and Momentic sizes the worker pool from your host's CPU count for faster local and CI runs.\n\nProvision ephemeral inboxes with email.create() and lease numbers from your org pool with sms.lease() right inside a test.\n\nThe recovery flow can inspect browser state, run steps, retry the failed step, and refresh stale caches, with per-step visibility.\n\nmomentic ai classify categorizes a run from its ID or URL so you can route each failure category to the right action.\n\nAndroid AI actions now plan up front, cache resolved steps, and self-heal, matching the web experience.\n\nScreen recordings are captured automatically during iOS and Android test runs and stored with the run attempt.\n\nCreate tests and modules, run step ranges, and drive emulator sessions for iOS and Android from Claude Code or Cursor.\n\nAI actions are enabled by default, so the ai.aiAction switch is no longer needed in momentic.config.yaml.\n\nMobile tests gain dedicated setup and teardown sections so shared preconditions and cleanup live in one place.\n\nAuthor and run Momentic tests against iOS, with modules, AI actions, and hosted simulators alongside Android.\n\nStart and terminate browser sessions, splice steps, and run step ranges from your coding agent over a stdio MCP server.\n\nNew request listener, request recording, and mock route step types let agents capture and stub network traffic.\n\nThe Run Viewer now charts system and process CPU and memory captured during execution to help debug flaky runs.\n\nFailure recovery now extends to mobile tests, retrying and adapting around transient issues on iOS and Android.\n\nmomentic results view launches a local run viewer to browse results on your machine without uploading anything.\n\nStep back and forward through edits in the mobile editor while authoring tests.", "url": "https://wpnews.pro/news/launch-hn-momentic-yc-w24-agents-that-catch-bugs-by-using-your-app", "canonical_source": "https://momentic.ai/", "published_at": "2026-11-02 17:05:25+00:00", "updated_at": "2026-11-02 17:22:04.340100+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "developer-tools", "agent-protocols", "artificial-intelligence"], "entities": ["Momentic", "Mo", "Y Combinator", "Poe.com", "Hacker News"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/launch-hn-momentic-yc-w24-agents-that-catch-bugs-by-using-your-app", "markdown": "https://wpnews.pro/news/launch-hn-momentic-yc-w24-agents-that-catch-bugs-by-using-your-app.md", "text": "https://wpnews.pro/news/launch-hn-momentic-yc-w24-agents-that-catch-bugs-by-using-your-app.txt", "jsonld": "https://wpnews.pro/news/launch-hn-momentic-yc-w24-agents-that-catch-bugs-by-using-your-app.jsonld"}}