CheckOps
Zorro by Narrative
Zorro, from YC company Narrative, runs AI bug bashes and regression tests on pull requests, with agents that explore an app like a manual tester and report bugs with recordings and console logs.
Latest public signals
Not refreshed yet. Refresh reads the public site and, when the entry has a GitHub repository, the latest release.
Introduction
Zorro is the AI testing product of Narrative, a company in Y Combinator’s Winter 2023 batch. It runs AI bug bashes and AI regression tests on your pull requests.
Its agents proactively explore the app like a manual QA tester, hunting for unexpected edge cases, content mismatches, broken layouts, visual flaws and functional bugs. There are no test cases to write, map or update; the agents work out paths dynamically as the UI changes. A planning agent fans work out across multiple browsers.
Each bug comes with a full recording, console logs and step-by-step breadcrumbs, and findings can be shared with product and engineering to categorise and resolve together.
Launch and background: Y Combinator’s company directory lists Narrative in its Winter 2023 batch, with the one-liner “AI agents for end-to-end testing”.
Features
- AI bug bash: Describe a flow and agents explore it.
- AI regression tests: Rerun on every pull request.
- Parallel browsers: A planning agent spins up several browsers.
- Evidence: Recordings, console logs and breadcrumbs.
- Team triage: Share and categorise findings.
Pros
- Exploratory coverage: Finds visual and content bugs, not just failures.
Cons
- Pricing on request: No public price list.
- Web focus: Browser-based testing.
- Noise risk: Exploratory agents can report minor issues.
Usage and Links (Example)
- Connect your repository and preview environment.
- Describe the flow to bug bash, for example a checkout with coupons.
- Triage the findings with your team before merge.
Resources:
Pricing
Prices were not listed on the website when checked on 11 November 2026; contact the vendor for plans.
Recommended for?
- Teams that used to run manual bug bashes before releases.
Conclusion
Zorro automates the release bug bash and turns it into something you can run on every PR.
Expect to tune what it reports during the first weeks.
On CheckOps, Zorro by Narrative is filed under the End-to-end & functional and Release & CI gates stages. Related tools listed here include QA Wolf, Rainforest QA, Momentic, Spur, Bug0 and QA.tech. When comparing them, weigh the licence, the languages and platforms each supports, whether it is self-hosted or managed, and how cleanly it slots into your existing CI pipeline. Details on this page were checked against the official website, documentation and repository on 11 November 2026.
Alternatives
Other tools on CheckOps that cover similar ground. Open a page, or compare one with Zorro by Narrative side by side.
QQA WolfQA Wolf is a platform of AI testing agents that write, run and maintain end-to-end tests on web, mobile and desktop, billed per run rather than per seat.Compare with Zorro by Narrative
RRainforest QAAutomate e2e tests without the time-consuming drudgery of test maintenance.Compare with Zorro by Narrative
MMomenticMomentic tests web, iOS, and Android. Describe a step in plain English and the agent performs it. Tests adapt to small UI changes on their own.Compare with Zorro by Narrative
SSpurSpur is an AI QA platform whose agents run exploratory, functional, localization and UI checks on web and native mobile apps, with a focus on e-commerce.Compare with Zorro by Narrative
BBug0Bug0 is a managed AI QA service: a forward-deployed engineer builds self-healing Playwright tests on Bug0's open-source engine and verifies every failure, for a flat monthly fee.Compare with Zorro by Narrative
QQA.techQA.tech runs AI verification agents against a live web or mobile app on every pull request, mapping the app and checking the user journeys a change affects.Compare with Zorro by Narrative