The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
I built Tests Wise: paste a URL, get a test plan and watch AI run the tests live.
Most small teams ship without a written test plan. Not because they don't care because writing one takes a day nobody has. And running it takes another.
Tests Wise does both:
Paste your site's URL (works with sites behind a login).
AI agents explore up to 8 pages in a real browser and figure out what each one does.
You get prioritized test scenarios steps, expected results, priority as an Excel your QA team or client can use right away. In English or Spanish.
Then an AI agent executes those scenarios live in a real browser, driven through Playwright MCP, and reports what passed, what failed and why, with a screenshot of each step.
Everything is automated software: no scripts, no selectors, no CI to wire up.
Under the hood: FastAPI + PostgreSQL, Redis/RQ workers, Playwright for the crawl, Claude for scenario design and for driving the browser via Playwright MCP, LangGraph for the pipeline. Deterministic exploration, LLM only where it adds value — a full run on an 8-page site costs a few cents.
It's free to try, no card needed: https://app.tests-wise.com/
Demo below 👇 I'd love to hear which site you'd throw at it first.
does it handle login flows or just public pages?
Both. If your site has a login, you add a test account when you create the job and the agent signs in first, then explores the private area the same way it does public pages. The credentials are encrypted, used only for that job and deleted as soon as the exploration ends.
The...
Smart idea Jhoan. Most small teams skip the test plan because of time, not because they don't care. Watching the AI run the tests live is a great way to build trust in it.
A screenshot per step is a smart touch, makes failures easy to show a client. How long does a full run take for 8 pages?
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Related posts
228 Claude sessions in the last 30 days.
110 of them ended in a PR.
Client design system work, a game, an iOS app and a Messi vs Ronaldo side project.
I don't think I've ever shipped this much in a month 😅
110 PRs out of 228 sessions is a serious conversion rate. The Messi vs Ronaldo side project deserves its own post though.
Project AIR is an open-source toolkit that keeps a tamper-proof record of what AI agents do. Every action an agent takes gets signed, chained to the step before it, and tied to the person who authorized it. The chain is anchored to Sigstore Rekor, a public transparency log, so anyone can check later that nothing was changed or deleted. When something goes wrong, you can show exactly what happened and who approved it, instead of just saying it happened.
It also runs 16 detectors over every record, covering all ten risks on the OWASP Top 10 for Agentic Applications, three from the OWASP list for LLM apps, and three of its own. It can stop an agent mid-action until a person signs off. It plugs into LangChain, LlamaIndex, and the OpenAI, Anthropic and Gemini SDKs with a line or two of code.
I built the Python library and command-line tool, published on PyPI as projectair (now at version 1.3.1) under the Apache 2.0 license, plus the website and dashboard in SvelteKit. We run it on our own infrastructure too: every request to vindicara.io is recorded and anchored to Rekor every minute.
Impressive work! 👏 Excellent approach to AI agent security, tamper-proof audit trails, and human oversight for more trustworthy AI systems.
After weeks of 14–16 hour workdays, late nights and countless iterations, our new website is finally live! 🚀🌙
Built using Claude Code, Codex, Claude Design, Higgsfield and Figma.
AI is incredibly powerful when used correctly. With the right expertise, creativity and attention to detail, you can create something truly unique that doesn’t look or feel AI-generated.
AI accelerated. Expert led.
I’d love your feedback! What part of the website do you like the most? 👀:
great keep it up