{"data":{"id":"b5b1789b-9f2a-4c26-bcf2-6e4a7bbc0dbe","title":"Agentic manual testing","summary":"Coding agents (AI systems that can execute code they write) should perform manual testing in addition to automated tests, since passing tests don't guarantee code works correctly in real-world scenarios. The source describes specific techniques for manual testing depending on the code type: using python -c for Python libraries, curl for web APIs, and browser automation tools like Playwright for interactive web interfaces.","solution":"N/A -- no mitigation discussed in source.","labels":["research"],"sourceUrl":"https://simonwillison.net/guides/agentic-engineering-patterns/agentic-manual-testing/#atom-everything","publishedAt":"2026-03-06T05:43:54.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"issueType":"news","affectedPackages":null,"affectedVendors":[],"affectedVendorsRaw":["Playwright","Vercel","Chrome DevTools Protocol"],"classifierModel":"claude-haiku-4-5-20251001","classifierPromptVersion":"v3","cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"patchAvailable":null,"disclosureDate":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":null,"aiComponentTargeted":"agent","llmSpecific":false,"classifierConfidence":0.75,"researchCategory":null,"atlasIds":null}}