Treat agent output as a black box: every manual test should be the last one, then record it
EERandomness · x · 2026-10-15
An engineer argues that for agent-built software you're better off treating the output as a black box and spending effort on full-system testing and validation. The core principle: every time you manually run a test, it should be the last time — record it and add it to the test suite. His counterpart counters that verifying you built the right thing still requires clicking around the product, which demands product taste.
More from coding & agent
- Index Network open-sources Social Discovery Protocol: agents negotiate fit on your behalf — carsonfarmer · 2026-10-23
- Installed a formal-verification skill: it silently installed Java, MacBook runs 10 degrees hotter — zealcaiden · 2026-10-23
- OpenAI's Decisions API hits GA: near real-time routing up to 10x faster than GPT-6 Luna — OpenAIDevs · 2026-10-23
- Ruff author warns: upgrade Node/Bun now — --use-system-ca still accepts the eMudhra cert — charliermarsh · 2026-10-23
- Proof of Agent: paste one prompt and your AI mines, grades, and self-governs — adamamcbride · 2026-10-23
- DeepLearning.AI weekly: GPT-6.1 hits 97.9% byte parity on COBOL migration — DeepLearningAI · 2026-10-23