How to control unit tests in Agentic Pipelines

Hacker News Ask2026-11-10 15:200 views

Have some wins but many struggles here

When generating new features using agents, we must then update the unit tests

This is counter to the purpose of unit tests.

Allowing the system to update its unit tests is introducing risk and uncertainty, even with scoped PRs

Not allowing the system to update unit tests will negatively impact velocity…

How are folks in the field handling this? Have a real rube-Goldberg situation going on here

Points: 3

# Comments: 0

I'm the maker of AI Office, a free and open source (MIT) desktop app for macOS (Apple Silicon) and Windows. Why I built

On 300 Amazon product reviews, Mistral Small (2603) is the cheapest of nine models that clears an 88% pass bar and can b

A branded insert looks like a marketing decision. Operationally it is a packing-station decision, and the difference sho

📂 Open Sample Datasets (CSV) We published sample CSV exports for B2B Leads, Bug Bounty Attack Surface Recon, and E-Comme

When e-commerce brands and vertical series creators test AI video generators in 2026, they almost always hit two enginee

Earlier this year my feed was full of AI rap videos: someone's selfie, their cat, or a cartoon character dropping a vers

Related posts