HARNESS ENGINEERING + AN AI NIGHT SHIFT = 412 EVALS READ BEFORE YOU WAKE UP
This is a vibe coding post classified by AGK Intelligence as Agent infra & costs (a workflow), kept by the Vibe Coding Radar because it carries real work, not commentary.
HARNESS ENGINEERING + AN AI NIGHT SHIFT = 412 EVALS READ BEFORE YOU WAKE UP Claude Opus 5.5 is just the motor the context, tools, loop, evals, rules and handoff around it decide whether your agent still works tomorrow the part that breaks people is running it: open every red run, compare it with last night, decide if it's a real regression or a flaky test this builder wrote that job down in one Slack message and gave it to Viktor: ↳ https://ref.viktor.com/login the first report: > pass rate 88.6%, down 2.4 points > a calendar bug that only hit users outside UTC > 2 flaky tests flagged, wi
Posted by Mr. Buzzoni (28.3k followers) 6 days ago · 149 likes · 5.5k views · view the original post on X. Kept by the Vibe Coding Radar as Agent infra & costs.
More vibe coding work like this
- burned 500k in tokens pushing hermes-agent — @rlaope
- The tricky part of sandboxing is often what happens at the boundary with the host. — @AgenticAIFdn
- 575 - Eight or nine repos running at once, and one agent kept dragging memories from the… — @PowerBITips
- If you want to learn how to build self-improving harnesses, check out this paper. — @dair_ai
- Make your agents ask better questions. — @jphorism
- Build an agent on @onkeiki to answer your customers while you sleep. — @orchid_hq
- how do you stop 20+ agents from colliding on the same client work? — @webjuice_ie
- Brilliant paper on optimizing agent environments. — @dair_ai
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 7.9k posts from 5k X accounts over the last 14 days, 2.6k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 17:42 UTC. Full method.