Alex Zhang defines the agent harness: code around an LLM, an agent once placed in an environment
CShorten30 · x · 2026-09-04
On the Weaviate Podcast, agent researcher Alex Zhang argues that scaffold, harness, and agent are all the same thing.
- Harness defined: whatever code you build around a language model is the harness.
- Relation to agents: that same object, once placed in an environment, becomes the agent.
- He was surprised the question is contested at all — a sign of how young the vocabulary of the field still is.
The episode offers a working definition of the agent harness, useful for anyone thinking about agent engineering terminology.
More from coding & agent
- Yutori ships Navigator n2, a 27B frontier computer-use model, tops MyPCBench — kohjingyu · 2026-09-04
- OpenAI ships async function calling, mid-turn steering and cache-safe reasoning effort in Responses API — msg · 2026-09-04
- Dev uses Codex as co-presenter at OpenAI hackathon — amaarora · 2026-09-04
- Standing out when everyone has AI: subtract the generic, then go deep — round · 2026-09-04
- GPT-6 Astra tip: delete your AGENTS.md and start fresh, old cruft will haunt you — i_dg23 · 2026-09-04
- Cognition brings GPT-6 Astra to Devin: near-Fable 5 performance at 64% lower cost — sandersted · 2026-09-04