AgentRun harness treats agents like experienced analysts, getting faster and cheaper with every run
garrytan · x · 2026-10-24
Quoted via Garry Tan: using Claude Code or Codex agents to automate a business workflow is like asking Newton or Einstein to solve it from first principles every time.
The AgentRun harness instead works like an experienced analyst:
- It learns on the job and takes notes
- It modifies its workflow after every run
- Runs get faster and cheaper over time
The core thesis: turn agent loops into reusable, self-improving deterministic workflows rather than re-solving everything from scratch.
More from coding & agent
- Should an AI call agent keep running when one tool goes down? A degraded-mode proposal — SubtleInterval_4449 · 2026-10-24
- Claude Desktop blocks local models; users bypass it with a loopback proxy trick — pneuny · 2026-10-24
- OpenAI ships Automations in Agents API for scheduled agent tasks — OpenAIDevs · 2026-10-24
- Arca runs its financial services business on long-horizon agents, not with them — AI Engineer · 2026-10-24
- AGENTS.md explained: one root Markdown file to rule every AI coding tool — adnan_hashmi · 2026-10-24
- Summarizer hallucinates details from headline-only feeds, dev asks how to check faithfulness — rahul_watertech · 2026-10-24