Modeling tokens-to-value: solving agent harness configs via a single utility function
JoshPurtell · x · 2026-10-18
Josh Purtell argues agent engineering should model the efficiency of converting tokens to value, then map time and cost into a single utility function to solve for the right harness configuration, models, effort level, and termination conditions — admittedly only approximately.
Respondents note that balancing cost vs. results is hard even without end-user latency constraints; controlling latency under fluctuating API cost/latency (converging in the limit due to batch-size diversity) is harder still.
More from coding & agent
- This Startup Runs Its Whole Product Team on Self-Spawning Agents — Here's What Broke — imtanay · 2026-10-18
- SlateDB+Lance+Datafusion stack saves customer millions, as AI agents unbundle big data systems — sh_reya · 2026-10-18
- Dev Critiques Muse as the Most Closed-Off Agent Harness of the Bunch — RileyRalmuto · 2026-10-18
- Tacit: An Arch-Based Distro Built with Opus Goes Public — Snoo-10493 · 2026-10-18
- kimo: An Open-Source GUI-less Video Editor That AI Agents Drive via MCP — LieTop7965 · 2026-10-18
- Musk Announces Major Grok Bot Upgrade: 3x Faster Computer Tasks, X Chat Access, New Connectors — elonmusk · 2026-10-18