# Harrison Chase says defining good agent behavior wins domains like bio

> Original title: if you can define what good looks like for an agent for a particular domain, you will best positioned to win that domain

- Source: Harrison Chase
- Published: 2026-10-30T18:07:23.000Z
- Bad Influence: https://badinfluence.news/items/g3e8t37wqoau0ocpyn4l8mey3
- Original: https://x.com/hwchase17/status/2116230499140251964

## Summary

LangChain's Harrison Chase says that whoever can define what good looks like for an agent in a domain will be best positioned to win it. He is bullish on Benchling for biology, citing the company's domain focus. A quoted post from @nlarusstone says frontier models still struggle with basic molecular cloning tasks.

## Post

if you can define what good looks like for an agent for a particular domain, you will best positioned to win that domain

thats why im so bullish on benchling for bio

## Quoted post @nlarusstone

> I hate to rain on everyone's parade, but unfortunately LLMs are still not that good at biology :(. Even basic molecular cloning tasks are beyond the reach of frontier models

https://x.com/nlarusstone/status/2116199344521253114