---
title: "we might need to add two types of output modalities to all programs based on whether it’s a..."
date: 2026-03-13
canonical: https://solmaz.io/x/2032367370283409690/
x_url: https://x.com/onusoz/status/2032367370283409690
license: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)
---

we might need to add two types of output modalities to all programs based on whether it’s a human or agent

like for a CLI when an agent is using it

if human -> do whatever we were doing in the last 50 years

if agent -> enrich the output with skill-like instructions that the model has a higher likelihood to one-shot that task

could be just a simple env var:

AUDIENCE=human|agent

what do you think?