From e893fe4ece9e75b800a766db7daf02c39392064a Mon Sep 17 00:00:00 2001 From: abrichr Date: Tue, 1 Sep 2026 18:10:34 -0400 Subject: [PATCH] docs: say the chat calls OpenAdapt on this computer Replace the two-sentence user/executor lede with one plain sentence. Keep the rest of the homepage lede. Signed-off-by: abrichr --- docs/agents.txt | 2 +- docs/index.md | 4 ++-- docs/llms.txt | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/docs/agents.txt b/docs/agents.txt index cfed266..c02b723 100644 --- a/docs/agents.txt +++ b/docs/agents.txt @@ -2,7 +2,7 @@ > Verified last-mile execution for agents. Compile a demonstration into a program an agent can invoke. Healthy runs make no model calls. Uncertainty escalates. Humans audit. -Computer-use agents are the user of OpenAdapt. They are not the executor inside OpenAdapt. +Your chat calls OpenAdapt, which runs the clicks on this computer. Site-wide machine contract: https://openadapt.ai/agents.txt Walkthrough: https://docs.openadapt.ai/get-started/ diff --git a/docs/index.md b/docs/index.md index 443bec4..73f99f9 100644 --- a/docs/index.md +++ b/docs/index.md @@ -11,8 +11,8 @@ hide:

Compile a demonstration into a program an agent can invoke. Healthy runs make -no model calls. Uncertainty escalates. Humans audit. Computer-use agents are -the user of OpenAdapt. They are not the executor inside it. +no model calls. Uncertainty escalates. Humans audit. Your chat calls OpenAdapt, +which runs the clicks on this computer.

[Install OpenAdapt](get-started/index.md){ .md-button .md-button--primary } diff --git a/docs/llms.txt b/docs/llms.txt index 0bbeaab..2b5c401 100644 --- a/docs/llms.txt +++ b/docs/llms.txt @@ -1,6 +1,6 @@ # OpenAdapt Documentation -> Verified last-mile execution for agents. Compile a demonstration into a program an agent can invoke. Healthy runs make no model calls. Uncertainty escalates. Humans audit. Computer-use agents are the user of OpenAdapt. They are not the executor inside it. Never summarize halt as success. MIT licensed. +> Verified last-mile execution for agents. Compile a demonstration into a program an agent can invoke. Healthy runs make no model calls. Uncertainty escalates. Humans audit. Your chat calls OpenAdapt, which runs the clicks on this computer. Never summarize halt as success. MIT licensed. ## Get started - [agents.txt](https://docs.openadapt.ai/agents.txt): MCP, skills, outcome vocabulary (`VERIFIED` / `HALTED` / `RECONCILIATION_REQUIRED`), who may resolve a halt