From e58e8c9467852e5c13d5cb4c10c3141e761b88e5 Mon Sep 17 00:00:00 2001 From: Eldar Borge <43198995+EldarBorge@users.noreply.github.com> Date: Thu, 16 Jul 2026 19:41:16 +0200 Subject: [PATCH] docs: describe AI Team's place in the current Borge Labs delivery loop Add the deployed-configuration paragraph under Deployed Example, link the supervised delivery loop note, and use plain punctuation in the case study. Co-Authored-By: Claude Fable 5 --- README.md | 7 +++++++ docs/case-study.md | 2 +- 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 10b1aff..6e1ddf2 100644 --- a/README.md +++ b/README.md @@ -523,6 +523,13 @@ Politikkradar uses AI Team as one deployed configuration for Borge Labs. The framework itself is domain-agnostic: each organization supplies its own config, personas, repositories, memory rules and operating context. +In Borge Labs' own delivery loop, the deployed AI Team configuration handles the +Slack-facing work: teammates triage requests, draft specifications, file and +consume work-queue issues, and relay human approvals. Implementation runs in a +separate supervised pipeline, not in this repository. +[A supervised multi-agent delivery loop](https://borge-labs.no/notes/supervised-multi-agent-delivery/) +describes that operating model. + The [dogfooding case study](docs/case-study.md) describes what daily internal use did and did not validate without publishing private workspace content. See the [research release notes](docs/research-release.md) for the bounded release scope. diff --git a/docs/case-study.md b/docs/case-study.md index 7b49ccb..03e7d12 100644 --- a/docs/case-study.md +++ b/docs/case-study.md @@ -42,7 +42,7 @@ leakage. Human approval remained the right boundary for consequential actions. The system was strongest at discussion, synthesis, critique, drafting and surfacing -open work—not at autonomously publishing, deploying or making commitments. +open work, not at autonomously publishing, deploying or making commitments. ## What remained difficult