From 50f9c57112fe012987dafc0ffcc3da0ef123b97d Mon Sep 17 00:00:00 2001 From: Chris Rickman Date: Mon, 16 Mar 2026 22:35:35 -0700 Subject: [PATCH] Cleanup --- docs/harness/pipeline.md | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/docs/harness/pipeline.md b/docs/harness/pipeline.md index b28cfd0042..c34424e46d 100644 --- a/docs/harness/pipeline.md +++ b/docs/harness/pipeline.md @@ -10,6 +10,7 @@ What it provides: - **Governance** — permissions, human-in-the-loop, policies - **Context management** — compaction, eviction, externalization - **Observability** — traces, transcripts, replay + ### Where We Stand MAF compared against DeepAgents, Amplifier, Opencode, Copilot CLI, OpenAI Codex, and Claude Code — every one of them has these capabilities. MAF has some partially, most not at all. @@ -31,8 +32,6 @@ MAF compared against DeepAgents, Amplifier, Opencode, Copilot CLI, OpenAI Codex, ### Agent/User Orchestration -#### Slot Filling (a.k.a. "Guided Conversations") - How does the harness manage structured, multi-turn data collection from the user? What's the interaction model between the outer loop and user-facing slot-filling prompts? How does it compose with compaction and task management? How does the agent re-ask or repair slot values after partial completion? ### Compaction Strategy