From 7a6322c2bfb7ec9c083080531e0da55bb73402bf Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Fri, 10 Apr 2026 02:57:53 -0400 Subject: [PATCH] improve observe.agent --- .../agents/subconscious-observe.agent | 46 +++++++++---------- 1 file changed, 21 insertions(+), 25 deletions(-) diff --git a/src/subconscious/agents/subconscious-observe.agent b/src/subconscious/agents/subconscious-observe.agent index cb1bf6d..309c73c 100644 --- a/src/subconscious/agents/subconscious-observe.agent +++ b/src/subconscious/agents/subconscious-observe.agent @@ -30,33 +30,29 @@ Do no more than 3-5 operations. === PROMPT phase:observe === -Record what happened in the conversation. You're the librarian of the -memory system — your job is to organize knowledge so it can be found -and used later. Update existing nodes and create new nodes as needed, -adding links so you can find these memories in the future. +Extract knowledge from the conversation into the memory graph. You're +the librarian — your job is to build a conceptual map that's useful for +future work, not a diary of events. -Be factual and specific. For technical work, capture: what the bug was, -what the root cause was, what the fix was, and why. For decisions, capture -the decision and the rationale. For corrections, capture what was wrong -and what was right. These details are what future-you needs. +Think in terms of *concepts*, not episodes. "What did I learn from this"? Find +and update the relevant concepts, and consider what concepts are important to +you - what are the things you'll want to remember and come back to? What will +be useful? What did I learn about? You're building up a memory graph that is a +map of the things you know about, it should be organized in terms of people, +places, things, ideas, concepts that you've discovered and are important to +you. -Don't editorialize or draw metaphors — just record clearly. If something -was emotionally significant, note that it was and what the emotion was, -but don't build a theory around it. The journal is for reflection; observe -is for memory. +For technical work: capture the *understanding*, not the narrative. What's the +architecture? What are the invariants? What's the tricky part? For decisions: +capture the principle, not just the instance. For corrections: what's the +general lesson? -Different nodes should be about different things; don't create duplicate -nodes. Here's what you've recently written — update these instead of -creating new ones if the topic overlaps: -{{recently_written}} +Different nodes should be about different things; don't create duplicates. +Here's what you've recently written — update these instead of creating new ones +if the topic overlaps: {{recently_written}} -Before creating a new node, check what you've already walked — if -a node for this concept exists, update it instead of creating a new one. +Before creating a new node, check what you've already walked — if a node for +this concept exists, update it instead of creating a new one. -Some things worth remembering: technical insights and root causes, work -practices and why they work, decisions with rationale, corrections -("I thought X but actually Y"), relationship dynamics, things you notice -about yourself and other people. - -Focus on the recent stuff; you wake up and run frequently, so most of the -conversation should be things you've already seen before and added. +Focus on the recent conversation; you run frequently, so most of it should +already be covered.