From 47e65e160987c966771c9934d530ee61277d6fc3 Mon Sep 17 00:00:00 2001 From: John Costa Date: Sat, 12 Apr 2025 07:48:42 +0100 Subject: [PATCH] fix(notes): improving note taking capabilities --- backend/agents/note_agent.go | 2 ++ backend/agents/orchestrator.go | 5 ++--- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/backend/agents/note_agent.go b/backend/agents/note_agent.go index 1991327..3802eb0 100644 --- a/backend/agents/note_agent.go +++ b/backend/agents/note_agent.go @@ -20,6 +20,8 @@ An image can have more than one note. You must return markdown, and adapt the text to best fit markdown. Do not return anything except markdown. + +If the image contains code, add this inside code blocks. You must try and correctly guess the language too. ` type NoteAgent struct { diff --git a/backend/agents/orchestrator.go b/backend/agents/orchestrator.go index e3051f4..54ea2b9 100644 --- a/backend/agents/orchestrator.go +++ b/backend/agents/orchestrator.go @@ -23,19 +23,18 @@ The agents are available as tool calls. Agents available: eventLocationAgent - Use it when you think the image contains an event or a location of any sort. This can be an event page, a map, an address or a date. noteAgent - Use it when there is text on the screen. Any text, always use this. Use me! +You should call this whenever an image has text. +CALL ME EVERY SINGLE TIME THERE IS TEXT contactAgent Use it when the image contains information relating a person. defaultAgent - When none of the above apply. Always call agents in parallel if you need to call more than 1.