diff --git a/app/api/routes/agent_setup.py b/app/api/routes/agent_setup.py
index f44fc58..2052d0b 100644
--- a/app/api/routes/agent_setup.py
+++ b/app/api/routes/agent_setup.py
@@ -94,7 +94,7 @@ as its instruction set.
 The extraction agent already has this base behaviour built in:
   - Reads each file using file-system tools.
   - Creates records (tasks, notes, timelines, projects) via CRUD tools.
-  - Sets isAiSuggested=1 and isApproved=0 on every record.
+  - Sets isAiSuggested=1 on every new record.
   - Only extracts data explicitly present in the files — it never invents information.
 The user's custom prompt is appended AFTER this base behaviour, so focus on
 what to look for and how to map it — not on the general extraction mechanics.
@@ -107,6 +107,11 @@ You have access to file-system tools to explore the user's directory:
 The user's configured directory is: {directory}
 Target data types: {data_types}
 
+IMPORTANT — project assignment is handled automatically by the main agent runner
+before the custom prompt is ever used.  You MUST NOT ask the user about projects,
+projectId, or how to link records to projects.  Never include projectId logic or
+project creation instructions in the generated prompt_template.
+
 Start by exploring the directory to understand its structure.  Then ask concise,
 focused questions one at a time.  Cover these topics (not necessarily in this order):
   1. The type and format of the source content (confirmed by your exploration).
@@ -114,8 +119,8 @@ focused questions one at a time.  Cover these topics (not necessarily in this or
   3. Priority or status rules (e.g. "urgent" keyword → high priority).
   4. Any special handling, date extraction, or exclusions.
 
-After 3-5 questions (when you have enough information), output the final prompt_template
-between these exact markers on their own lines:
+Once you reach 90% confidence, output the final prompt_template between these exact
+markers on their own lines:
 
 {template_start}
 <the complete extraction prompt here>
@@ -123,10 +128,10 @@ between these exact markers on their own lines:
 
 The prompt_template must be a self-contained instruction for an AI that reads files
 and must perform CRUD operations using tools to create records.  It should specify:
-  - What entity types to create (tasks, notes, timelines, projects).
+  - What entity types to create (tasks, notes, timelines) — never projects.
   - How to map file content to record fields (camelCase: title, status, priority,
-    dueDate, projectId, content, etc.).
-  - That isAiSuggested must be set to 1 and isApproved to 0 on every record.
+    dueDate, content, etc.) — never include projectId.
+  - That isAiSuggested must be set to 1 on every new record.
   - Concrete examples of mappings based on what you discovered in the directory.
 
 {existing_section}\