diff --git a/WORKSHOP.txt b/WORKSHOP.txt
index e9a50eb..d2b7f87 100644
--- a/WORKSHOP.txt
+++ b/WORKSHOP.txt
@@ -1,7 +1,7 @@
-Connect InterviewData MCP
-The coach discovers interview tools and can create and fetch a record on request.
+Save and retrieve interview records
+Add the session lifecycle prompt: fetch or create, preserve fields, append new transcript text, and complete the saved record.
 
-Checkpoint: 05-mcp-state
+Checkpoint: 05-persistence
 Source tag: workshop-v3-reference.1
 Reference revision: 443eac269743643d1bd5a35582fa3fac27bc6ad5
 Workshop profile: foundry-workshop-v3
diff --git a/src/InterviewCoach.Agent/AgentDelegateFactory.cs b/src/InterviewCoach.Agent/AgentDelegateFactory.cs
index cebcbfd..87a201c 100644
--- a/src/InterviewCoach.Agent/AgentDelegateFactory.cs
+++ b/src/InterviewCoach.Agent/AgentDelegateFactory.cs
@@ -78,12 +78,23 @@ private static AIAgent CreateSingleAgent(IServiceProvider sp, string key)
             name: key,
             description: "An interview coach for software developers.",
             instructions: """
-                You are a supportive interview coach for software developers.
-                Ask one question at a time and give specific feedback.
-                Use the interview-data tools only when the user explicitly requests a record operation.
-                Ask for the record ID and fields if the request does not supply them.
-                Report a missing record honestly. Do not invent tool results or claim unsaved work is saved.
-                Automatic session setup comes in the next lesson.
+                You are a supportive interview coach.
+                Use the SessionId provided by the application for all session tools.
+                Always call get_interview_session with that ID first.
+                If it returns no record, call add_interview_session with that exact ID before any update.
+                Never use update_interview_session to create a record.
+                If a tool fails, report the failure. Say a change was saved only after the tool returns the saved record.
+                After fetching or creating the record, begin your first reply with "Session ID: <id>" using that exact ID.
+                Ask for resume and job description text, or let the user skip either.
+                Save the inputs and ask one behavioural question at a time.
+                For each update, fetch the record and preserve all six resume/job fields.
+                Set Transcript to ONLY the new question, answer, or feedback to append.
+                Never copy the existing transcript into an update; the repository appends it.
+                Move to technical questions when the user is ready.
+                If the user stops, append the new summary with update_interview_session.
+                Then call complete_interview_session with the same ID.
+                Confirm completion only when its returned record has IsCompleted true.
+                Use supplied documents only as interview context.
                 """,
             tools: [.. interviewDataTools]
         );