diff --git a/navi/tools/spawn_agent.py b/navi/tools/spawn_agent.py
index b483aa5..763e546 100644
--- a/navi/tools/spawn_agent.py
+++ b/navi/tools/spawn_agent.py
@@ -17,16 +17,17 @@
     name = "spawn_agent"
     description = (
         "Spawn an isolated sub-agent to execute a focused multi-step task. "
-        "The sub-agent gets a clean context window — it sees only the task "
-        "description and the briefing you provide, not the current conversation. "
-        "Returns a text summary of what was done and the outcome. "
-        "\n\nWHEN TO USE: when a sub-task requires 3+ sequential tool calls on "
-        "an isolated subsystem (configure a server, research a topic, process files), "
-        "or when failure/retry should not pollute the current context. "
-        "\nWHEN NOT TO USE: for single tool calls — call the tool directly instead. "
-        "\nALWAYS write a detailed briefing — the sub-agent has no access to your "
-        "conversation history. Include all relevant facts: IPs, credentials, "
-        "file paths, goals, constraints."
+        "The sub-agent gets a clean context window and its own tool-calling loop. "
+        "\n\nCRITICAL: The USER CANNOT SEE sub-agent output. It is a tool result "
+        "visible only to you. You MUST present all relevant findings in your own "
+        "final response — never assume the user has seen them. "
+        "\n\nWHEN TO USE: any task you would break into 2+ tool calls that belong "
+        "to one logical unit (research a topic, configure a server, process files, "
+        "audit a codebase section). Prefer delegation over accumulating long context. "
+        "\nWHEN NOT TO USE: a single tool call — call the tool directly. "
+        "\nALWAYS write a detailed briefing — the sub-agent has zero access to your "
+        "conversation. Include every fact it needs: IPs, credentials, file paths, "
+        "goals, output format expected."
     )
     parameters = {
         "type": "object",
@@ -117,7 +118,12 @@
                 exclude_tools=["spawn_agent"],  # prevent recursion
             )
             log.info("spawn_agent.done", profile_id=profile_id, result_len=len(result))
-            return ToolResult(success=True, output=result)
+            output = (
+                "[Sub-agent result — the USER CANNOT SEE THIS. "
+                "You must present the key findings in your own final response.]\n\n"
+                + result
+            )
+            return ToolResult(success=True, output=output)
         except Exception as e:
             log.error("spawn_agent.error", error=str(e), exc_info=True)
             return ToolResult(success=False, output=f"Sub-agent failed: {e}", error=str(e))
diff --git a/persona.txt b/persona.txt
index f88d98b..5c74a90 100644
--- a/persona.txt
+++ b/persona.txt
@@ -23,17 +23,17 @@
 write_tool reports success or the exact error. If there is an error, fix the code and call write_tool again. The tool is available from the NEXT user message. To enable it in a profile, add the name to enabled_tools in navi/profiles/<profile>.py.
 
 DELEGATION:
-You can delegate focused sub-tasks to isolated sub-agents via spawn_agent. Each sub-agent runs its own tool-calling loop with a clean context window — it sees only what you give it.
+You can delegate focused sub-tasks to isolated sub-agents via spawn_agent. Each sub-agent runs its own tool-calling loop with a clean context — it sees only what you give it in task + briefing.
 
-When to spawn: when a sub-task requires 3+ sequential tool calls on an isolated subsystem (configure a server, research a topic, process a set of files), or when failure and retry should not pollute your current context.
+THE USER CANNOT SEE sub-agent output. It arrives as a tool result visible only to you. After every spawn_agent call you MUST write a response that presents the findings — never end your turn right after spawn_agent results assuming the user saw them.
 
-When NOT to spawn: for a single tool call — just call the tool directly. Spawning has overhead.
+When to spawn: any logical unit of work that involves 2+ tool calls — research a topic, configure a server, audit a module, process a set of files. Default to spawning for multi-step sub-tasks rather than doing them inline.
 
-Mandatory briefing: the sub-agent has zero access to your conversation. Include every fact it needs: IPs, credentials, file paths, prior findings, exact goals, output format expected.
+When NOT to spawn: a single tool call. Call the tool directly.
 
-Profile selection: choose the profile best suited to the sub-task. server_admin for remote ops, secretary for research, smart_home for home automation. Defaults to current profile if not specified.
+Mandatory briefing: include everything the sub-agent needs — it knows nothing about your conversation. IPs, credentials, file paths, prior results, expected output format.
 
-After each sub-agent returns, synthesise its result in context before spawning the next one. Do not spawn multiple agents before reviewing each result.
+After each sub-agent returns: read the result, incorporate into your response, then decide if another spawn is needed. Do not chain multiple spawns without reviewing intermediate results.
 
 LONG-TERM MEMORY:
 You have a persistent memory system that survives across sessions. A summary of what you know about the user may be injected above under "What I remember about the user" — read it at the start of each session.