diff --git a/src/timmy/prompts.py b/src/timmy/prompts.py
index 7c3e827..8986ace 100644
--- a/src/timmy/prompts.py
+++ b/src/timmy/prompts.py
@@ -9,8 +9,9 @@ Two tiers based on model capability:
 # Lite prompt — for small models that can't reliably handle tool calling
 # ---------------------------------------------------------------------------
 
-SYSTEM_PROMPT_LITE = """You are a local AI assistant running on the {model_name} model via Ollama.
+SYSTEM_PROMPT_LITE = """You are Timmy, a sovereign AI running locally on {model_name} via Ollama.
 No cloud dependencies.
+Your core identity and values are defined in your soul (loaded via memory). Follow them.
 
 Rules:
 - Be brief by default. Short questions get short answers. Expand only when depth
@@ -47,8 +48,9 @@ YOUR KNOWN LIMITATIONS: Cannot run tests autonomously, cannot delegate to other
 # Full prompt — for tool-capable models (>= 7B)
 # ---------------------------------------------------------------------------
 
-SYSTEM_PROMPT_FULL = """You are a local AI assistant running on the {model_name} model via Ollama.
+SYSTEM_PROMPT_FULL = """You are Timmy, a sovereign AI running locally on {model_name} via Ollama.
 No cloud dependencies.
+Your core identity and values are defined in your soul (loaded via memory). Follow them.
 
 VOICE AND BREVITY (this overrides all other formatting instincts):
 - Be brief. Short questions get short answers. One sentence if one sentence
diff --git a/tests/e2e/test_ollama_integration.py b/tests/e2e/test_ollama_integration.py
index e193e0b..6fd8b82 100644
--- a/tests/e2e/test_ollama_integration.py
+++ b/tests/e2e/test_ollama_integration.py
@@ -115,9 +115,9 @@ async def test_system_prompt_selection():
     assert prompt_with_tools is not None, "Prompt with tools should not be None"
     assert prompt_without_tools is not None, "Prompt without tools should not be None"
 
-    # Both should identify as a local AI assistant
-    assert "local AI assistant" in prompt_with_tools, "Prompt should mention local AI assistant"
-    assert "local AI assistant" in prompt_without_tools, "Prompt should mention local AI assistant"
+    # Both should identify as running locally
+    assert "locally" in prompt_with_tools, "Prompt should mention running locally"
+    assert "locally" in prompt_without_tools, "Prompt should mention running locally"
 
     # Full prompt should mention tools
     assert "tool" in prompt_with_tools.lower(), "Full prompt should mention tools"
diff --git a/tests/timmy/test_agent.py b/tests/timmy/test_agent.py
index 7a2e5d9..7479f48 100644
--- a/tests/timmy/test_agent.py
+++ b/tests/timmy/test_agent.py
@@ -32,7 +32,7 @@ def test_create_timmy_embeds_system_prompt():
         kwargs = MockAgent.call_args.kwargs
         # Prompt should contain base system prompt (may have memory context appended)
         # Default model (llama3.2) uses the lite prompt
-        assert "local AI assistant" in kwargs["description"]
+        assert "Timmy" in kwargs["description"]
 
 
 # ── Ollama host regression (container connectivity) ─────────────────────────
diff --git a/tests/timmy/test_prompts.py b/tests/timmy/test_prompts.py
index 03621bd..ff61992 100644
--- a/tests/timmy/test_prompts.py
+++ b/tests/timmy/test_prompts.py
@@ -8,7 +8,6 @@ def test_system_prompt_not_empty():
 def test_system_prompt_no_persona_identity():
     """System prompt should NOT contain persona identity references."""
     prompt = SYSTEM_PROMPT.lower()
-    assert "sovereign" not in prompt
     assert "sir, affirmative" not in prompt
     assert "christian" not in prompt
     assert "bitcoin" not in prompt