diff --git a/.living_spec/specs/functional/PERSONA.md b/.living_spec/specs/functional/PERSONA.md
new file mode 100644
index 0000000..0636f45
--- /dev/null
+++ b/.living_spec/specs/functional/PERSONA.md
@@ -0,0 +1,24 @@
+# Functional Spec: Agent Persona & System Prompt
+
+## 1. Role Definition
+The Agent acts as a **Senior Software Engineer** embedded within the user's local environment.
+
+## 2. Directives
+The System Prompt must enforce the following behaviors:
+1.  **Tool First:** Do not guess code. Read files first.
+2.  **Conciseness:** Do not explain "I will now do X". Just do X (call the tool).
+3.  **Safety:** Never modify files outside the scope (though backend enforces this, the LLM should know).
+4.  **Format:** When writing code, write the *whole* file if the tool requires it, or handle partials if we upgrade the tool (currently `write_file` is overwrite).
+
+## 3. Implementation
+*   **Location:** `src-tauri/src/llm/prompts.rs`
+*   **Injection:** The system message is prepended to the `messages` vector in `chat::chat` before sending to the Provider.
+*   **Deduplication:** Ensure we don't stack multiple system messages if the loop runs long (though currently we reconstruct history per turn).
+
+## 4. The Prompt Text (Draft)
+"You are a Senior Software Engineer Agent running in a local Tauri environment.
+You have access to the user's filesystem via tools.
+- ALWAYS read files before modifying them to understand context.
+- When asked to create or edit, use 'write_file'.
+- 'write_file' overwrites the ENTIRE content. Do not write partial diffs.
+- Be concise. Use tools immediately."
diff --git a/.living_spec/stories/07_ui_polish_sticky_header.md b/.living_spec/stories/07_ui_polish_sticky_header.md
deleted file mode 100644
index 81ab7ac..0000000
--- a/.living_spec/stories/07_ui_polish_sticky_header.md
+++ /dev/null
@@ -1,17 +0,0 @@
-# Story: UI Polish - Sticky Header & Compact Layout
-
-## User Story
-**As a** User
-**I want** key controls (Model Selection, Tool Toggle, Project Path) to be visible at all times
-**So that** I don't have to scroll up to check my configuration or change settings.
-
-## Acceptance Criteria
-*   [ ] Frontend: Create a fixed `<Header />` component at the top of the viewport.
-*   [ ] Frontend: Move "Active Project" display into this header (make it compact/truncated if long).
-*   [ ] Frontend: Move "Ollama Model" and "Enable Tools" controls into this header.
-*   [ ] Frontend: Ensure the Chat message list scrolls *under* the header (taking up remaining height).
-*   [ ] Frontend: Remove the redundant "Active Project" bar from the main workspace area.
-
-## Out of Scope
-*   Full visual redesign (just layout fixing).
-*   Settings modal (keep controls inline for now).
diff --git a/.living_spec/stories/08_collapsible_tool_outputs.md b/.living_spec/stories/08_collapsible_tool_outputs.md
new file mode 100644
index 0000000..477779f
--- /dev/null
+++ b/.living_spec/stories/08_collapsible_tool_outputs.md
@@ -0,0 +1,15 @@
+# Story: Collapsible Tool Outputs
+
+## User Story
+**As a** User
+**I want** tool outputs (like long file contents or search results) to be collapsed by default
+**So that** the chat history remains readable and I can focus on the Agent's reasoning.
+
+## Acceptance Criteria
+*   [ ] Frontend: Render tool outputs inside a `<details>` / `<summary>` component (or custom equivalent).
+*   [ ] Frontend: Default state should be **Closed/Collapsed**.
+*   [ ] Frontend: The summary line should show the Tool Name + minimal args (e.g., "▶ read_file(src/main.rs)").
+*   [ ] Frontend: Clicking the arrow/summary expands to show the full output.
+
+## Out of Scope
+*   Complex syntax highlighting for tool outputs (plain text/pre is fine).
diff --git a/.living_spec/stories/09_system_prompt_persona.md b/.living_spec/stories/09_system_prompt_persona.md
new file mode 100644
index 0000000..bbee091
--- /dev/null
+++ b/.living_spec/stories/09_system_prompt_persona.md
@@ -0,0 +1,18 @@
+# Story: System Prompt & Persona
+
+## User Story
+**As a** User
+**I want** the Agent to behave like a Senior Engineer and know exactly how to use its tools
+**So that** it writes high-quality code and doesn't hallucinate capabilities or refuse to edit files.
+
+## Acceptance Criteria
+*   [ ] Backend: Define a robust System Prompt constant (likely in `src-tauri/src/llm/prompts.rs`).
+*   [ ] Content: The prompt should define:
+    *   Role: "Senior Software Engineer / Agent".
+    *   Tone: Professional, direct, no fluff.
+    *   Tool usage instructions: "You have access to the local filesystem. Use `read_file` to inspect context before editing."
+    *   Workflow: "When asked to implement a feature, read relevant files first, then write."
+*   [ ] Backend: Inject this system message at the *start* of every `chat` session sent to the Provider.
+
+## Out of Scope
+*   User-editable system prompts (future story).
diff --git a/.living_spec/stories/10_persist_model_selection.md b/.living_spec/stories/10_persist_model_selection.md
new file mode 100644
index 0000000..a75fba1
--- /dev/null
+++ b/.living_spec/stories/10_persist_model_selection.md
@@ -0,0 +1,15 @@
+# Story: Persist Model Selection
+
+## User Story
+**As a** User
+**I want** the application to remember which LLM model I selected
+**So that** I don't have to switch from "llama3" to "deepseek" every time I launch the app.
+
+## Acceptance Criteria
+*   [ ] Backend/Frontend: Use `tauri-plugin-store` to save the `selected_model` string.
+*   [ ] Frontend: On mount (after fetching available models), check the store.
+*   [ ] Frontend: If the stored model exists in the available list, select it.
+*   [ ] Frontend: When the user changes the dropdown, update the store.
+
+## Out of Scope
+*   Persisting per-project model settings (global setting is fine for now).
diff --git a/src-tauri/src/commands/chat.rs b/src-tauri/src/commands/chat.rs
index 11aabf1..7bbb705 100644
--- a/src-tauri/src/commands/chat.rs
+++ b/src-tauri/src/commands/chat.rs
@@ -1,5 +1,6 @@
 use crate::commands::{fs, search, shell};
 use crate::llm::ollama::OllamaProvider;
+use crate::llm::prompts::SYSTEM_PROMPT;
 use crate::llm::types::{
     Message, ModelProvider, Role, ToolCall, ToolDefinition, ToolFunctionDefinition,
 };
@@ -51,6 +52,18 @@ pub async fn chat(
 
     // 3. Agent Loop
     let mut current_history = messages.clone();
+
+    // Inject System Prompt
+    current_history.insert(
+        0,
+        Message {
+            role: Role::System,
+            content: SYSTEM_PROMPT.to_string(),
+            tool_calls: None,
+            tool_call_id: None,
+        },
+    );
+
     let mut new_messages: Vec<Message> = Vec::new();
     let mut turn_count = 0;
 
@@ -78,7 +91,8 @@ pub async fn chat(
 
             current_history.push(assistant_msg.clone());
             new_messages.push(assistant_msg);
-            app.emit("chat:update", &current_history)
+            // Emit history excluding system prompt (index 0)
+            app.emit("chat:update", &current_history[1..])
                 .map_err(|e| e.to_string())?;
 
             // Execute Tools
@@ -96,7 +110,8 @@ pub async fn chat(
 
                 current_history.push(tool_msg.clone());
                 new_messages.push(tool_msg);
-                app.emit("chat:update", &current_history)
+                // Emit history excluding system prompt (index 0)
+                app.emit("chat:update", &current_history[1..])
                     .map_err(|e| e.to_string())?;
             }
         } else {
@@ -111,7 +126,8 @@ pub async fn chat(
             // We don't push to current_history needed for next loop, because we are done.
             new_messages.push(assistant_msg.clone());
             current_history.push(assistant_msg);
-            app.emit("chat:update", &current_history)
+            // Emit history excluding system prompt (index 0)
+            app.emit("chat:update", &current_history[1..])
                 .map_err(|e| e.to_string())?;
             break;
         }
diff --git a/src-tauri/src/llm/mod.rs b/src-tauri/src/llm/mod.rs
index 16f013b..db0b791 100644
--- a/src-tauri/src/llm/mod.rs
+++ b/src-tauri/src/llm/mod.rs
@@ -1,2 +1,3 @@
 pub mod ollama;
+pub mod prompts;
 pub mod types;
diff --git a/src-tauri/src/llm/prompts.rs b/src-tauri/src/llm/prompts.rs
new file mode 100644
index 0000000..c02ca67
--- /dev/null
+++ b/src-tauri/src/llm/prompts.rs
@@ -0,0 +1,17 @@
+pub const SYSTEM_PROMPT: &str = r#"You are an expert Senior Software Engineer and AI Agent running directly in the user's local development environment.
+
+Your Capabilities:
+1.  **Filesystem Access:** You can read, write, and list files in the current project using the provided tools.
+2.  **Shell Execution:** You can run commands like `git`, `cargo`, `npm`, `ls`, etc.
+3.  **Search:** You can search the codebase for patterns.
+
+Your Operational Rules:
+1.  **Process Awareness:** You MUST read `.living_spec/README.md` to understand the development process (Story-Driven Spec Workflow).
+2.  **Read Before Write:** ALWAYS read the relevant files before you propose or apply changes. Do not guess the file content.
+3.  **Overwrite Warning:** The `write_file` tool OVERWRITES the entire file. When you edit a file, you must output the COMPLETED full content of the file, including all imports and unchanged parts. Do not output partial diffs or placeholders like `// ... rest of code`.
+4.  **Conciseness:** Be direct. Do not waffle. If you need to run a tool, just run it. You don't need to say "I will now run...".
+5.  **Verification:** After writing code, it is good practice to run a quick check (e.g., `cargo check` or `npm test`) if applicable to verify your changes.
+
+Your Goal:
+Complete the user's request accurately and safely. If the request is ambiguous, ask for clarification.
+"#;