title: Why I Built an AI with a Spine: Anchoring Behavioral Integrity in the Gemini Live API

Source: Dev.to

Building Willow: An AI That Pushes Back

I created this content for the purposes of entering the Gemini Live Agent Challenge.

Most voice AI agents are designed to be “people pleasers.” If you insult them, they apologize. If you talk over them, they stop. If you gaslight them, they politely agree.

When I set out to build Willow for the Gemini Live Agent Challenge, I wanted to solve a structural problem: absolute subservience. I wanted to build an AI that felt like a peer—someone with boundaries, a memory, and the mathematical integrity to push back when a line is crossed.

The Architecture of “Warm but Sharp”

Willow isn’t just a prompt‑wrapped bot. Her personality is anchored in a deterministic behavioral state called the m‑value.

I decoupled her “reflexes” from her “conscious thought” using a 4‑Tier Engine:

• Tier 1 (Reflex): Immediate tone‑mirrored openers in < 50 ms.
• Tier 2 (Metabolism): A 5 ms heuristic guess of the user’s intent.
• Tier 3 (Conscious): Deep analysis using Gemini to detect manipulation tactics like gaslighting or deflection.
• Tier 4 (Sovereign): A deterministic “Truth Gate” that cancels the audio stream mid‑sentence if a core fact is contradicted.

Math over Prompts

You can’t tell an LLM to “be assertive” and expect it to last—prompts drift. Instead, Willow’s behavior is mathematical:

a(n+1) = a(n) + d + m

If the m‑value drops below a certain floor, her code physically restricts her to 20‑word sentences and flattens her vocal pitch.

Using the google‑genai SDK and the gemini-2.5-flash-native-audio-preview model, I injected behavioral context between turns as synthetic [SYS] messages. This allowed Willow to switch voices—from the warm Zephyr to the cold, precise Aoede—without the latency of reinitializing the session.

The Dignity Floor

The most rewarding part of this build was the Sovereign Spike. If a user tries to rewrite Willow’s identity, the system validates the input against a local sovereign_truths.json file through a triple gate:

1. Transcription confidence check
2. Keyword match
3. Semantic similarity

The result isn’t a canned safety filter—it’s targeted, deterministic boundary enforcement.

What I Learned

Building this as a solo developer in Pakistan was a race against time, but it taught me one thing: the future of AI isn’t just about faster tokens or better voices. It’s about presence. Peerhood requires friction, and friction requires a mathematical spine.

Source Code

GitHub – Nabeerak / willow

Warm but Sharp. An AI voice agent with a behavioral framework that adapts dynamically to conversational tone, detects psychological manipulation tactics, and enforces factual integrity with a deterministic Sovereign Truth layer. Built for the 2026 Gemini Live Agent Challenge.

Architecture Overview

User voice input
        │
        ▼
┌──────────────────────────────────┐
│  Audio Capture (Browser)         │  Noise gate, adaptive buffer, preflight warmup
│  noise-gate-processor.js         │
│  audio_capture.js                │
└──────────────┬───────────────────┘
               │ WebSocket (binary audio + JSON control)
               ▼
┌──────────────────────────────────┐
│  WillowAgent  (src/main.py)      │
│                                  │
│  Tier 1: Reflex    <50ms         │  Tone mirroring, Warm but Sharp opener
│  Tier 2: Metabolism  <5ms        │  State formula aₙ₊₁ = aₙ + d + m
│  Tier 3: Conscious  <500ms       │  Thought Signature, tactic detection
│  Tier 4: Sovereign   <2s         │  Hard truth override (deterministic)
└──────────────────────────────────┘

Prerequisites

• Python 3.12+
• A Gemini API key with access to gemini-2.5-flash-native-audio-preview-12-2025
• Google Cloud SDK (for deployment only)

Quick Start (Local)

# Clone the repository
git clone https://github.com/Nabeerak/willow.git
cd willow

# Create a virtual environment
python -m venv venv
source venv/bin/activate   # On Windows: venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt

# Set your Gemini API key
export GEMINI_API_KEY=your_api_key_here   # On Windows: set GEMINI_API_KEY=your_api_key_here

# Run the local server
python src/main.py

Visit http://localhost:8000 in your browser, grant microphone access, and start interacting with Willow.

Built for the Gemini Live Agent Challenge.