# Google AI Ultra Integration Plan

> Master tracking document for integrating all Google AI Ultra products into
> Project Timmy (Sovereign AI Agent) and The Nexus (3D World).

**Epic**: #739  
**Milestone**: M5: Google AI Ultra Integration  
**Label**: `google-ai-ultra`

---

## Product Inventory

| # | Product | Capability | API | Priority | Status |
|---|---------|-----------|-----|----------|--------|
| 1 | Gemini 3.1 Pro | Primary reasoning engine | ✅ | P0 | 🔲 Not started |
| 2 | Deep Research | Autonomous research reports | ✅ | P1 | 🔲 Not started |
| 3 | Veo 3.1 | Text/image → video | ✅ | P2 | 🔲 Not started |
| 4 | Nano Banana Pro | Image generation | ✅ | P1 | 🔲 Not started |
| 5 | Lyria 3 | Music/audio generation | ✅ | P2 | 🔲 Not started |
| 6 | NotebookLM | Doc synthesis + Audio Overviews | ❌ | P1 | 🔲 Not started |
| 7 | AI Studio | API portal + Vibe Code | N/A | P0 | 🔲 Not started |
| 8 | Project Genie | Interactive 3D world gen | ❌ | P1 | 🔲 Not started |
| 9 | Live API | Real-time voice streaming | ✅ | P2 | 🔲 Not started |
| 10 | Computer Use | Browser automation | ✅ | P2 | 🔲 Not started |

---

## Phase 1: Identity & Branding (Week 1)

| Issue | Title | Status |
|-------|-------|--------|
| #740 | Generate Timmy avatar set with Nano Banana Pro | 🔲 |
| #741 | Upload SOUL.md to NotebookLM → Audio Overview | 🔲 |
| #742 | Generate Timmy audio signature with Lyria 3 | 🔲 |
| #680 | Project Genie + Nano Banana concept pack | 🔲 |

## Phase 2: Research & Planning (Week 1-2)

| Issue | Title | Status |
|-------|-------|--------|
| #743 | Deep Research: Three.js multiplayer 3D world architecture | 🔲 |
| #744 | Deep Research: Sovereign AI agent frameworks | 🔲 |
| #745 | Deep Research: WebGL/WebGPU rendering comparison | 🔲 |
| #746 | NotebookLM synthesis: cross-reference all research | 🔲 |

## Phase 3: Prototype & Build (Week 2-4)

| Issue | Title | Status |
|-------|-------|--------|
| #747 | Provision Gemini API key + Hermes config | 🔲 |
| #748 | Integrate Gemini 3.1 Pro as reasoning backbone | 🔲 |
| #749 | AI Studio Vibe Code UI prototypes | 🔲 |
| #750 | Project Genie explorable world prototypes | 🔲 |
| #681 | Veo/Flow flythrough prototypes | 🔲 |

## Phase 4: Media & Content (Ongoing)

| Issue | Title | Status |
|-------|-------|--------|
| #682 | Lyria soundtrack palette for Nexus zones | 🔲 |
| #751 | Lyria RealTime dynamic reactive music | 🔲 |
| #752 | NotebookLM Audio Overviews for all docs | 🔲 |
| #753 | Nano Banana concept art batch pipeline | 🔲 |

## Phase 5: Advanced Integration (Month 2+)

| Issue | Title | Status |
|-------|-------|--------|
| #754 | Gemini Live API for voice conversations | 🔲 |
| #755 | Computer Use API for browser automation | 🔲 |
| #756 | Gemini RAG via File Search for Timmy memory | 🔲 |
| #757 | Gemini Native Audio + TTS for Timmy's voice | 🔲 |
| #758 | Programmatic image generation pipeline | 🔲 |
| #759 | Programmatic video generation pipeline | 🔲 |
| #760 | Deep Research Agent API integration | 🔲 |
| #761 | OpenAI-compatible endpoint config | 🔲 |
| #762 | Context caching + batch API for cost optimization | 🔲 |

---

## API Quick Reference

```python
# pip install google-genai
from google import genai
client = genai.Client()  # reads GOOGLE_API_KEY env var

# Text generation (Gemini 3.1 Pro)
response = client.models.generate_content(
    model="gemini-3.1-pro-preview",
    contents="..."
)
```

| API | Documentation |
|-----|--------------|
| Image Gen (Nano Banana) | ai.google.dev/gemini-api/docs/image-generation |
| Video Gen (Veo) | ai.google.dev/gemini-api/docs/video |
| Music Gen (Lyria) | ai.google.dev/gemini-api/docs/music-generation |
| TTS | ai.google.dev/gemini-api/docs/speech-generation |
| Deep Research | ai.google.dev/gemini-api/docs/deep-research |

## Key URLs

| Tool | URL |
|------|-----|
| Gemini App | gemini.google.com |
| AI Studio | aistudio.google.com |
| NotebookLM | notebooklm.google.com |
| Project Genie | labs.google/projectgenie |
| Flow (video) | labs.google/flow |
| Stitch (UI) | labs.google/stitch |

## Hidden Features to Exploit

1. **AI Studio Free Tier** — generous API access even without subscription
2. **OpenAI-Compatible API** — drop-in replacement for existing OpenAI tooling
3. **Context Caching** — cache SOUL.md to cut cost/latency on repeated calls
4. **Batch API** — bulk operations at discounted rates
5. **File Search Tool** — RAG without custom vector store
6. **Computer Use API** — programmatic browser control for agent automation
7. **Interactions API** — managed multi-turn conversational state

---

*Generated: 2026-03-29. Epic #739, Milestone M5.*