Flint — Interview Co-Pilot
Real-time AI co-pilot desktop app for live conversations and job interviews. Captures system audio, transcribes locally with Whisper and RNNoise, and fires parallel LLM guidance threads in a stealth overlay that is invisible to screen-share capture. RAG over session context via sqlite-vec keeps answers grounded in your own experience.
Technology Stack
Rust
Tokio
Tauri 2
React 18
TypeScript
Tailwind CSS
Whisper
RNNoise
VAD
RAG
sqlite-vec
fastembed
Groq
Ollama
Supabase
Key Results
Local Whisper — zero audio leaves the device
Transcription
Groq cloud with Ollama fallback; sub-second P95 response time
Inference
sqlite-vec + bge-small-en-v1.5 — fully on-device RAG
Context Store
Overlay excluded from screen-share capture via Tauri OS compositor hints
Stealth
3 LLM threads (directional, depth, clarifying) fired simultaneously per question
Parallel Threads
API keys stored in OS keychain only — never on disk or in env
Keychain
Challenges & Solutions
- Capturing system audio without touching the microphone to isolate interviewer speech
- Running Whisper transcription and RNNoise suppression in real time with sub-second latency
- Firing parallel directional, depth, and clarifying LLM threads per detected question without blocking the UI
- Building a stealth overlay with Tauri that stays on top, is transparent, and is excluded from screen-capture APIs
- Local RAG over session context using sqlite-vec and bge-small-en-v1.5 embeddings fully on device
- Graceful failover from Groq cloud inference to a local Ollama model when the network is unavailable
- Storing API keys only in the OS keychain — never in config files or environment variables
Project Stats
1
Team Member
2
Months