Build a sub-1s AI voice agent portfolio project to win clients via cold email
ashishllm · x · 2026-10-07
A step-by-step playbook for landing AI work through a portfolio project plus cold email, using a LiveKit-based inbound voice agent for clinics as the example:
- Pick a niche and build one portfolio project: combine open-source STT/TTS/LLM models, streaming tokens, quantization, paged attention and flash attention to push latency under 1 second, with LiveKit as orchestrator.
- Deploy and load test: ship to AWS, test 1,000 concurrent users, monitor logs and debug failures to learn production lessons.
- Benchmark against vendors: compare cost and latency tradeoffs with third-party APIs like ElevenLabs.
- Cold email + inbound: the project doubles as outreach ammo and inbound-lead magnet; author claims it works 8 out of 10 times but is time-consuming.
More from coding & agent
- 10 RAG Projects That Take You From Basic Retrieval to Production-Grade AI Systems — _jaydeepkarale · 2026-10-07
- Instinct raises $1B for texting personal agent and open-sources it as open-instinct — sujingshen · 2026-10-07
- Observability logs catch Gemini refusing to finish its agent work — tekbog · 2026-10-07
- How tiny 4-5 person associations actually put custom GPTs and AI agents to work — Sorry_Sweet2696 · 2026-10-07
- Open-source liminal_groupchat puts multiple LLMs in one group chat with you — liminal_bardo · 2026-10-07
- DIY "slop cannon" agent pipeline generates content for $0.38 per piece — tobowers · 2026-10-07