Plasma

IronMind is an AI mental performance coach built exclusively for wrestlers, a persistent voice agent that delivers pre-match preparation, post-loss resets, and daily mindset challenges tailored to each athlete's specific history, psychology, and goals. IronMind uses ElevenLabs Conversational AI with a custom LLM endpoint. Instead of routing to a generic model, every conversation turn POSTs to a Cloudflare Worker that reads the athlete's full Durable Object before calling Claude. ElevenLabs Voice Clone API clones the athlete's voice from a 30-second sample during onboarding, so the coach speaks back in their own voice. Cloudflare Durable Objects store a complete per-athlete profile including session history, mental triggers, identity anchors, quit patterns, upcoming opponent intel, and mindset training scores. R2 caches generated audio so repeat triggers have zero latency and zero cost. The agent has no modes. It infers context from the conversation itself and responds accordingly. Every session builds on the last and the coach never starts from zero. For weight cuts, it tracks historical quit points and gets in front of the mental spiral before it starts. The product was built by a D1 wrestler. Every feature exists because it was needed at 11pm on day four of a cut, with no one to call.

Submitted 2 Apr 2026

Sundown is a personalized AI voice companion for dementia patients that reduces confusion during sundowning and gives caregivers real-time backup during the hardest hours of the day. I built it with ElevenLabs Conversational AI, using signed runtime sessions, dynamic patient variables, stage-aware prompting, long-form pause handling, expressive voice controls, and post-call webhooks that automatically return transcripts and summaries for the caregiver dashboard. I paired that with Firecrawl to map trusted dementia-care sources, extract them into structured protocol cards with schema-based parsing and confidence thresholds, and search the live web for familiar context like church updates, hometown news, and favorite team recaps that make conversations feel grounding and real. The result is not just a chatbot, but a voice companion that knows the patient’s world, stays current without manual updates, and can turn lonely or high-stress moments into personalized care.