Work
AI products built end-to-end: from voice agents to research engines. Case studies cover the problem, the architecture, and the decisions that mattered.
DentinFlow
In buildAn AI voice agent, "Mila," that answers the phone for dental practices day and night, books appointments through normal conversation, and keeps after-hours calls from rolling to voicemail.
AI stack: Practice-scoped JSON embeddings use in-process cosine ranking with keyword fallback. Vapi conversations reach bounded scheduling tools; identity checks, signed slots and idempotent writes protect the appointment ledger.
Isaac
LiveAn AI coaching app with a soul: eight personality archetypes, a five-layer memory updated through background reflection, and proactive daily check-ins. Built in React Native, shipped to TestFlight.
AI stack: Claude receives structured profiles, goals, memory layers and recent conversations from Supabase. Background reflection and weekly synthesis update stored context; there is no vector retrieval or model training in this path.
PRAXIS
LiveA gamified, industry-generic way to actually practice product management. A six-level path from your first PM job to VP where you build mastery by doing the reps: drills, written artifacts, stakeholder roleplay, and a simulation that teaches itself. Runs in the browser, no signup.
AI stack: Deterministic simulations sit alongside bounded Claude rubric grading and roleplay. Prompt-driven JSON is normalized into feedback; thirty synthetic calibration samples rehearse a human-panel study, with conditional database-backed budgets.
Filings Analyst
LiveA research workspace over SEC filings that separates structured financial facts from narrative retrieval, checks generated claims against their sources, and makes missing evidence visible.
AI stack: text-embedding-3-small (1,536 dimensions), section-aware parent/child chunks, pgvector + PostgreSQL full-text search and rank fusion. LangGraph verifies financial claims against XBRL facts and source inputs.
Canadian Policy Navigator
LiveA policy workbench that keeps employee submissions outside the answer library until independent review, with exact document versions and source-backed retrieval.
AI stack: text-embedding-3-small + Chroma, BM25Plus and rank fusion retrieve eligible policy editions. Optional Cohere reranking; private employee uploads stay outside external embedding and generation calls.
Evidence Desk
LiveA research workspace with inspectable source support, bounded manual and LangGraph agent execution, and reviewed explanations and diagrams.
AI stack: OpenAI web search and safe page reading feed local term-overlap passages, with no vector index. Manual/LangGraph stages checkpoint research and separately audit claims, lessons and diagrams.
Realty Support
LiveA fictional brokerage support workspace with client/staff views, private notes, property exploration and human-approved appointment changes.
AI stack: Guided rules use selected-client records; optional gpt-4.1-mini has no write tools. Staff approval, original-time checks and collision checks own appointment changes. No embeddings or vector retrieval.
Model Observatory
LiveA lab for comparing three model providers, inspecting token usage, and separating prepared examples from measured evidence.
AI stack: Native OpenAI, Google and Anthropic adapters, validated structured answers and a bounded calculator loop. Provider token accounting and human task scores stay inspectable; no embeddings or RAG.