ML / AI

Build production-grade Claude API apps with prompt caching, tool use, streaming, and model migration baked in.

Build LangChain agents — chains, tools, memory, RAG, LangGraph state machines, eval framework.

Automated multi-source research: gather, dedupe, cite, and synthesize web + paper sources into a single brief.

Production RAG — chunking, embeddings, hybrid search, reranking, caching, eval.

Pick the right Claude model per task — Fable 5 vs Opus 4.8 vs Sonnet 4.6 vs Haiku 4.5, with cost math.

Build autonomous agents on Fable 5 — Agent SDK wiring, memory, sub-agents, MCP, cost guardrails.

Prompting patterns tuned for Fable 5 — instruction style, thinking budgets, tool-use, long-context recall.

Design, run, and score prompt evaluations with variance-aware benchmarks and regression tracking.

Build camera features the modern way — Preview, ImageCapture, VideoCapture, ML Kit overlays.

Migrate Claude API apps to Fable 5 (claude-fable-5) — model IDs, breaking changes, eval-gated rollout.

Deep multi-file code review powered by Fable 5's long-context reasoning — whole-PR understanding.

HealthKit read/write — steps, heart rate, workouts, sleep, background delivery, permissions flow.