Spec-Driven Dev & Context Engineering
Cross-vendor context architecture (AGENTS.md, CLAUDE.md, Cursor rules), progressive disclosure, and Spec-to-Plan-to-Tasks agent workflows.
Practical 12-page visual handbooks for context engineering, multi-agent orchestration, Orca workspaces & parallel Git worktrees, production MCP servers, Chrome DevTools & Playwright browser agents, document & web scraping pipelines (Docling, Crawl4AI & Firecrawl), OpenTelemetry & prompt caching, structured outputs & state machines, voice-first coding, vector RAG, security, evals, System One decisions, and local on-device AI.
Cross-vendor context architecture (AGENTS.md, CLAUDE.md, Cursor rules), progressive disclosure, and Spec-to-Plan-to-Tasks agent workflows.
Designing specialist subagents, context forks, least-privilege tool scoping, lifecycle hooks, and multi-agent coordinator-worker swarms.
Running parallel coding agents without file collisions—covering Git worktree fleets, isolated ports/databases, safety hooks, and teardown.
Building persistent semantic memory for AI agents with structure-aware chunking, Chroma, pgvector, Qdrant, local Ollama, and hybrid retrieval.
Turning LLM vibe-checks into deterministic CI deploy gates with golden datasets, code scorers, calibrated LLM-as-judge, and Promptfoo.
Defending tool-calling and browsing AI agents against indirect prompt injection, poisoned MCP servers, secret exfiltration, and unsafe output sinks.
Running private, zero-per-token LLMs and embeddings on your own hardware—mastering GGUF quantization, Apple Silicon memory math, Ollama, and llama.cpp.
Replacing fragile LLM JSON parsing with fast, calibrated System One decisions—mastering Choice, Score, and Noul primitives, parallel fan-out, and confidence-gated routing.
Architect, test, and ship high-reliability Model Context Protocol servers in TypeScript (SDK v2) and Python (FastMCP)—mastering stateless Streamable HTTP factories, Zod v4 & outputSchema, OAuth 2.1, MCP Inspector, and 10-question evals.
Pair live Chrome DevTools MCP diagnostics (accessibility uid snapshots, LCP subpart traces, HttpOnly cookie forensics, and heap leak diffs) with deterministic Playwright E2E regression gates.
Architecting ephemeral microVMs, Firecracker, E2B, Docker, and gVisor environments for safe autonomous code execution, snapshotting, and network egress control.
Orchestrate parallel AI coding agents across isolated Git worktrees, coordinator-worker task DAGs, inline diff annotations, embedded browser captures, and remote SSH or mobile runtimes.
Instrument multi-agent workflows with OpenTelemetry GenAI trace trees, maximize static-first KV cache hit rates, compact historical tool outputs, and route models for predictable token FinOps.
Eliminate fragile regex loops with CFG/FSM constrained decoding, Pydantic v2 and Zod v4 contracts, streaming partial objects, explicit transition tables, idempotency, and HITL approval gates.
Turn spoken architectural intent into code and notes with mlx-whisper and Superwhisper, codebase symbol glossaries, voice PR diff triage, and automated Obsidian _inbox/ capture pipelines.
Transform messy PDFs, Office suites, and JS-heavy websites into clean, chunked, citation-ready Markdown using Docling, Granite-Docling VLM, Crawl4AI fit_markdown, Firecrawl v2, and SHA-256 deduplication.