What is Synthesis Engineering?
Synthesis engineering is the professional discipline of systematic human-AI collaboration for complex work. It's not automation (AI replacing humans) or augmentation (AI enhancing humans) — it's genuine synthesis where both parties contribute irreplaceable value to produce results neither could achieve alone.
The fundamental insight: design systems for AI capabilities, not human limitations. Traditional workflows optimize for human cognition — folder hierarchies, periodic reviews, status meetings. AI has different strengths: instant full-text search, perfect recall within sessions, tireless consistency, ability to synthesize across documents.
Synthesis engineering asks: what if we redesigned our workflows to use AI's strengths while preserving human judgment, expertise, and control?
The Crafts
Synthesis engineering encompasses specific crafts — domains where the discipline's principles are applied to particular types of work:
Synthesis Coding
Build production code with AI—without losing control. Human-AI collaboration for writing production-grade software. The human provides architectural authority, judgment, and quality standards. The AI provides execution speed, pattern recognition, and consistency.
Learn more at synthesiscoding.org →Synthesis Project Management
Project management redesigned for AI capabilities. Durable project memory lives in CONTEXT.md, REFERENCE.md, and session archives so work can move across Claude Code, Codex, other capable agents, and any workstation synced through a private git repo — and a claim-based coordination board now lets several agents work the same project at the same time without overwriting each other.
Synthesis Writing
The craft of thoughtful human authorship in the age of AI. The writer writes. The AI assists with scaffolding — spelling, grammar, structural feedback, fact-checking, reformatting. Substance, voice, and judgment stay human. Positioned as a disciplined antidote to AI slop, not a product.
Learn more at synthesiswriting.org →As AI capabilities evolve, new crafts will emerge. The pattern applies anywhere humans and AI collaborate on complex work — research, design, analysis, and more.
How It's Different
Synthesis engineering is distinct from both "vibe coding" and "agentic coding":
| Approach | Human Role | AI Role | Best For |
|---|---|---|---|
| Vibe Coding | Minimal oversight | Generates everything | Experiments, learning, throwaway code |
| Agentic Coding | Sets goal, steps away | Operates autonomously | Well-defined, bounded tasks |
| Synthesis Engineering | Directs, reviews, approves | Executes under supervision | Production systems, complex work |
Key Distinctions
vs. Vibe Coding: Vibe coding is "just let AI write it"—great for rapid experiments and personal tools, but production systems need architectural coherence, security, team comprehension, and long-term maintainability. Synthesis engineering maintains these standards.
vs. Agentic Coding: Agentic approaches emphasize AI autonomy—set a goal and let AI figure it out. Synthesis engineering keeps humans in the loop because complex work requires judgment calls AI can't make: architectural trade-offs, security decisions, business context, and accountability.
The same developer might use all three approaches in a single day. The skill is recognizing which approach fits each task.
Get Started
Synthesis engineering methodology is now available as installable Agent Skills — portable instruction packages that work with Claude Code, Codex, Cursor, GitHub Copilot, and other AI agents. Install proven practices for code review, project management, content quality, and multi-contributor integration.
Install as a native plugin in Claude Code or OpenAI Codex — one shared catalog, both runtimes:
# Claude Code
claude plugin marketplace add synthesisengineering/synthesis-skills
claude plugin install synthesis-skills@synthesis-engineering
# OpenAI Codex
codex plugin marketplace add synthesisengineering/synthesis-skills
codex plugin add synthesis-skills@synthesis-engineeringOr install direct copies for Cursor, GitHub Copilot, and 40+ other agents: npx skills add synthesisengineering/synthesis-skills --global --all --copy. Licensed under CC0 (public domain). Browse the catalog on GitHub →
One shipped artifact of the ecosystem: slopcheck, a free hosted slop-detection tool built on the upgraded synthesis-content-quality v4.0 and synthesis-fact-checking v2.0 skills. Zero data collection, no signup. See the methodology piece for the catalog structure behind it.
Articles
Browse All →- The Decision Packet: batching AI agents' questions without rubber-stamping them
A synthesis engineering pattern for staying in command of AI agents at speed: collect every decision they owe you into o
- The migration that was finished until a stranger looked
A synthesis engineering story about Blind-Spot Rotation: how an AI reviewer with fresh context can find gaps the origina
- Choosing Local AI Models by Measuring the Machine
Profile a computer, choose local open-weight models that fit, install them safely, and map exact artifacts to each machi
- Why Synthesis Engineering Exists: Building Across AI Agent Runtimes, Not Around Them
Why synthesis engineering exists: model, runtime, and state portability across Claude Code, OpenAI Codex, Cursor, Hermes
- My AI executive assistant writes in its own voice. My AI chief of staff writes in mine.
Ragbot and Ragenie, EA AI and chief-of-staff AI: why my executive assistant agent writes in its own voice while my chief
- My design record ruled out agent-to-agent messaging. Six days later I shipped it.
I documented why session-to-session agent messaging would fail, then built it six days later. Why a design record is not
- What agent memory research taught me about twenty years of notes
Tiered memory for a personal knowledge base: what MemGPT, Zep, and Mem0 teach about structuring two decades of notes so
- AI tools should copy GitHub's identity model, not your employer's
Enterprise workspaces hand you an account and take it back on departure. GitHub does the opposite. Multi-user AI tooling