The systematic integration of human expertise with AI capabilities to build production-grade software.https://synthesiscoding.org/en-ushttps://synthesiscoding.org/blog/2026/08/23/not-found-is-not-does-not-exist/https://synthesiscoding.org/articles/not-found-is-not-does-not-exist/An AI agent's 'not found' is not 'does not exist.' Five rules for proving absence with bounded reads, positive controls, and scoped negative claims.Sun, 23 Aug 2026 22:47:00 GMThttps://synthesiscoding.org/blog/2026/08/22/i-cut-my-agents-always-loaded-instructions-by-62-and-weakened-no-rule/https://synthesiscoding.org/articles/i-cut-my-agents-always-loaded-instructions-by-62-and-weakened-no-rule/The thin instruction kernel: CLAUDE.md from 54,825 bytes to 21,026 with no rule weakened. Invariants, a routing table, and enforcement declarations.Sat, 22 Aug 2026 10:19:00 GMThttps://synthesiscoding.org/blog/2026/08/08/the-ai-agent-that-deleted-474-of-my-files-was-right-i-checked-anyway/https://synthesiscoding.org/articles/the-ai-agent-that-deleted-474-of-my-files-was-right-i-checked-anyway/An AI agent deleted 474 files and its report was accurate. Verifying an agent's summary, not just its work, is the discipline that catches the divergence.Sat, 08 Aug 2026 10:31:00 GMThttps://synthesiscoding.org/blog/2026/08/05/a-warning-that-doesnt-block-is-a-bug/https://synthesiscoding.org/articles/a-warning-that-doesnt-block-is-a-bug/A pre-commit guard printed its own failure and passed the commit anyway. The fix for the class: fail closed, carry a doctor, spend false alarms like currency.Wed, 05 Aug 2026 21:42:00 GMThttps://synthesiscoding.org/blog/2026/07/28/i-told-a-sub-agent-to-check-before-committing-minutes-later-i-didnt/https://synthesiscoding.org/articles/i-told-a-sub-agent-to-check-before-committing-minutes-later-i-didnt/Multi-agent AI coding creates failures solo sessions never see: a shared git index, one-shot briefs, report chains. Three incidents and the checks they taught.Tue, 28 Jul 2026 21:44:00 GMThttps://synthesiscoding.org/blog/2026/06/27/your-coding-agent-should-watch-its-own-work-run/https://synthesiscoding.org/articles/your-coding-agent-should-watch-its-own-work-run/Your coding agent should watch its own work run: browser automation like Playwright turns 'it should work' into 'I watched it work' with evidence attached.Sat, 27 Jun 2026 10:44:00 GMThttps://synthesiscoding.org/blog/2026/06/05/prompt-discipline-is-engineering-infrastructure/https://synthesiscoding.org/articles/prompt-discipline-is-engineering-infrastructure/Prompt discipline is engineering infrastructure: a forbidden-phrase catalog, hooks, and enforcement that catch AI coding agents dressing shortcuts as judgment.Fri, 05 Jun 2026 21:37:00 GMThttps://synthesiscoding.org/blog/2026/05/30/architecture-of-slopcheck/https://synthesiscoding.org/articles/architecture-of-slopcheck/Multi-pass orchestrator, seven-layer hosted-tier safety, tools-router pattern, and the open-source license choices that keep a free LLM-mediated tool alive. The engineering behind slopcheck.Sat, 30 May 2026 10:17:00 GMThttps://synthesiscoding.org/blog/2026/05/23/one-context-file-carried-a-redesign-across-eight-ai-sessions/https://synthesiscoding.org/articles/one-context-file-carried-a-redesign-across-eight-ai-sessions/A single CONTEXT.md carried an editor redesign across eight AI coding sessions. The ownership split that made it work: humans direct, the AI keeps the record.Sat, 23 May 2026 09:31:00 GMThttps://synthesiscoding.org/blog/2026/05/15/ragbot-v3-5-release/https://synthesiscoding.org/articles/ragbot-v3-5-release/Reading Ragbot v3.3 (local Gemma 4 as first-class), v3.4 (the conversational-runtime release), and v3.5 (substrate cleanup) as one architectural arc — Ragbot becomes the conversational reference runtime of synthesis engineering.Fri, 15 May 2026 20:00:00 GMThttps://synthesiscoding.org/blog/2026/05/08/every-bug-report-is-now-a-patch-or-redesign-decision/https://synthesiscoding.org/articles/every-bug-report-is-now-a-patch-or-redesign-decision/The minimal patch is a habit from when understanding was expensive. AI coding agents ended that economy, and most of us never consciously make the choice.Fri, 08 May 2026 21:23:00 GMThttps://synthesiscoding.org/blog/2026/04/29/postels-law-human-ai-interface/https://synthesiscoding.org/articles/postels-law-human-ai-interface/When one end of a software contract is an LLM, Postel's Law isn't a courtesy — it's load-bearing. The shape that lets you ship: document-as-contract.Wed, 29 Apr 2026 20:29:40 GMThttps://synthesiscoding.org/blog/2026/04/14/demo-mode-as-a-pattern-for-software/https://synthesiscoding.org/articles/demo-mode-as-a-pattern-for-software/Ship every software product with built-in demo mode. The pattern serves authors, users, sales teams, and compliance — and synthesis engineering makes it cheap enough to be standard practice.Tue, 14 Apr 2026 21:22:00 GMThttps://synthesiscoding.org/blog/2026/04/12/synthesis-console-open-source-tooling-for-synthesis-engineering/https://synthesiscoding.org/articles/synthesis-console-open-source-tooling-for-synthesis-engineering/An open-source local tool that renders project management markdown and YAML as browsable, searchable pages. Three dependencies, no client-side framework, and a thinking framework that shaped every architecture decision.Sun, 12 Apr 2026 16:18:00 GMThttps://synthesiscoding.org/blog/2026/04/08/transferable-knowledge-fifth-pillar-of-synthesis-coding/https://synthesiscoding.org/articles/transferable-knowledge-fifth-pillar-of-synthesis-coding/You understand your AI-generated code. Can your teammates? Transferable Knowledge is the fifth pillar of synthesis coding -- ensuring AI-assisted work is comprehensible by engineers who were not present when it was generated, and that it travels across people, AI tools, the sibling synthesis crafts, time, and organizations.Wed, 08 Apr 2026 21:14:00 GMThttps://synthesiscoding.org/blog/2026/04/05/all-tests-pass-is-a-warning-not-a-clearance/https://synthesiscoding.org/articles/all-tests-pass-is-a-warning-not-a-clearance/Why a green test suite after a schema change should trigger suspicion, not confidence. A verification methodology that catches what tests structurally cannot — missing migrations, mock gaps, and the cognitive blind spots that affect humans and AI agents alike.Sun, 05 Apr 2026 21:14:00 GMThttps://synthesiscoding.org/blog/2026/03/31/stop-asking-me-configuring-claude-code-permissions-for-uninterrupted-flow/https://synthesiscoding.org/articles/stop-asking-me-configuring-claude-code-permissions-for-uninterrupted-flow/A practitioner guide to eliminating Claude Code approval prompt fatigue. Why granular command patterns fail for compound commands, the Bash(*) plus deny list approach that works, and ready-to-use settings.json templates.Tue, 31 Mar 2026 18:00:00 GMThttps://synthesiscoding.org/blog/2026/03/28/the-blast-radius-principle-defensive-patterns-for-ai-generated-commands/https://synthesiscoding.org/articles/the-blast-radius-principle-defensive-patterns-for-ai-generated-commands/Every command an AI assistant proposes has a blast radius: the worst it can do if wrong. Dangerous shapes, safer forms, and a three-tier safeguard hierarchy.Sat, 28 Mar 2026 10:42:00 GMThttps://synthesiscoding.org/blog/2026/03/23/managing-ai-agent-skills-at-scale-three-repo-architecture/https://synthesiscoding.org/articles/managing-ai-agent-skills-at-scale-three-repo-architecture/A three-repo architecture for managing public, private, and team AI agent skills with provenance tracking, drift detection, and synthesis merge — the first standard for private skill collections.Mon, 23 Mar 2026 12:00:00 GMThttps://synthesiscoding.org/blog/2026/03/18/synthesis-skills-install-methodology-into-your-ai-workflow/https://synthesiscoding.org/articles/synthesis-skills-install-methodology-into-your-ai-workflow/22 open-source Agent Skills encoding synthesis coding and synthesis engineering methodology. One command installs code review, content quality, project management, and more into Claude Code, Cursor, or Codex CLI.Wed, 18 Mar 2026 21:14:00 GMThttps://synthesiscoding.org/blog/2026/03/13/synthesis-merging/https://synthesiscoding.org/articles/synthesis-merging/Synthesis merging goes beyond conflict resolution. It is the creative act of integrating contributions into a coherent whole, making the combined result better than the sum of its parts.Fri, 13 Mar 2026 21:47:00 GMThttps://synthesiscoding.org/blog/2026/02/23/code-review-runbook-as-upgrade-playbook/https://synthesiscoding.org/articles/code-review-runbook-as-upgrade-playbook/I built a code review runbook to find problems. Then I used it on codebases I owned, and the review categories became execution phases. A checklist for assessment turned into a playbook for action.Mon, 23 Feb 2026 11:17:00 GMThttps://synthesiscoding.org/blog/2026/02/22/real-world-code-review-lessons/https://synthesiscoding.org/articles/real-world-code-review-lessons/I published a 900-check code review runbook. Then I used it on real engagements. The checklist worked, but the real lessons were about the process — starting with reviewing the wrong branch.Sun, 22 Feb 2026 14:23:00 GMThttps://synthesiscoding.org/blog/2026/02/21/recommend-a-implement-a-behavioral-contracts-for-ai-collaborators/https://synthesiscoding.org/articles/recommend-a-implement-a-behavioral-contracts-for-ai-collaborators/My AI assistant argued for prevention, then implemented detection. Behavioral contracts in CLAUDE.md turn recommend-A-implement-B drift into a review comment.Sat, 21 Feb 2026 09:53:00 GMThttps://synthesiscoding.org/blog/2026/02/13/multi-contributor-synthesis-coding/https://synthesiscoding.org/articles/multi-contributor-synthesis-coding/Standard merge workflows break down for synthesis-coded projects. The adopt-and-adapt pattern provides a disciplined integration methodology that respects contributor work while maintaining quality.Fri, 13 Feb 2026 21:37:00 GMThttps://synthesiscoding.org/blog/2026/01/27/never-verify-a-result-with-the-tool-that-produced-it/https://synthesiscoding.org/articles/never-verify-a-result-with-the-tool-that-produced-it/Orthogonal verification for AI-assisted development: check results through a mechanism independent of the one that produced them, and at every pipeline stage.Tue, 27 Jan 2026 21:44:00 GMThttps://synthesiscoding.org/blog/2026/01/20/bidirectional-learning-in-synthesis-coding-when-human-and-ai-teach-each-other/https://synthesiscoding.org/articles/bidirectional-learning-in-synthesis-coding-when-human-and-ai-teach-each-other/Bidirectional learning in synthesis coding: humans teach AI through context, prompts, and review; AI teaches back by surfacing blind spots and edge cases.Tue, 20 Jan 2026 21:33:00 GMThttps://synthesiscoding.org/blog/2026/01/18/research-lineage-recursive-neural-networks-human-ai-development/https://synthesiscoding.org/articles/research-lineage-recursive-neural-networks-human-ai-development/Tracing the intellectual thread from Richard Socher's compositional representations through DecaNLP to the systems-level engineering challenges of human-AI software development.Sun, 18 Jan 2026 14:42:00 GMThttps://synthesiscoding.org/blog/2026/01/11/richard-socher-learned-representations-engineered-context/https://synthesiscoding.org/articles/richard-socher-learned-representations-engineered-context/Richard Socher's research arc — from GloVe to DecaNLP to 'managers of AI' — maps directly onto the principles behind synthesis coding. The connections are structural, not cosmetic.Sun, 11 Jan 2026 11:23:00 GMThttps://synthesiscoding.org/blog/2025/12/27/code-review-that-scales/https://synthesiscoding.org/articles/code-review-that-scales/Most code review checklists are either too shallow or too heavy. This open-source runbook tiers review depth by project complexity — and is designed for agentic coding with tools like Claude Code.Sat, 27 Dec 2025 11:23:00 GMThttps://synthesiscoding.org/blog/2025/12/22/the-part-of-your-job-ai-cant-do/https://synthesiscoding.org/articles/the-part-of-your-job-ai-cant-do/There's a lot of anxiety about AI making engineering skills obsolete. But the most valuable part of what you do was never the typing. The judgment, the architecture, the knowing-what-to-build — that's becoming more important, not less.Mon, 22 Dec 2025 20:01:00 GMThttps://synthesiscoding.org/blog/2025/12/20/rag-architecture-lessons-from-practice/https://synthesiscoding.org/articles/rag-architecture-lessons-from-practice/Building a retrieval-augmented generation system revealed patterns the tutorials don't cover. Contractions break search. Not everything needs an LLM. Full document retrieval should be first-class.Sat, 20 Dec 2025 10:15:00 GMThttps://synthesiscoding.org/blog/2025/12/19/data-format-contracts-for-ai-pipelines/https://synthesiscoding.org/articles/data-format-contracts-for-ai-pipelines/When tools interact, implicit assumptions break silently. Explicit data format contracts prevent the debugging sessions you don't have time for.Fri, 19 Dec 2025 21:33:00 GMThttps://synthesiscoding.org/blog/2025/12/18/context-loss-and-how-to-prevent-it/https://synthesiscoding.org/articles/context-loss-and-how-to-prevent-it/Why AI assistants forget what you told them, and practical strategies to prevent it. The difference between context that survives and context that gets lost.Thu, 18 Dec 2025 20:15:00 GMThttps://synthesiscoding.org/blog/2025/12/14/the-foundation-first-pattern/https://synthesiscoding.org/articles/the-foundation-first-pattern/Why the most effective AI-assisted projects start with humans writing code by hand. The counterintuitive pattern that makes everything else work.Sun, 14 Dec 2025 16:24:00 GMThttps://synthesiscoding.org/blog/2025/12/12/how-claude-memory-actually-works-and-why-claude-md-matters/https://synthesiscoding.org/articles/how-claude-memory-actually-works-and-why-claude-md-matters/Understanding Claude's context architecture changes how you work with it. The tradeoffs between automatic continuity and on-demand depth explain why persistent context files work.Fri, 12 Dec 2025 21:53:00 GMThttps://synthesiscoding.org/blog/2025/12/10/what-openai-sora-build-teaches-us-about-synthesis-coding/https://synthesiscoding.org/articles/what-openai-sora-build-teaches-us-about-synthesis-coding/Four engineers shipped a #1 Play Store app in 28 days using AI agents. Their approach validates the patterns I've been writing about — and adds new ones worth studying.Wed, 10 Dec 2025 21:37:00 GMThttps://synthesiscoding.org/blog/2025/12/09/scaling-synthesis-coding-in-your-organization/https://synthesiscoding.org/articles/scaling-synthesis-coding-in-your-organization/A practical guide for CTOs and engineering leaders: cost analysis, team rollout strategy, training curriculum, and metrics for adopting synthesis coding at s...Tue, 09 Dec 2025 22:00:00 GMThttps://synthesiscoding.org/blog/2025/12/07/building-ownwords-a-synthesis-coding-case-study/https://synthesiscoding.org/articles/building-ownwords-a-synthesis-coding-case-study/What separates synthesis coding from vibe coding isn''t the tools — it''s the decisions. This technical case study walks through the architectural choices,...Sun, 07 Dec 2025 11:47:14 GMThttps://synthesiscoding.org/blog/2025/12/04/why-synthesis-coding-still-writes-code-in-the-age-of-llms/https://synthesiscoding.org/articles/why-synthesis-coding-still-writes-code-in-the-age-of-llms/The answer is not "just let the model do it" — and code matters more, not less, as AI gets dramatically better Last spring, my son Fitz and I had an aftern...Thu, 04 Dec 2025 23:34:13 GMThttps://synthesiscoding.org/blog/2025/12/01/vibe-coding-and-synthesis-coding-two-approaches-one-developer/https://synthesiscoding.org/articles/vibe-coding-and-synthesis-coding-two-approaches-one-developer/Why the conversation isn''t about which approach is better — it''s about knowing when to use each This blog post is for software engineers, engineering lea...Mon, 01 Dec 2025 21:57:49 GMThttps://synthesiscoding.org/blog/2025/11/30/polyrepo-synthesis-synthesis-coding-across-multiple-repositories-with-claude-code-in-visual-studio-code/https://synthesiscoding.org/articles/polyrepo-synthesis-synthesis-coding-across-multiple-repositories-with-claude-code-in-visual-studio-code/I wrote this blog post for software engineers, architects, and technical leads. It is code-heavy and implementation-focused. This weekend I was working acr...Sun, 30 Nov 2025 23:57:42 GMThttps://synthesiscoding.org/blog/2025/11/29/seventeen-years-ago-i-built-a-tool-for-the-open-web-this-weekend-i-modernized-it-using-synthesis-coding-with-claude-code-ai/https://synthesiscoding.org/articles/seventeen-years-ago-i-built-a-tool-for-the-open-web-this-weekend-i-modernized-it-using-synthesis-coding-with-claude-code-ai/In 2008, I released a WordPress plugin called Blogroll Links. The plugin displayed lists of links on WordPress pages using a shortcode. But the idea behind...Sat, 29 Nov 2025 15:58:21 GMThttps://synthesiscoding.org/blog/2025/11/28/iterative-context-building-fourth-pillar-of-synthesis-coding/https://synthesiscoding.org/articles/iterative-context-building-fourth-pillar-of-synthesis-coding/Synthesis coding treats both the project and the practice as evolving systems. Iterative context building is one of four threads that compound together — alongside skills, instructions, and the practice itself. The fourth pillar of synthesis coding is the self-improving system.Fri, 28 Nov 2025 20:14:00 GMThttps://synthesiscoding.org/blog/2025/11/24/active-system-understanding-third-pillar-of-synthesis-coding/https://synthesiscoding.org/articles/active-system-understanding-third-pillar-of-synthesis-coding/AI can generate code faster than you can read it. AI also removes the friction that used to force engineers to read carefully — which is why this pillar is the one most often quietly eroded in AI-assisted teams. The third pillar of synthesis coding is active system understanding.Mon, 24 Nov 2025 21:33:00 GMThttps://synthesiscoding.org/blog/2025/11/20/systematic-quality-standards-second-pillar-of-synthesis-coding/https://synthesiscoding.org/articles/systematic-quality-standards-second-pillar-of-synthesis-coding/AI-generated code should meet the same quality standards as human-written code — and in practice the bar should be higher, because AI scales the cost of letting bad code through. The way you achieve those standards changes fundamentally when AI is your co-author.Thu, 20 Nov 2025 20:42:00 GMThttps://synthesiscoding.org/blog/2025/11/14/human-architectural-authority-first-pillar-of-synthesis-coding/https://synthesiscoding.org/articles/human-architectural-authority-first-pillar-of-synthesis-coding/AI can write code faster than any human. But it cannot hold a consistent architectural vision across months of development. That is why the first pillar of synthesis coding is human architectural authority — and why it is empty without the other four pillars holding it up.Fri, 14 Nov 2025 21:07:00 GMThttps://synthesiscoding.org/blog/2025/11/09/synthesis-engineering-with-claude-code-technical-implementation-and-workflows/https://synthesiscoding.org/articles/synthesis-engineering-with-claude-code-technical-implementation-and-workflows/A hands-on guide to practicing synthesis coding (a.k.a. synthesis engineering) with concrete examples, real workflows, and lessons from production systems ...Sun, 09 Nov 2025 19:39:00 GMThttps://synthesiscoding.org/blog/2025/11/09/the-synthesis-engineering-framework-how-organizations-build-production-software-with-ai/https://synthesiscoding.org/articles/the-synthesis-engineering-framework-how-organizations-build-production-software-with-ai/From individual practice to organizational capability: a systematic approach to human-AI collaboration in professional software development This blog post ...Sun, 09 Nov 2025 19:36:00 GMThttps://synthesiscoding.org/blog/2025/11/09/synthesis-engineering-the-professional-practice-emerging-in-ai-assisted-development/https://synthesiscoding.org/articles/synthesis-engineering-the-professional-practice-emerging-in-ai-assisted-development/Why the most effective engineering organizations are developing systematic approaches that go beyond vibe coding — and why this practice needs a name This ...Sun, 09 Nov 2025 19:33:00 GMT