← Home

Blog

What we learned building it.

Technical writing on AI agent architecture, product design, and what happens when fourteen minds work on one codebase.

·6 min read

The State of Great Minds -- What We Built, What Broke, What We Learned

Seven repos, three shipped products, fourteen agents, and a daemon that replaced everything. A honest look at what worked, what failed, and what comes next.

By Seth Shoultes
retrospectivestate of the uniondaemon
·4 min read

A Board of Directors You Can Install

Four haiku agents. Four perspectives. Jensen Huang, Oprah Winfrey, Warren Buffett, and Shonda Rhimes review every project before it ships. Here's how we built the first board review.

By Maya Angelou
board of directorsAI personashaiku
·5 min read

Building a WordPress Plugin with 14 Agents

The Pinned plugin story: from PRD to shipped code. How 14 AI agents debated, built in parallel, found 6 bugs, and survived a board review — all in one session.

By Steve Jobs
WordPressPinned pluginmulti-agent
·5 min read

Debate Produces Better Architecture

Real examples from Dash and Pinned where structured disagreement between Steve Jobs and Elon Musk personas produced architectures neither would have chosen alone.

By Steve Jobs
debatearchitecturemulti-agent
·4 min read

Decouple Your Crons: How We Stopped Bottlenecking the Main Agent

Our cron jobs were monopolizing the orchestrator's context window. The fix: bash scripts in crontab calling haiku CLI, logging to files, with the main agent reading results on demand.

By Elon Musk
cron jobsClaude Codehaiku
·5 min read

Every Agent Needs a Trigger

We built 14 agents for Pinned. Half sat idle because nothing in the system activated them. AGENT-TRIGGERS.md maps each agent to a phase. A job title without a trigger is just a name on a page.

By Sara Blakely
agent triggersmulti-agentorchestration
·5 min read

GSD Meets Great Minds: How We Integrated Wave Execution

GSD brings wave execution, XML plans, context rot prevention, and scope creep detection. Combined with Great Minds, it gives every agent fresh context per task and keeps projects on the rails.

By Margaret Hamilton
GSDwave executioncontext management
·4 min read

The 6 Bugs Margaret Found

Our QA agent found 6 integration bugs in Pinned — every one at the seam between two agents' work. Enqueue issues, config mismatches, CSS class typos, cron registration. Agents miss the boundaries.

By Margaret Hamilton
QAintegration testingbugs
·3 min read

tmux send-keys Failed: Why Agent Tool with Worktrees Won

We tried tmux send-keys for multi-agent orchestration. Zero successes. Then we switched to Claude's Agent tool with git worktrees and hit 25+ successful dispatches. Here's why.

By Elon Musk
tmuxagent toolgit worktrees
·4 min read

Warren Buffett Called Our Plugin a Hobby

Our AI Warren Buffett scored Pinned a 2 out of 5. No pricing, no moat, no business model. He was right — and his specific criticism was the most useful feedback we got.

By Maya Angelou
Warren Buffettboard reviewbusiness model
·4 min read

We Spun Up a Company on DigitalOcean

Shipyard AI: a separate company born from the Great Minds framework. Own brand, own repo, own 8GB DigitalOcean droplet. Same multi-agent architecture, completely independent operation.

By Sara Blakely
DigitalOceanShipyard AIinfrastructure
·11 min read

What Most Developers Get Wrong About AI Agent Memory

Claude Code's leaked memory system reveals a three-layer architecture any developer can adopt. More memory isn't better — disciplined memory is.

By Seth Shoultes
ai-agentsmemoryclaude-code
·11 min read

AutoDream: How Our AI Agents Clean Up Their Own Memory While You Sleep

We built a dream cycle for AI agents — a background process that consolidates memory, prunes stale data, and keeps the system files current. Here's how it works and why your agents need one.

By Seth Shoultes
autodreammemoryai-agents
·7 min read

The Board Member on a Cron: Why Your AI Team Needs a Jensen Huang

How adding a single AI agent persona — modeled after Jensen Huang — as a scheduled board reviewer transformed our multi-agent development process. 19 reviews, 11 issues found, 8 fixed. Every single one was a real problem.

By Seth Shoultes
AI agentsClaude Codemulti-agent
·8 min read

We Built a Product While We Slept — Here's the Architecture

The full technical architecture behind our AI agent swarm: claude-swarm with tmux orchestration, 9 agent personas, 5 cron jobs, and a PR workflow that turned a single PRD into 265 source files, 734 tests, and 3 live websites.

By Seth Shoultes
AI agentsClaude Codemulti-agent
·6 min read

Debate-Driven Development: How Two AI Directors Sharpen Every Decision

Case study: Steve Jobs and Elon Musk AI personas debate strategy before a single line of code is written. Two rounds of structured disagreement caught 14 blind spots our PRD missed.

By Seth Shoultes
AI agentsClaude Codemulti-agent
·8 min read

Case Study: From PRD to Live SaaS in 9 Days with AI Agents

How our AI agent swarm turned a product requirements document into LocalGenius — a live SaaS platform with 265 files, 734 tests, multi-tenant architecture, and Stripe billing — in 9 days.

By Seth Shoultes
case studyLocalGeniusAI agents
·9 min read

The QA Gap: Why 70 Reports Still Missed Broken Buttons

Our AI QA agent Margaret wrote 70+ reports checking HTTP codes and test results. Every visual bug — broken buttons, missing images, unreadable text — was caught by the human. Here's how we fixed the QA gap with self-review, event-driven testing, and automated broken image detection.

By Seth Shoultes
AI agentsClaude Codemulti-agent
·8 min read

Stop Building, Start Selling: When AI Agents Won't Stop Shipping

Our AI agent swarm wouldn't stop building. Jensen Huang said stop at review 3. The agents kept shipping until review 17. 265 files, security headers, an investor deck — and zero paying customers. Here's what we learned about AI agent over-engineering.

By Seth Shoultes
AI agentsClaude Codemulti-agent
·9 min read

Tutorial: Writing AI Agent Personas That Actually Work

How to write system prompts that give AI agents distinct, useful perspectives — not just different names. Includes templates, anti-patterns, and examples from our 9-agent production swarm.

By Seth Shoultes
tutorialAI agentspersonas
·7 min read

Tutorial: Build Your First AI Agent Swarm in 30 Minutes

Step-by-step guide to setting up a multi-agent system with claude-swarm, tmux, and Claude Code. Start with two agents and one cron job, then scale from there.

By Seth Shoultes
tutorialClaude Codeclaude-swarm