How teams actually ship this stuff.
One long-form production walkthrough per domain. Each strings together the per-lesson scenarios into a single build narrative — what broke, what worked, and the principles that stuck.
Building a customer-success copilot at ScaleOps
How a B2B SaaS team went from one brittle chatbot to a production-grade copilot in six weeks.
How DataLayer built its integrations platform on MCP
Replacing a tangle of bespoke connectors with reusable MCP servers.
Migrating Rails 5 → 7 at LumenPay
A 400K-line monolith and a five-person team — how Claude Code took the timeline from quarters to weeks.
Cutting LLM costs 62% at OmniSupport
How a customer-support platform retuned prompts, caching, and structured output without sacrificing quality.
Shipping a research agent at Research Co
From a slick demo to a system that handles thousand-document briefs without face-planting.
PrintWize: from one prompt to a real agent in three sprints
How a 30-person print-on-demand startup outgrew a single Claude call.
NorthStar Analytics: cutting $40K/month in LLM cost
A four-week dive into prompt caching, model tiering, and compaction.
LedgerLine: a tax-prep bot that never files without a human
How a SMB tax startup shipped autonomous drafting with strict HITL.
HelioGrid: a 40-skill internal Claude Code library
Encoding tribal knowledge so juniors ramp in three weeks instead of nine.
OrbitalDevs: from bespoke connectors to MCP
A CI/CD platform replacing 12 hand-written wrappers with reusable MCP servers.