ANDMOD.AND-10 · v1.0

Ship code faster
— without 5×
the bugs.

10 micro-lessons · ~102 min · Real Docker images

THE SHIPPING BAY · LIVE
BAY.A · 4 ROUTES
ROUTING
REPOPLANEDITTESTSHIP
ROUTE 1/4 · in-flightagent + tests
ANDROLE TRACKHOT

AI-native software development

Ship 5× faster with coding agents you actually trust.

WHY THIS MATTERS · SWE-BENCH VERIFIED · ANTHROPIC 2026 AGENTIC CODING TRENDS · VECTARA 591-INCIDENT TAXONOMY
By April 2026, top SWE-bench Verified scores cleared 87.6% (Claude Opus 4.7 Adaptive). Stripe ships 1,000+ AI PRs/week internally; Shopify reports 20% engineering productivity lift. The pattern that makes those numbers real isn't 'better prompts' — it's the read-plan-edit-verify loop with rules, hooks, MCPs, and a cost dashboard. This course is the rollout playbook.
WHAT YOU'LL LEARN
01The agentic dev loop
02Project rules: AGENTS.md / CLAUDE.md
03Plan mode and the read-only stage
04TDD with agents — the only way that scales
05Subagents and parallel research
06MCP servers and tool wiring
07Hooks, automations, and rails
08PR review automation and auto-fix loops
09Cost, telemetry, and $-per-merged-PR
10Production rollout: SOC 2, secrets, and audit
YOU'LL BE ABLE TO
Run the read-plan-edit-verify loop reliably across claude-code / cursor-agent / aider
Author CLAUDE.md / AGENTS.md, hooks, and MCP servers that survive long sessions
Wire a TDD-with-agent loop, PR review pipeline, and $/merged-PR dashboard end-to-end
Run a Tier 0 → Tier 1 → Tier 2 rollout with audit log + signing + kill switch
Cut $-per-merged-PR by 5-10× via structural fixes (rules, hooks, severity tagging)
RUNNABLE ON YOUR MACHINE
$ docker pull snap/ai-native-dev:agent-dev-shell
$ docker run --rm -it snap/ai-native-dev:agent-dev-shell
snap/ai-native-dev:agent-dev-shell
QUICK PREVIEW · 7 MIN
VERIFIED ENGINEER REVIEWS
The agent-dev-shell bake-off is the spike kit my team has been missing. We picked claude-code for backend and cursor for frontend in week 2.
@claude_code_kimVERIFY ON GITHUB
The cost-dashboard lesson alone paid for the course. We dropped from $4.20 median $/PR to $0.30 in 8 weeks of running it.
@dx_eng_julesVERIFY ON GITHUB
LESSONS10
HOURS~1.7
LEARNERS0
THIS WEEK+0%