9 posts
AI-Driven Development isn't a replacement lifecycle — it re-wires the one you already run. A stage-by-stage field guide mapping ADD onto requirements, design, dev, review, test, security, release, ops, and maintenance — grounded in two real projects.
19 min readA field study of ai-proxy, a multi-tenant AI gateway built end-to-end with ADD: 23 milestones, ~120 tasks, six days, zero waivers. What the method felt like in production and how the LLM behaved when scope was clamped.
12 min readThe step that closes the loop: Observe production behavior and fold the spec delta back into the next Specify. How ADD keeps documents living while old-school artifacts rot — and how the method improves itself.
11 min readVerify by evidence, not by reading the diff. ADD's earned-green: an adversarial refute-read that tries to break the result, because AI code is frequently plausible and wrong. Trust through proof.
13 min readAI made writing code nearly free and quietly broke the SDLC. AI-Driven Development — five competencies, eight steps — constrains what an agent builds while freeing how it builds, proven across a 23-milestone production gateway shipped in six days.
26 min readOne agent is a worker. A team of agents with a supervisor, evals, tracing, guardrails, and cost control is a platform. Here's when multi-agent actually helps, when it hurts, and the four pieces of scaffolding that turn a demo into a product you can run.
12 min readThe invisible foundation beneath every AI harness layer: centralized state management, per-model cost tracking, rate limit handling, a custom React-to-terminal renderer, and multiple entry points. This post covers what makes 'works in a demo' become 'works in production.'
9 min readWithout health checks, your load balancer sends traffic to dying instances. Without graceful shutdown, every deploy drops requests. Here is how ShelfWise achieves zero-downtime deployments with proper probes, SIGTERM handling, and connection draining.
11 min readTheory without deployment is fiction. This capstone assembles all 22 prior patterns into a deployed, monitored, incident-ready multi-tenant Python backend — from Docker Compose to runbooks to your first production incident.
22 min read