Engineering Recap: Rebuilding Logistics Systems with AI
alex_verem · x · 2026-07-16
This is an engineering recap of how to rebuild real production systems using AI/agents, avoiding the empty hype of "we used AI so it's faster". The author notes that this system is a delivery orchestration platform supplying FedEx, dealing with a brownfield code base facing real users, real logistics, and real consequences of failure. The team originally estimated an 7–8 month rebuild for the core system.
Their approach: writing no code in the first week. Instead, they scanned the entire repository, built a knowledge graph, and documented every module, dependency, data flow, and domain term in markdown. Later, agents read this knowledge graph before modifying any code. The author emphasizes that many teams skip this step, but it is crucial in complex legacy systems.
More from coding & agent
- Claude Code skill uses 10 Markdown rules to make outputs ADHD-friendly — alex_verem · 2026-07-22
- A better path to agent autonomy is running waves, finding friction, and iterating — JnBrymn · 2026-07-22
- Coding agents are heading toward an AI-writes, AI-reviews, human-approves workflow — aftahi_ai · 2026-07-22
- oMLX 0.5.2 adds Mac menu-bar stats, low-bit decode kernels, and faster downloads — awnihannun · 2026-07-22
- GitHub review bot hits its PR limit and forces a 39-minute cooldown — DanielLockyer · 2026-07-22
- Max reasoning effort appears to be mobile-only in Codex Remote, not desktop — GabGarrett · 2026-07-22