Notes from Daniel
RSS FeedA working notebook on applied AI, backend engineering, cloud systems, security, and the ideas that sit between them. Written from Lagos, shared in public.
Start with the latest note, search the archive, or head back to oduonye.com.
Read my selected work.
Featured
AI-Native Engineering: Course Index
The reading map for a build-first AI-native engineering series: nine focused posts, one capstone, and a rigorous learner-critic release bar.
LLM Evaluation for Production Workflows
How to design a useful LLM evaluation set for production workflows using real task cases, failure modes, regression checks, and human review.
Reliable AI Starts Where the Demo Ends
A practical checklist for turning an AI feature from a happy-path demo into a system people can trust.
A small corner, now with a blog
Why this site has a blog, and what I intend to put here.
Recent Posts
AI-Native Engineering 08: Build the Software Factory
Turn a backlog into a safe, observable conveyor belt where agents make incremental progress.
AI-Native Engineering 07: Parallelize Background Agents as a Bounded DAG
Split independent work across isolated agents while controlling cost, conflict, and retries.
AI-Native Engineering 06: Secure the Agent as an Untrusted Operator
Reduce blast radius with boundaries, least privilege, approvals, and observable failure paths.
AI-Native Engineering 05: Review Agent Work with Intent and Evidence
Review behavior, tests, traces, and risk—not just a plausible-looking diff.
AI-Native Engineering 04: Make the Codebase Agent-Ready
Give a fresh agent the map, invariants, commands, and handoffs it needs to work safely.
AI-Native Engineering 03: Connect Capabilities Through MCP Portals
Govern discovery, authorization, routing, and audit for Model Context Protocol tools.
AI-Native Engineering 02: Engineer Context, Not Just Prompts
Curate the smallest high-signal context and preserve state across long agent runs.
AI-Native Engineering 01: Package Procedural Knowledge as Agent Skills
Turn team know-how into discoverable, versioned, testable Agent Skills.