Skip to content

Folarin Akinloye

Home Articles Projects Topics About Contact

Loading…

Folarin Akinloye

AI Product Engineer in London, UK. I write about building AI systems that make it to production.

Content

All articles
Projects
Topics
Series
RSS feed

More

About
Contact

© 2026 Folarin Akinloye

Articles · Folarin Akinloye

Archive

Technical writing

Long-form writing on agents, retrieval, and what it takes to run this stuff in production.

Agentic AI AI Infrastructure AI System Design LLM Integration RAG

79 articles

Agentic AIA Skill Is a Dependency That Runs CodeAn Agent Skill is not a prompt template. It carries injectable instructions and executable scripts, so treat it like any package you install.August 2, 20268 minAugust 2, 20268 min
Agentic AISkills vs MCP vs Tools vs Subagents: Stop Conflating ThemFour different answers to "extend the agent," each solving a different problem. They stack, they do not compete.August 2, 20268 minAugust 2, 20268 min
Agentic AIWhat Agent Skills Are, and Why Progressive Disclosure Changes the MathA skill is a folder of know-how an agent loads only when a task needs it. The mechanism underneath is the whole point.August 2, 20267 min

August 2, 20267 min

04From Demo to Product · Part 12Designing UX for a Confidently-Wrong InternTraditional UX assumes the system is correct and fast. An AI feature is neither guaranteed. Design for that.August 2, 20267 minAugust 2, 20267 min

05From Demo to Product · Part 11The Reference Architecture for a Production AI AppThe model call is one box out of ten. The other nine are the engineering.August 2, 202611 minAugust 2, 202611 min

06From Demo to Product · Part 10Who Owns Quality: The Benevolent Dictator and AI Incident ResponseOn an AI product, quality is a judgment call that needs one owner, and an incident whose postmortem output is a new eval exampleAugust 2, 20269 minAugust 2, 20269 min

07From Demo to Product · Part 9Detect, Contain, Monitor: The Risks That Sink AI ProductsYou do not eliminate AI-product risk. You bound the blast radius and watch the rate.August 2, 20267 minAugust 2, 20267 min

08From Demo to Product · Part 8The Unit Economics of an AI ProductEvery request costs real money. Why the unit is cost per task, not per call, and how to keep it profitable.August 2, 20268 minAugust 2, 20268 min

09From Demo to Product · Part 7LLMOps and the Data FlywheelLaunch is the start of the work. How you operate an AI product, and how production usage compounds into a moat.August 2, 20268 minAugust 2, 20268 min

1 2…9