Alejandro M. P.
In the previous post we looked at hidden furnaces in agentic products. The example was the most common one, title generation. You type the first message, and the product quietly asks another model to name the conversation. Small and useful.This time I want to add recaps to our tiny harness. Not...
Alejandro M. P.
Something that is important to understand when working with agentic products is that we are always in the hands of the product developer.Of course, the developer has always decided what the product does. But with AI products there is a new layer that I think we need to pay more attention to. The...
Alejandro M. P.
The most interesting AI workflow I have right now is not a coding workflow. It has code in it. It has a small Swift CLI, some auth state, a few JSON exports, a Codex automation, and way too much knowledge about how Discourse represents unread things. But it is not one of those fancy loops that...
Alejandro M. P.
Since I’ve been working with AI agentic tools, and especially since I’ve been working on the various incarnations of my own agent harness, there is something that is very clear to me.One of the most powerful things you can give an AI is the power of reflection.Not in the mystical sense. I don’t...
Alejandro M. P.
WWDC week has always been a funny mix of excitement and overload for me.There are the big moments from the keynote, the more technical State of the Union, the individual sessions, the screenshots people share, the tweets with tiny details, and then my own messy reactions as I notice what actually...
Alejandro M. P.
A few weeks ago I read An Interpreter for Swift, from Cocoanetics, and I had that nice feeling of somebody else having already articulated the thing that was vaguely floating in your head.Let me just say it outright: I get very sad every time somebody insists that TypeScript is the future of...
Alejandro M. P.
Skills are everywhere right now. People talk about them as if they were some magical incantation that will make AI more powerful while also keeping it under control.But as with pretty much everything else in this space, once you look closely, it is much less mystical than it sounds. It is mostly...
Alejandro M. P.
In the previous post we gave superpowers to the harness in the form of a bash tool. Even doing it just for the learning experience, it was already very eye-opening. It made this little Swift harness feel much closer to the real thing.And that is exactly why I don’t want to hand-wave the next part...
Alejandro M. P.
After teaching the harness to load AGENTS.md, my mind went back to thinking about the tools, and wondered, do we even need multiple tools?Our tiny Swift harness had the usual little trio: read_file, list_files, and edit_file. Which is fine. It works. It is also exactly the kind of thing that makes...
Alejandro M. P.
In the previous post, Have You Built an Agent Harness Yet?, we built a tiny harness in Swift. We gave it a loop, a prompt, and some tools, and with that it already had most of the features we are used to with modern AI. No magic. Just autocomplete, and a harness deciding what the model gets to see...
Alejandro M. P.
For years I have repeated a thing that I still believe. Every programmer should write a promise library once. I think agent harnesses are the 2026 version of that exercise.If you use AI coding tools every day, and especially if you have opinions about agent workflows, subagents, MCPs, commands,...
Alejandro M. P.
I have this weird feeling of deja vu.If you know me, you know I think dogma is one of the biggest curses in software engineering. Dogma is what happens when a practice gets treated as universal truth before context, evidence, and tradeoffs are considered.Dogma is what made OOP feel like the answer...
Amir Teymoori
Ever watched an AI coding assistant grep through your codebase looking for function references? Hundreds of matches scroll by, including comments, string literals, and similarly-named variables. Somewhere in that noise are the actual usages you care about. There’s a better way. The Language...
Amir Teymoori
This comprehensive guide covers the most frequently asked interview questions for AI and LLM engineering positions at startups and tech companies in 2025. From transformer architecture to RAG systems, prompt engineering to production deployment – these are the questions that separate candidates...