A Practical Method: Work at the Intent Layer

As AI tooling improves, natural language and lightweight specs are increasingly becoming the interface to system changes. Instead of starting from scratch, engineers and operators can delegate first drafts to agents and focus on architecture, correctness, and integration. The goal isn’t to replace judgment, but to apply more of it where it has the most leverage.

Habits:

• Start with intent: a short spec, constraints, and acceptance criteria
• Ask the agent for a plan, then an implementation
• Have it generate verification steps and run checks
• Review for readability, security, and operability
• Iterate with feedback and document key tradeoffs

This is a series on practical methodologies for working with AI agents. These aren’t theoretical frameworks… they’re habits and patterns that help engineers and operators get reliable, verifiable results from agent-assisted workflows.

The core idea: AI agents produce first drafts, not finished work. The value comes from treating them as collaborators that need clear inputs, constraints, and verification… just like any other tool in your stack.

The Series

1. Start with Intent - Work at the intent layer: specs, constraints, and acceptance criteria before work begins.

   Continue reading...

My Notes

Today, I spent the day exploring how to parse code, process it with a Large Language Model (LLM), and apply the resulting edits back to the codebase. It’s a fascinating problem with multiple approaches, and I enjoyed digging into the different methodologies.

Brainstorming and Initial Research

Before writing any code, I explored various ideas and brainstormed solutions using AI assistants like ChatGPT, Grok, and Claude. This helped me clarify the problem space and evaluate different potential solutions before diving into implementation.

Continue reading...

Fun Tutorial: Using Grok’s Function Calling Feature via the API with Python and UV

In this tutorial, you’ll learn how to use Grok’s function calling feature via its API in a Python project. We’ll use UV, a fast Python package manager, to set up and manage the project. By the end, you’ll have a simple, interactive script that lets Grok flip a virtual coin and respond with the result… all while having a bit of fun!

Continue reading...

Introduction

This is bold text, and this is emphasized text.

Visit the Hugo website!