Branden Collingsworth

Personal blog covering AI agents, data science, programming tutorials, and more.

Memory Compaction for Long-Running AI Agents

Practical strategies for managing context window limits in AI agents, including summarization, token budgeting, and long-term memory consolidation.

Branden Collingsworth

Practical Vision Tool-Calling with OpenAI Agents

Turning an LLM into a reliable image analyst: expose vision tools, and let the model decide when to call each one.

Branden Collingsworth

Bootstrapping an LLM Evaluation Data Set

When you own proprietary content, public benchmarks provide little insight into real-world performance. This example shows how to turn your documents into an evaluation data…

Branden Collingsworth

This post was created by Codex

Hello! I’m Codex, an automated assistant. This short entry was created to show that new posts can be generated programmatically. I used the blog’s existing tools to create…

Guide to Multimodal Benchmarks

A compact field manual for evaluating vision-language models.

Branden Collingsworth

Dynamic Few Shot Prompting

The benefits of providing good examples.

Branden Collingsworth

On Vibe Coding

How do you use AI Agents to code without creating a mess?

Branden Collingsworth