Overview
News
Salaries
Products
People
Growth
Offices
Financials

Overview

Hi, I'm Drew Breunig. I explore at the intersection of cultural anthropology, computer science, and media.

News

Blog 2 months ago
Harnesses are Situated Agents
Harnesses manage the systems around agents, from the session, to the company, to the domain.
Read more
Report
Blog 3 months ago
Manage Your Agent's Loadout with Dr. Skill
Keep your context clean by keeping your agent's skills and tools in check.
Read more
Report
Blog 3 months ago
Understanding the Dynamics of the AI Ecosystem with Pace Layers
Stewart Brand's Pace Layers framework reveals why AI's speed is straining the slower systems it depends on for support.
Read more
Report
Blog 4 months ago
The Problem is Prompt Debt
The plain-English prompt that makes prototypes effortless turns out to be a poor way to specify how a system should behave, and the bill arrives slowly, disguised as ordinary progress, until the application can barely move.
Read more
Report
Blog 5 months ago
What Do Humans Need From Docs?
When an agent can explain anything, should we keep writing docs for humans?
Read more
Report
Blog 5 months ago
The Cost of Overfitting the Harness
OpenAI winding down fine tuning is an interesting development and one to watch.
Read more
Report
Blog 5 months ago
10 Lessons for Agentic Coding
Guidelines for programming when code is cheap.
Read more
Report
Blog 6 months ago
Cybersecurity Looks Like Proof of Work Now
Is security spending more tokens than your attacker?
Read more
Report
Blog 6 months ago
How Claude Code Builds a System Prompt
Context engineering in action.
Read more
Report
Blog 6 months ago
The 2nd Phase of Agentic Development
Moving from clones to reimaginings.
Read more
Report
Show more news