This is a short summary. ↗ Open original to view full content
Harnesses are Situated Agents
from blog Drew Breunig, | ↗ original
More from Drew Breunig
Fable & The End of the Free Lunch
23 Aug 2026 |
original ↗
There’s some talk today about how agentic coders are balking at Anthropic’s pricing and adopting alternatives. I was reminded of a thought I had in the weeks following Fable’s release: the free lunch was over.
Manage Your Agent’s Loadout with Dr. Skill
27 Jul 2026 |
original ↗
Keep your context clean by keeping your agent's skills and tools in check.
Understanding the Dynamics of the AI Ecosystem with Pace Layers
4 Jul 2026 |
original ↗
Stewart Brand's Pace Layers framework reveals why AI's speed is straining the slower systems it depends on for support.
The Problem is Prompt Debt
23 Jun 2026 |
original ↗
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.
What Do Humans Need From Docs?
31 May 2026 |
original ↗
When an agent can explain anything, should we keep writing docs for humans?