· 5 min read
When Does More Context Make an AI Worse?
Agents should support fluid conversation and structured workspaces without making users understand the context machinery that keeps either one reliable.
← All posts 
Posts tagged "engineering"
10 posts on this topic
· 9 min read
What a New Hire Learns That Enterprise AI Still Misses
The right model for enterprise AI is not 'better search.' It is compressed onboarding. A real enterprise second brain teaches an agent what a strong new hire learns in the first six months, then turns that knowledge into reliable action.
· 7 min read
The Codebase Is the Onboarding Manual
If agents are blank slate coworkers, product strategy can no longer live in Slack, Notion, or someone else's head. It has to become part of the execution environment.
· 8 min read
Sycophancy Is the Last Hard Problem in AI-Assisted Software Development
RLHF-trained coding agents do not just make mistakes. They silently implement the wrong thing, accruing alignment debt that passes tests and leaves the codebase worse off.
· 8 min read
Why Does Enterprise AI Cost More and Deliver Less?
Microsoft shipped an enterprise Anthropic integration in weeks. They clearly can deliver frontier AI. So why does Copilot for 365 feel like a downgrade from a $20 subscription?
· 9 min read
Inference Is in the Name
If your workflow has no unknowns, runtime LLM inference is often the wrong architecture. Build deterministic cores, then add AI where adaptation actually matters.
· 7 min read
Benchmark Leaders, Agentic Laggards
The AI leaderboard tells you which model reasons best in isolation. It tells you almost nothing about which model completes real work.
· 7 min read
What the Fair Use Conversation Is Missing About LLM Data Extraction
The AI copyright debate focuses on training data. But the more commercially relevant question might be extraction, and the legal framework for it may already exist.
· 10 min read
What I Learned Running OpenClaw as a Solo Dev for Two Weeks
Agentic harnesses solve the orchestration problem. The models are the bottleneck. Here's what actually works after 43 PRs and a zettelkasten full of operational data.
· 12 min read
Building a Coffee Data Pipeline from Scratch
The most interesting thing about the purveyors data pipeline isn't the scraping. It's the recursive feedback loop, and what it reveals about directing AI agents.