Stop babysitting your agents... — Brandon Waselnuk, Unblocked
Source
AI Engineer
Author
AI Engineer
Date
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
context engineering — Deciding what an agent sees at each step — the discipline that replaced prompt engineering once context windows got large enough to fill badly.
MCP — The Model Context Protocol — an open standard that lets any AI assistant plug into any tool or data source without custom integration code.
Why it matters
If your coding agents compile but produce subtly system-breaking changes, the fix may be pre-flight context engineeringDeciding what an agent sees at each step — the discipline that replaced prompt engineering once context windows got large enough to fill badly.Full definition → — reasoning across your codebase, Slack, PR history, and org decisions to assemble a research packet before the AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → writes — rather than adding more MCPThe Model Context Protocol — an open standard that lets any AI assistant plug into any tool or data source without custom integration code.Full definition → tool access or a bigger context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition →.
Key quotes
“The gap is not intelligence at this point. It is context.”
Brandon Waselnuk
“An agent should write code that feels like it was written by someone who's been on your team for years.”
Brandon Waselnuk
“if you cache a correct answer, and then tomorrow someone asks the same question, and you answer it, you probably lied to them now because things probably changed in the 24-hour clock”
Brandon Waselnuk
“you're not going to wake up to a PR, you're going to wake up to a am I allowed to use this tool?”
Brandon Waselnuk
“the first piece of data it finds, it goes, oh, this this must be the pattern. It stops looking.”
videoWhy AI Agents Need Million-Token Context — Thomas Wolf & Olive Song, MiniMax
videoYour company brain will leak secrets: how we stopped it for big banks — Tanmai Gopal, PromptQL
videoTethered: Our Agents Are Us — Shu Fang, Two Sigma
videoAgents' next frontier: agent-to-agent and network effects — Jean-Denis Greze, Town
