Stop babysitting your agents... — Brandon Waselnuk, Unblocked
- Source
- youtube.com
- Author
- AI Engineer
- Date
Context
A coding may have access to company systems yet miss the existing service or design decision that should shape its implementation. Unblocked's account of its context engine describes gathering relevant information across code, documentation and conversations, then returning a compact research packet before the agent plans its work.
The company uses relationships between engineers, repositories and past contributions to help determine which information matters for a request. It also reports that reusing previously correct answers caused trouble when the underlying organization changed. The proposed benefit is supplying relevant, current working knowledge at the point of decision, reducing how often a developer must manually explain the company's practices again. These are vendor claims; the talk does not supply a controlled .
- 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.
- benchmark — A standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.
- token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
“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.”
Brandon Waselnuk
videoBetter AI Models Won't Fix Your Engineering Team — Nicholas Arcolano, Jellyfish
videoWhy AI Writing Still Reads Like Slop — Louis-François Bouchard, Towards AI
videoHow to Test AI Agents When No Benchmark Exists — Nathanael Weill, Air Canada
video1,368 AI Failures and What They Teach About Evals — Vishal Srivastava & Tanmay Sah, New York Life
videoYour agents lack context: Here's how to fix "You're absolutely right!" — Brandon Waselnuk, UnblockedAI Engineer
videoHow to Generate Mergeable Code with a Context Engine — Peter Werry, UnblockedAI Engineer
videoMergeable by default: Building the context engine to save time and tokens — Peter Werry, UnblockedAI Engineer
Checking sign-in…
Loading comments…