How to Generate Mergeable Code with a Context Engine — Peter Werry, Unblocked
- Source
- youtube.com
- Author
- AI Engineer
- Date
Context
A coding can read a repository and still miss why a team chose its design. The talk description presents Unblocked's engine as a way to bring in past decisions, conventions and discussions, with sources attached so a person can check them.
The company's engineering article explains the mechanism: combine source code with pull request history, documentation and conversations, then retrieve what is relevant to the proposed change. Its illustrative scenario is a change adding retry logic that looks reasonable alone, while a Slack thread would show the team had removed retries because they masked cascading failures. The intended benefit is to give an agent the decision history that would change a human review.
- 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.
video1,000 Agent Tasks in a Sandbox: What Breaks When LLMs Run Code — Kevin Orellana, AWS
videoHow Inference Keeps Up with Our Insatiable Need for Tokens — Cerebras & Gimlet Labs
videoAuth for Agents: Let AI Sign Up for Your Product with auth.md — Michael Grinich, WorkOS
videoDecoupling the Brain from the Hands: Claude Managed Agents (Part 1 of 4) — Anthropic
Checking sign-in…
Loading comments…


