@mattpocockuk: An actual slide from my talk at @aiDotEngineer Paris next Thursday. People have this mad idea that their implementer ag…
Summary
Matt Pocock shares a slide from his upcoming talk at AI Engineer Paris, discussing the idea of hiding coding standards from implementer agents to fix them in review.
View Cached Full Text
Cached at: 09/18/26, 10:49 PM
An actual slide from my talk at @aiDotEngineer Paris next Thursday.
People have this mad idea that their implementer agent should ALSO apply their coding standards
The solution? Hide your coding standards from your implementer agent, fix them in review https://t.co/WPWOiCBsmr
Similar Articles
@mattpocockuk: Submitted a session to @aiDotEngineer Paris "Fixing The PR Bottleneck" - all about how you can apply software fundament…
A tweet announces that a session titled 'Fixing The PR Bottleneck' has been submitted to the AI Engineer Paris event, focusing on applying software fundamentals and automated review to speed up pull requests, with the session to be recorded and shared on YouTube.
@mattpocockuk: I gave a viral talk recently, and @swyx asked me to put something together to explain how I did it - to help future AIE…
Matt Pocock shares advice on delivering AI conference talks, drawing on his background as a voice coach to discuss managing tension, breathing, audience engagement, and slide design.
@mattpocockuk: Adding a set of Martin Fowler's code smells from Refactoring into my /review skill Mysterious Name, Duplicated Code, Fe…
Matt Pocock announces adding Martin Fowler's code smells to his /review skill for AI coding agents, and shares his open-source collection of composable agent skills designed to improve real engineering workflows.
@SergioPaniego: sharing the slides from today’s talk at seLIA (https://selia.codeberg.page) on how to train an open coding agent using …
Sharing slides from a talk at seLIA on training an open coding agent using TRL and OpenEnv, part of an open-source conference on free software and open AI.
@mattpocockuk: This is an extremely good watch. The things that felt novel/interesting to me: 1. Lock down your agents Humans tend to …
This post summarizes insights from Lauren's talk on shipping 2,500 PRs using locked-down AI agents, emphasizing verification infrastructure and feature maps for efficient codebase management.