Speaking to myself
• 212 words • 1 min • updated
Lately I’ve been stealing Simon Willison’s playbook of taking to oneself:
My habit of creating long issue threads where I talk to myself about the features I’m planning is proving to be a good fit for outsourcing implementation work to this new generation of coding assistants.
I am mostly interested in leaving a paper trail of my actions and decisions whilst debugging and investigating a problem or implementing a feature.
The paper trail doubles down as:
- (i) documentation for my teammates, so that I don’t need to repeat myself during code reviews;
- (ii) context for me and my teammates’1 future selves, so that we can understand why I chose to do something in a certain way at the time;
- (iii) as Simon suggests, context for LLM agents so that I don’t need to repeat myself to them.
I find it useful to do so in chat apps (e.g. Slack threads), in addition to bug trackers (e.g. GitHub Issues or JIRA tickets). Be verbose! The more context the better.
As a side note, blog posts yield the same benefit. The more the merrier!
Reference: https://simonwillison.net/2025/May/26/notes/
-
Your periodic reminder that “teammates” sounds much better than “colleagues”. Or you can use “coworkers” too. Though I tend to use “teammates” as “coworkers in my immediate team”. ↩︎