---
title: "Speaking to myself"
url: https://perrotta.dev/2025/06/speaking-to-myself/
last_updated: 2025-09-05
---


Lately I've been stealing [Simon Willison](https://simonwillison.net/)'s
playbook of [taking to oneself](https://simonwillison.net/2025/May/19/#:~:text=My%20habit%20of%20creating%20long,new%20generation%20of%20coding%20assistants):

> My habit of [creating long issue
> threads](https://simonwillison.net/2022/Nov/26/productivity/#issue-thread)
> 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/

[^1]: 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".