
## The Big Idea

When providing accurate context is make-or-break for your workflow, everyone needs to become a better writer.

We convinced ourselves that moving fast was the same as being smart. Shipping first. Reacting faster than anyone else. What we did not notice is that this trained an entire generation of builders to think only in the moment, never on the record.

That mindset worked when everything stayed in your own head. It breaks completely when your collaborators are machines. And it is the same thing your teammates have quietly been begging you to fix for years.

### Why this suddenly matters

- With LLMs and agents, context is not just helpful, it is _everything_.
- Developers are historically allergic to context. We want to skip the ticket and jump to the code.
- That habit is now actively expensive.
- Clear writing is fast implementation. Fuzzy writing creates hallucinations, bugs, and rework, and wastes time.
- If you get good at writing for agents, you automatically get better at writing for humans. Your teammates have been asking for this for years anyway - they're gonna love you for it.



## A simple framework for writing to agents (and humans, and future-you)

1. State the problem or goal. What is happening? What outcome matters?
2. Provide history. What have you already tried, seen, or ruled out?
3. List constraints. What absolutely must not break?
4. Point to the code. If you were starting, where would you look first? Any past examples or similar patterns?

Go back and re-read your instructions, and imagine this is the first time you're hearing about the bug or feature you're describing. Is there enough information for you to get the job done?

Iterate as needed. That's really all there is to it.

## A real example

I was getting spam signups to the Tiny Improvements mailing list. Dozens a day. Instead of stewing on it internally like I used to, I wrote up this description from my phone while on a plane:

```
I have been getting spam signups on my newsletter form for the past couple weeks - can you read through `SubscriptionForm.tsx` and help me come up with a plan to deter spam signups?

Here are some sample subscriptions from the past few weeks that are all spam:
(list of ~50 spam signups, including the addresses, first and last names used)

Based on what I'm seeing here, I think we can probably do a few things to deter spam signups:
1. make sure the honeypot field on the form is working as expected
2. Automatically reject signups where the first name is mixed case has >3 capital letters: i.e. XavcASkiox
3. Automatically reject signups where the first name has >4 consecutive consonants: i.e. mtpDQVeZaqb

For signups that _fail_ any of our spam checks, we should make it look like the subscription was a success, but don't actually subscribe the email address, and instead log the spam signup attempt to Posthog analytics for further analysis.
```

That 90 seconds of writing turned into a working fix with minimal edits, and thankfully, spam fell off a cliff.

And bonus: writing it down cleared background mental noise I did not realize I was carrying.

## Conclusion

If context is now make-or-break, writing is no longer optional - it's the difference between wasting your time and speeding up your workflow.

Write down what you're thinking about. It frees your brain, helps your team, and makes agents actually useful.

_And if you're the one sending automated spam signups to my newsletter: c'mon, dude._

---

### For more Context on Context

- [Matt Pocock's video on LLM Context](https://youtu.be/-uW5-TaVXu4) is a superb explainer on the topic, with a really helpful series of diagrams to help you visualize the concept.
- Michael Reeves shows what happens when you [corrupt the back-context](https://www.youtube.com/shorts/WP5_XJY_P0Q) of an LLM conversation. It's chaotic - and convincing.


The next great engineering skill is not coding

A simple framework for writing to agents (and humans, and future-you)


Hey there,

I hope you're well.

I love the turnover of the year: a time where people tend to become the most hopeful and optimistic. January can feel both cleansing and refreshing, like we've all just stepped over an invisible barrier that was holding something back. I love the way people share their goals openly and reflect on their past year's progress. Even if you're the type to turn your nose up at New Year's Resolutions™️, by doing so you've acknowledged that some people find them motivating. That right there is what has me transfixed right now.

From motivation grows enthusiasm. In enthusiasm, there is value.

## On Working in Public

In a [recent newsletter](https://mikebifulco.com/newsletter/on-seasonal-change-open-source-carbon-offsets), I mentioned that I had just finished reading a great book on building Open Source Software, called Working in Public. I had a few hiccups get in the way of getting my notes out into the world, but by now they're public! Feel free to [give them a read](https://mikebifulco.com/posts/working-in-public). I'd love to know what you think.

## On Enthusiasm

Lately, I've been describing myself as an _Enthusiast's Enthusiast_ - I truly love the feeling of developing and growing a new passion. I find that I go through regular cycles of passion for this-and-that, growing my expertise quickly and listening to others to glean as much as I can from them. I could make a list a mile long of the things I've done this for, but I thought I'd share a few recent passions that might interest you:

- 🧧 I've been reading about **Bitcoin** lately, as I'm sure you may have been as well. A friend pointed me to a few great primers on the subject, which I tore through as my on-ramp to learning more. I'd recommend getting started with an article called [The Bullish Case for Bitcoin](https://vijayboyapati.medium.com/the-bullish-case-for-bitcoin-6ecc8bdecc1), by Vijay Boyapti.
- ☕ I really, truly love great **Espresso**. To me, there's nothing better than taking in a cup of perfectly brewed beans. Learning about how and why coffee can taste so wildly different has opened my appreciate for the experience that much more. I'd recommend checking out [James Hoffman](https://www.youtube.com/channel/UCMb0O2CdPBNi-QqPk5T3gsQ) on Youtube - he's a former World Barista Champion, and a genuinely wonderful human being. His videos are world-class, relaxing, and supremely informative.
- 📝 I've never really had a habit for **writing** -- but I'm trying to build one. I'd love it to be easier for me to knock out a few paragraphs. I've been told it's simple: just write more, and it gets easier. In an attempt to do so, I've started a small daily writing habit based on [Morning Pages](https://juliacameronlive.com/basic-tools/morning-pages/) -- every day I write stream-of-consciousness thoughts in my notes, to help me to clear my mind, organize my day, and express myself more clearly. I was on the fence at first, but after a couple weeks, I think I'll stick with it for a bit!

## What are you working on?

I'd love to hear about your passions, or what you're looking to learn about in the new year. I'm here to learn and to listen just as much as I am to share. What's your latest muse? Let's [talk about it](mailto:hello@mikebifulco.com)! hello@mikebifulco.com. If you found this interesting or useful, I'd love it if you shared it with a friend.

In the meanwhile, be excellent to each other. Thanks for reading Tiny Improvements - talk soon!

Mike


#writing: 2 posts tagged

The next great engineering skill is not coding

The Enthusiast's Hidden Superpower