25+ yrs battle-tested Software Engineering | Architecture, Clean Code, AI in dev | Hot takes + Deep dives | YouTube insights 👇| Let's discuss! 🚀
Lost in Code
Joined February 2018
- Tweets7.4K
- Following402
- Followers1.9K
- Likes11.2K
My coding agent instructions say:
- Follow KISS
- Be minimalist
I even added the supreme design principle:
“Perfection is achieved, not when there is nothing more to add, but when there is nothing left to take away.”
And still ... 🤦♂️
GenAI may not be truly creative.
But it can point you to existing ideas
you would never have thought of.
And often, that is enough
to build great solutions. 😉
Seb retweeted
These stat lines are getting pretty wild.
Thanks for 300K stars and nearly 30m installs.
Big plans for 2027 too. Onwards and upwards!
Gherkin seems to be the best way
to make agent-written specs and tests reviewable.
But coding agents seem less efficient
at working with Gherkin than with other languages.
Anyone found a significant improvement?
Linter? Compiler? Editor?
Intermediate language? 🤔
Which multi-agent framework do you use? 🤔
I used github.com/unclebob/swarm-fo… by @unclebobmartin very successfully for quite a while 👍
Now working on my own which I'll release soon 😉
We used to refactor code.
Now we refactor Markdown. 😉
When agents maintain prompts and skills,
they tend to keep adding more text
instead of simplifying what is already there.
Over time, this creates "technical debt".
So I now regularly run review and cleanup sessions
to keep my agent instructions
sharp, simple, and focused.
Treating coding agents as tools
is the wrong mental model.
A better one:
A coding agent is like a skilled developer
who is new to your team and project every day.
That changes how you work with them.
You focus on building a harness
that provides the knowledge,
rules, and feedback they need. 😉
I have multiple projects
where almost all the code is written by AI.
How much of your code is written by AI meanwhile? 🤔
This tendency of current models
to overengineer is pretty annoying 😤
My agent team worked for 3 hours -
I just requested a full rollback
and complete rework🤦♂️
How do you handle context compaction
in your coding agents?
I switched to a simple rule:
"Always compact before starting the next slice."
Gives me more control over the context.
And so far, it seems to save tokens too. 😉
Have you seen getartcraft.com/apps?
Photoshop, Illustrator, Excel, ...
rebuilt with AI coding agents:
"Clean-room: implemented from public specs and observed behaviour only."
A small team can now use existing software as an executable specification to (re)build complex applications.
Impressive. 🤯
Very nice 👇😉
LGTM (Looks Good to Me) - Claude Opus 5.5 music video youtu.be/3TNpOD6bov8?si=ixt5… via @YouTube
Coding agents seem to struggle with abstract thinking
as much as humans do 🤷♂️
Example:
Single-action execution already exists.
Now add batch execution.
The obvious abstraction?
A single action is just a batch of one.
What did the agents do?
Added another execution path.
Sometimes the hardest part is convincing agents to remove code instead of adding more. 🤷♂️