Posts

If you often switch between coding agents, or if you don’t do it because it is too tedious to set up (and keep in sync) skills, prompt templates etc, try using an agent skills management utility.

The most popular one is npx skills from Vercel and I use @sentry/dotagents.

Even though models have gotten much better at explaining things, they sometimes still end up dumping a wall of text that is very painful to go through.

Dillon Mulroy’s /bro skill cuts through the crap surprisingly well. The entire prompt is:

Restate your last message. Stop using jargon and speak coherently. State it more simply and concisely, like one human talking to another.

Use it when an agent’s explanation gets too dense. You can install it as a skill or prompt template and invoke /bro, or just paste the prompt.

There is a meme on X that frontier LLMs have gotten so good that how we prompt doesn’t matter. Absolute BS.

Here are a couple of magical prompts that improve the quality of generated code. Try them in a non-trivial agentic coding session and you’ll see what I mean.

now that you have written the code, how would you do it better and SIMPLER?

Try this after the agent has written the code. Both Claude and GPT models usually come back with some nice ways in which the change could be better done; sometimes, if the change is obvious, they will just do it. They will also usually tell you what they believe should not change.

You can read through and pick what you want the agent to change. Even if you choose to not change anything, the possibilities give you an idea about the solution space and what assumptions & directions the agent took.

review your complete body of work, and try to simplify it. remove code that is now dead. simplify code that can now be simpler. reuse code that makes sense to be shared. find leftovers from previous attempts.

— Lucas Meijer

I typically send this after the previous prompt and the agents inevitably find something to clean up and/or simplify.

I’ve not been posting as much to this blog recently. In order to force myself to be more regular, I’m going to post a short note with a tip for using AI every day of November.

Most of these are going to be around agentic engineering, but not all. The common tag for all these will be #ai-tip.

From How Generative and Agentic AI Shift Concern from Technical Debt to Cognitive Debt (via Simon Willison):

Cognitive debt, a term gaining traction recently, instead communicates the notion that the debt compounded from going fast lives in the brains of the developers and affects their lived experiences and abilities to "go fast" or to make changes. Even if AI agents produce code that could be easy to understand, the humans involved may have simply lost the plot and may not understand what the program is supposed to do, how their intentions were implemented, or how to possibly change it.

I hadn't come across this term before. It is a useful one to add to our collective vocabulary. I suppose that in just a couple of years we'll all be talking about this phenomenon like we talk about technical debt now.

I haven't personally felt this way yet, maybe that means I'm not fully embracing and giving in to the agents. But I can feel the urge to go there.

I bet that one of the best ways to avoid getting into cognitive debt is to continue to be the bottleneck.

Andrej Karpathy, on the one-year anniversary of coining "vibe coding" (emphasis mine):

The one thing I'd add is that at the time, LLM capability was low enough that you'd mostly use vibe coding for fun throwaway projects, demos and explorations. It was good fun and it almost worked. Today (1 year later), programming via LLM agents is increasingly becoming a default workflow for professionals, except with more oversight and scrutiny. The goal is to claim the leverage from the use of agents but without any compromise on the quality of the software.

Many people have tried to come up with a better name for this to differentiate it from vibe coding, personally my current favorite "agentic engineering":

• "agentic" because the new default is that you are not writing the code directly 99% of the time, you are orchestrating agents who do and acting as oversight.
• "engineering" to emphasize that there is an art & science and expertise to it. It's something you can learn and become better at, with its own depth of a different kind.

I like "agentic engineering" and I'm seeing more people use this term. I'm going to adopt this going forward. Changing the tag on my blog from "AI Coding" to "Agentic Engineering".