Search: "agents"

9 results

Easy agent skills that have proven useful in fixing bugs

What are agent skills? They're files that determine how an agent should behave and what tooling and workflows they should use. I think some are useful for now, but they will eventually be consumed by the models themselves and be integrated to the harnesses (some already have been). Project spesific workflows will provide value for a good while, since they are not generic.

I've used VSC and Kiro professionally in agentic engineering and Cursor & herdr on my hobby projects. This article focuses on relatively simple bugs, and isn't well suited for more complex items.

Fixing the VFS5011 fingerprint reader on Omarchy

My laptop has a Validity VFS5011 fingerprint reader and I wanted fingerprint auth on Omarchy. Enrolling worked fine. The verify right after it didn't, and the Omarchy setup script took that as a hard fail and never wrote the PAM config, even though my print was already enrolled. Turns out the reader just wedges after enrollment. A USB reset fixes it.

Taste is not the err in human input

Agents and swarms of agents are quite nifty nowdays. My current setup is simple. It runs a coordinator that I communicate with, and that delegates work to a others. The flow is generally: "Hey, I need this feature from roadmap. Ask questions if needed, if I don't answer in due time, make the best call with our north star." -> Coordinator makes a plan for dev/qa -> dev devs -> pushes to branch when tests are green -> qa verifies results on dev server -> loopy-loop until obvious bugs are fixed. Review bot makes review for PR. Later on I test the feat to see if it's anything like I wanted and correct, then merge when good and pool to releases that are gated. Currently working on trying to get the agents to know what is good in my opinion.

I think the current killer combo is the ability to be creative and have some propriatory data, as that's something that can't be accessed by competition. The cost of iteration is low. So low that I see no point in using a wireframe demo for the ui, as simple paper sketches can be read by AI to close enough for live iteration for actually working software. And most rigid general UI's are going away too in favor of agents generating a personalized UX on the fly, so this is just temporary. Omarchy is the beacon for this, a machine that is ever evolving to your needs.

The stuff that stays valuable is hard to automate - having taste, accountability, human relationships and even defining what is good. No one knows what the future will be, but it will be awesome.

Futurama

Building an MCP bridge

MCP was not clicking for me, so the best way to learn was to build a thing with it. I have a plethora of notes everywhere and now I have a machine that drops rough ideas into my publishing backlog.

MCP is basicly an api for AI that tells agents how it's supposed to be used.

Agents as productivity leverage (24 tested PR's to production during naptimes)

Agents, and especially great harnesses, like Cursor, have taken the drudgery out of coding. I like solving problems, and the level of abstraction for problems does not matter. Some programmers struggle with the change, since a big part of their identity has been chiseling out the code.

At the same time, I'm grateful for the fact that I can code, so I can appreciate the tools we now have. It's not unlike music - you can appreciate it more, if you understand the complexity and skills required to produce it.

Harry Potter moment

Went shopping for bananas, shipped 3 new features on the 30 min walk.

Simple CI-workflow example for agentic publishing

I've long done work with single dev workflows, where the CI-machine has been my laptop. That's perfectly fine for small software projects and stuff that does not require that much collaboration. Now I've hit a limit on that, because agents have become my team, so I needed a better solution.

Master's thesis

Completed a master's thesis, so that's in public domain now. Here are the key observations from the said thesis.

Elements of Sustainable ICT pt. 8 (On AI)

AI is the discipline of developing intelligent agents that encompases machine learning, deep learning, generative AI (ability to create new content based on what's learned). Types of DL models are Discriminate models (can classify cat pictures) and Generative AI models that can generate cat pictures (very compute intensive).

ML and AI models are build in 4 phases: development (Collect data -> clean -> train), training (Live data and validation produces trained models), Inference (Query -> prediction (output of some sort)) and Monitoring.