Anthony Bible

  This is part 2 of my Go logging series. If you haven’t read part 1 , I recommend starting there. In that post, we looked at changing log levels dynamically based on error volume. In this post, we’ll look at another approach: using OS signals to change log levels at runtime without restarting the application. The Foundation OS Signals Before we begin, let’s do a quick crash course on OS signals. Signals are a low-level operating system feature, and POSIX standardizes many of the common Unix signal behaviors. They notify a process that an event has happened. That event might be a user pressing Ctrl+C, a terminal closing, or the OS asking the process to terminate. Both Linux and macOS have signal handling although they may not implement the exact same set of signals. You've probably interacted with signals without realizing it. Whenever you send   CTRL+c   or when you press CTRL+z,  this sends a SIGINT and SIGTSTP respectively.  ...

Prelude   In the previous post  I talked about the basics of an agent and why I decided to create my own. While I encourage you to go back to read the previous post, here's a refresher: an agent allows an LLM to interact with the outside world. I'm doing this for two main reasons, the first being that there is no great open source AI troubleshooting agent today and the second being that I find it helpful for my day-to-day activities.   I talked a little about the technical parts in the earlier post but it was all generic and pertained to all agents, in this post I am going to talk about how my AI agent works, from how it receives a signal to how it investigates to how it escalates or presents its RCA. Chain of Thought Traditionally, LLMs worked that you asked a question and it answered immediately by just spitting out an answer. Then in January of 2022 a paper came out detailing chain of thought (CoT), where you prompt the LLM to reason...

I've been building my own agent harness for a few months and figured it was time to write about it. I don't have all the answers, but I learned a lot from other people's process posts and wanted to add to that pile. This is part one.  The foundation: You've probably heard the word agentic before, maybe a bit too much since it's sold as a marketing term. Agentic workflows, agentic coding, agentic hotel booking, agentic breathing. With as much hype as it's getting you would expect it to cure cancer and maybe one day it will but as of right now it's not creating any cures for cancer. So what separates agents and a chat application like ChatGPT? Well if you ask someone that today, the line is getting thinner and thinner. But a chat application is exactly what it sounds like where you chat back and forth with the LLM. With an agent you give it hands and fingers stretching out into the world to gather information and take actions. This can be any...