Ed Spencer's Blog

Paddock is a better interface for Claude Code.

I don't know about you, but I have dozens of Claude Code sessions going at any one time.

I justed added support for Composable Fleets to herdctl.

One of the most valuable unlocks with herdctl for me has been having a bunch of agentic things that just happen every day, without me having to intervene. herdctl itself already uses the following agents that run on a daily schedule: changelog - updates t…

This week herdctl gained support for Slack and Web connectors, opening up two new ways to interact with your Claude Code agents, running on whatever machine you like.

I recently upgraded to 2.5 gigabit managed switches for my home network.

herdctl can now run Claude Code Agents in Docker containers, significantly expanding your options for running powerful local agents that do not have full access to your system - whether you're running agents on your laptop, in the cloud or both.

I love Claude Code, but there are three things I really wish it could do: Invoke itself, on a schedule or in response to events Let me talk to it over discord or slack Let me coordinate dozens of Claude Code agents together This is what herdctl aims to do.

As a developer who occasionally creates technical content, I've always found thumbnail creation to be a friction point.

About 9 months ago I launched bragdoc.ai, an AI tool that helps software engineers keep track of their work and turn it into useful documents for performance reviews, weekly updates, and resume sections.

The Claude Code docs suggest that if you want to run more that one Claude Code session simultaneously for the same project, you should use git worktrees.

A few weeks ago I released mdx-prompt, which makes it easy for React developers to create composable, reusable LLM prompts with JSX.

Sometimes I find myself doing the same thing over and over again.

In the last 6 months, the way that leading software engineers build software has undergone a fundamental shift.

After 2 years of doing my own thing, I recently got the itch to work on something bigger than myself again and earn some money in the process.

In the previous article, we went on a deep dive into how I use mdx-prompt on bragdoc.ai to write clean, composable LLM prompts using good old JSX.

I just released mdx-prompt, which is a simple library that lets you write familiar React JSX to render high quality prompts for LLMs.

I'm a big fan of IndyDevDan's YouTube channel.

Feel free to run your own version if you don't want to pay me the $2.50/month for the hosted version.

Every word in every article on this site was, for better or worse, written by me: a real human being.

Recently I posted about AI Content Recommendations with TypeScript, which concluded by introducing a new NPM package I've been working on called ReadNext.

Part 3 will dive into how to use InformAI to create personalized predictive recommendations based on a user's pattern of interaction with your app.

This is the first article in a trilogy that will go through the process of extracting content from a large text dataset - my blog in this case - and making it available to an LLM so that users can get answers to their questions without searching through l…

Authoring long-form content like blog posts is a pleasant experience with Markdown as it lets you focus on the content without worrying about the presentation or making the browser happy.

Most web applications can benefit from AI features, but adding AI to an existing application can be a daunting prospect.

React Server Components are a game-changer when it comes to building large web applications without sending megabytes of JavaScript to the client.

Last week we looked at how React Server Component Payloads work under the covers.

If you've spent any time playing with React Server Components, you've probably noticed a bunch of stuff like this at the bottom of your web pages: <script>(self.

During my time at Palo Alto Networks, I spent most of my time working on a product called AutoFocus.

When I'm writing software I usually have the following windows open, all at the same time: 2 column layout VS Code (window = 2560 x 2160) A fullscreen-equivalent browser with usable console to see what I'm working on (window = 1920 x 2160) A large terminal

When the web was young, HTML pages were served to clients running web browser software that would turn the HTML text response into rendered pixels on the screen.

React and Next.js introduced Server Actions a while back, as a new/old way to call server-side code from the client.

tl;dr: a Backups API exists for OPNSense. opnsense-autobackup uses it to make daily backups for you.

Disclaimer: Theater enjoyment may be diminished by using it to watch Manchester United I built out a home theater in my house a couple of years ago, in what used to be a bedroom.

I have a bunch of these nice Minka Aire fans in my house: They're nice to look at and, crucially, silent when running (so long as the screws are nice and tight).

As I mentioned in the previous post, OpenAI dropped a ton of functionality recently, with the shiny new Assistants API taking center stage.

OpenAI dropped a ton of cool stuff in their Dev Day presentations, including some updates to function calling.

The microservice architecture pattern solves many of the problems inherent with monolithic applications.

A lot has changed in the last few years when it comes to implementing applications using JavaScript.

I use Jasmine as my JavaScript unit/behavior testing framework of choice because it's elegant and has a good community ecosystem around it.

So another great Sencha Con is over, and I'm left to reflect on everything that went on over the last few days.

Love working with Sencha frameworks?

Just as with Jacky's session, I didn't plan on making a separate post about this, but again the content was so good and I ended up taking so many notes that it also warrants its own space.

I didn't plan on writing a post purely on Fastbook, but Jacky's presentation just now was so good I felt it needed one.

Sencha Con 2013 kicked off today, with some stunning improvements demoed across the product set.

One of the things I really loved about Rails in the early days was that it introduced me to the concept of autotest - a script that would watch your file system for changes and then automatically execute your unit tests as soon as you change any file.

As some of you may know, I left Sencha last week to move to another startup just up the road in San Mateo.

At its simplest, a Sencha Touch 2 application is just a small collection of text files - html, css and javascript.

Disclaimers: this is the most unofficial, non-Sencha-backed poll of all time.

The last few months have flown by faster than almost any before them.