Ai

Background Okay, so this post is a follow up to a few different posts, but most notably The Token Saving Cake is a Lie. Before reading this one, I highly recommend checking that out first. Go ahead. I’ll wait. Back? Good. Let’s continue. Headroom So I said that the solution is probably something like Lynkr, but before building the integration, I discovered Headroom (45k stars, Python, its own trained compression model, ships RTK as a component). It does everything the Lynkr plan described, supposedly better. Set ANTHROPIC_BASE_URL=http://localhost:8787, run headroom wrap claude, done. ...

Previous posts for context: The Future of AI Coding is Directing and C.A.S.T Progress: First Blood Last time I had one event flowing from a ticket board to a NATS topic. That was the plumbing. This time the plumbing has something running through it: a ticket goes in one end as a one-line wish, and a reviewed, merged, cleaned-up branch comes out the other. No human types a line of code in between. ...

Tools Full comparisons and context in my 2026 AI tech stack post. This is just what you need installed to follow the workflow below. Claude Code If you’re new, start with the cheat sheet and Anthropic best practices. Security — set this up first: Claude Code Security Hooks — 7-layer prompt injection defence, read guards, canary files Lock down your .env and any git-secret files in .claude/settings.local.json before anything else MCP: Context7 — library/API docs on demand DeepWiki — open source repo documentation Skills: ...

Previous post for context: The Future of AI Coding is Directing. Let Me Introduce You to Your C.A.S.T. Also, this banner was generated by ChatGPT and whatever model they are using at the moment, and I’m kinda impress, NGL. When I wrote about C.A.S.T last month, the design was solid but unproven. I had a SPEC, ADRs, hire/fire scripts, and a lot of conviction. What I didn’t have was a single event flowing from a ticket board to a NATS topic to a waiting agent. ...

Introduction In some ways, a lot has changed since my last post, and in other ways, not much has changed. There has been a big shift in the last 12 months, especially toward “agentic engineering” and how we run multi-agent AFK setups vs HITL as we have been. I touched on this in my introduction to the tool I’m working on as well, which, spoiler, is part of my toolchain. Kinda. It’s a WIP… ...

I have not been “AI pilled” yet. (Also, what a stupid term.) While AI has become deeply integrated into my workflow, and I genuinely love having agents run things for me in the background while I focus on other things, I wouldn’t say I’ve had some red pill moment where “I see the truth now” and AI became an essential and daily thing… You see, my morning routine when I start work is the same: I open my terminal of choice (Warp), and I open my IDE of choice (whichever JetBrains one is applicable). And then if the task deems it, I’ll open Junie or Claude inside my IDE. ...

Do trust and accountability go hand in hand? This is something I’ve been chewing on over the weekend. And I don’t know really, but here’s where I’m coming from. One of my side projects at PiForge at the moment is building a system around Agentic Engineering using team lead principles I’ve honed over years, and applying how human teams communicate and organize over the SDLC to agents (i.e. start with a spec, write tickets on a kanban board, grab the next highest priority, work till done, test, PR, release, document). ...

Trigger warning: this is part rant, part genuine exploration, and entirely my opinion. As usual. Also; research heavy. I wanted this to be informed. I’ve been thinking about this one for a while. In a previous post I argued that not everyone who writes code is an engineer, and that the title carries expectations. In another I complained about the lack of standards in an industry that rewards speed and hype over depth. And more recently I got on my soapbox about fundamentals mattering — about how the people who actually understood the machines they worked on are slowly dying off, and what we’re being left with instead. ...

Just because your fancy new Claude Code plugin prints out “50% tokens saved” in the logs doesn’t mean you actually got them. I was playing around with Caveman Compression last week and tried to get the UserPromptSubmit hook to rewrite prompts using the tool for savings across the board. Turns out? The hook doesn’t allow it. Probably for security reasons; can you imagine the injection attacks if any random plugin could hook into and replace your prompts? ...

Introduction I came across caveman-compression — a tool that compresses text into a token-efficient “caveman” format before sending it to an LLM. The pitch is simple: It can cut 30-65% of tokens depending on the content, which at Claude Opus prices adds up fast. I immediately wanted to wire it into Claude Code so compression would happen automatically on every prompt. The obvious hook was UserPromptSubmit. ...