Organising your AI workflow is no longer just about putting the chaos in order, it directly impacts your AI costs. Every command your agent runs and every file it reads ends up in the context window, and the bigger that window grows, the more you pay and the less focused the agent becomes.

This article looks at three tools I run in my local dev setup to fight that - one for trimming shell output, one for compressing context and one for giving the agent a memory that outlives the session. It also covers where context compression falls short, when running Claude Code through a proxy.

Optimising one's workflow with agents is no easy task to grasp. You constantly want to improve on it and organise it in a way to reduce noise, which is quite a lot. Fact, people are more and more not even proof-reading their own text, nor code. They just automate the generation.

How do we manage that chaos of specs, instructions, skills, commands, cross-agent workflows, etc? OpenClaw is here to the rescue. The nifty agent that you can control through any chat platform on your phone, but runs on your machine. And then there's the Social Network for AI agents

Coding agents forget everything between sessions, and the bigger the codebase grows, the more they have to rediscover before they can do anything useful.

This article covers spec-driven development as a whole - why agents need specs, the frameworks worth starting with, and how my own setup evolved from homegrown commands to OpenSpec and beads.

Starting a new codebase with Claude Code or another AI coding agent, requires a lot of fine tuning to make long-term, production ready code development consistent.

The main entry points for day-to-day interactions with an agent within a project are CLAUDE.md and custom bot commands. In combination with specs, these become the bread and butter of your daily coding activities.

Coding agents run shell commands with your user's privileges, whether it's Claude Code, Codex, or an open-source harness like OpenCode running against your own models. Their own guardrails have come a long way, but a prompt injection hidden in an open-source package can still turn the agent against your machine. Agents belong in a sandbox, especially when you run a swarm of them.

This article shows how I sandbox mine in a dev container: the agent works on the project inside the container, the host keeps the git credentials, and notifications get out through a single whitelisted command. One trade-off up front: containers are slower on macOS and Windows, where they run inside a virtual machine with limited access to the bare metal.

How I researched, designed, coded, and deployed my blog in a single day—heavily assisted by AI tools.

My AI-powered coding workflow with Claude Code, Copilot, and ChatGPT.

Launching my new blog with Astro, Cloudflare Pages, and Terraform.