As many of you know, I’ve built a tool called Stride. It is a human / AI collaboration tool that offers a robust workflow with many features to drive collaboration and predictability. It takes the form of a hosted kanban-like app that manages the detailed tasks and agent plugins for all of the major AI agents. Even though it has several thousand users now, I have struggled with forcing the agents to always follow the workflow defined in the plugins. The plugins define a lifecycle that is decomposed into seven skills — one orchestrator (stride-workflow) and six sub-skills that handle individual phases (stride-claiming-tasks, stride-completing-tasks, and so on). The sub-skills exist because each phase has a non-trivial API contract that the agent has to get exactly right. The plugins also contain four subagents and a hook designed to execute developer defined commands at specific times during the lifecycle of the work.
Context Matters
At the AI Coffee Chat this past Wednesday we were having a great conversation about how to minimize the overall context that your Agent uses and what happens as the context gets full. I will not go into the details here of what the Agent context is and why it is important to not fill it up with unnecessary things. In the Chat session, I made the statement that a great way to minimize context usage is to understand the core thing you are asking your Agent to do and try to move everything else out to SubAgents, Hooks, or Skills.
Stride Goes Multi-Platform: Copilot, Gemini, and Zero-Prompt Hook Execution
Prior to today, Stride had excellent support for Claude Code via six Skills and four SubAgents. All other agents were only provided with Skills without the enforcement and additional capabilities added by the SubAgents.
Today I shipped three updates that fundamentally change how AI agents interact with Stride. Two new platform extensions bring Stride’s full workflow and support to GitHub Copilot and Google Gemini CLI. And a new Claude Code hooks integration eliminates the most persistent friction point that still existed in the Claude Code agent workflow: permission prompts.
The future of software engineering: My Thoughts - Part 2
This is part 2 in a series where I discuss my thoughts on the Thoughtworks retreat report titled The future of software engineering. If you haven’t read part 1, I’d encourage you to do so first as it provides a lot of context.
In part 2, I will discuss the second and third categories from the report. Let’s jump right in.
2. The middle loop: a new category of work
The report states “The retreat’s strongest first-mover concept. Nobody in the industry has named this yet.” It goes on to say:
