I'm paying for three dedicated AI subscriptions and somehow that's the minimum.

- Claude for thinking and writing.
- GitHub Copilot for cloud agents that run while I review.
- OpenCode for cheaper open models when I want to offload.

Then Perplexity (from a Pro account) for research that actually cites its sources. Gemini (from Google One) for images and calendar integrations.

Each one has one job. None of them do all the others.

Here's what actually changed my workflow: I stopped writing code and started steering it.

My day looks like: describe a feature to Copilot's agent, switch to Claude to plan the next one while it works, come back to review what it built, ask for adjustments, repeat.

The dynamic changed from "I write, AI assists" to "AI writes, I review and direct."

GitKraken 12.0 helped with this too. Agent Mode lets me run multiple coding agents in parallel without terminal gymnastics. One panel shows status for all active sessions. One click spins up a new worktree. One click cleans it up when you're done.

Non-agentic tools haven't changed much: Capacities for notes, TickTick for tasks, Helium Browser for browsing without Google's telemetry, Warp for terminal multiplexing.

The stack works. But I'm aware half of it might not exist in six months.

What's your workflow look like? Still writing most of the code yourself?

#ai #developer #workflow #typescript #freelance

The future of AI productivity is not just better prompts. It is better context, better systems, and a clearer sense of who you are trying to become.

Press enter or click to view image in full size

Photo by Compagnons on Unsplash

Most people use AI like a vending machine.

They type a prompt, get an answer, and move on.

That works for quick tasks. It does not work well for building a serious body of work, a stronger personal brand, or a higher-performance life. If you are trying to become more intellectually sharp, more operationally effective, and more strategic over time, the real edge is not only in prompting. It is in context.

The breakthrough in my workflow came when I stopped treating AI as a collection of isolated chats and started treating it as a context-aware operating environment.

That shift changed everything.

Platforms are increasingly building around memory, project context, shared files, and persistent workspaces. ChatGPT’s Projects are built around project memory and can use prior chats and files inside a project as working context. OpenAI has also expanded project-only memory options for some plans, which makes it possible to keep one stream of work separate from the rest of your broader AI usage. Claude positions itself as a tool for problem solving and collaborative thinking, with Artifacts giving users a dedicated space to iterate on documents, code, and visual outputs. Gemini has been pushing in a similar direction through Gems, Canvas, Deep Research, file uploads, and tight integration with Google Workspace.

This matters because context is how AI stops being a novelty and starts becoming leverage.

...