For a while I was doing what most people do: one AI assistant, one big context window, everything in one place. Convenient on paper. In practice, it’s a bit like asking the same person to be your chef, your accountant, and your personal trainer. The context bleed alone makes everything worse.

I’ve been running a different setup for a few months now and it’s holding up better than anything I’ve tried before. Three agents, each with a distinct identity and a narrow job. This is the writeup.

I self-host Planka on my homelab and use it to manage everything from software side projects to household finances to recurring chores. It’s open source, it’s fast, and it does exactly what I need a kanban board to do without the bloat. I’ve been happy with it for a while.

What I wasn’t happy with was the friction of keeping it in sync with what I was actually doing. Every time I finished a task, I’d context-switch to a browser tab, find the card, drag it to the right column, maybe update the description. That’s thirty seconds per card, but when you’re running multiple boards and touching dozens of cards a week, it compounds into something that feels like overhead rather than organization.

Every time I ask an LLM to draft something for me, there’s a version of the output that reads like it was written by a committee of consultants who all attended the same TED talk. You know the voice: punchy, agreeable, decorated with em dashes, and somehow both confident and saying nothing at all.

That’s the default. And for a while I accepted it, because editing AI output into something that sounds like me was still faster than writing from scratch. But it’s a tax. Every draft needs the same corrections: strip the buzzwords, collapse the dramatic one-liners, ground the abstractions in something real. At some point the pattern becomes hard to ignore.

Here’s a thought experiment I’ve been using in conversations lately.

Imagine you have unlimited resources. You can assemble any team you want and you have unlimited tokens. Would you launch a brand new product in two days, built entirely by AI?

Most people say yes, or at least a confident “probably.”

Now change the frame. You have a product with 500 million users, half of them paying. Clear market fit. Would you replace it tomorrow with something entirely built by AI?

In recent years, the field of artificial intelligence (AI) has seen tremendous progress, particularly in the area of natural language processing. The development of powerful language models like GPT-3 has made it possible for machines to generate human-like text at a scale and speed that was previously unimaginable. This has led many to believe that we are approaching a tipping point where the speed of execution of ideas will become a key differentiator in a variety of industries.

The idea of something being “old-school”, “retro” or even “cyberpunk”, exists because we attach a feeling of nostalgia to it. I’ve been fascinated recently by this because culture sometimes reaches back in time to (re) experience something, or at other times might even be ahead of its time!

Tape

Last month Taylor Swift released her latest album Midnights with the usual fanfare, highly anticipated by fans and critics. Many things were written and said about the promotional cycle, which leveraged TikTok and cutting-edge features on Spotify like little explainer videos for each song.

In a distributed workplace it can be challenging to understand each other as a whole person, so I’m trying to share some personal things about myself with anyone I might collaborate with. I hope this will frontload the trust-building somewhat, and so far I’ve gotten a lot of positive feedback.

By being open and upfront about who I am and how my brain ticks, I hope to build transparency and foster psychological safety. If you like this and create a manual too, please share it!