
Product @CultureAmp. Previously @Atlassian. Future of work, mashups, home brewing, and automation. Opinions my own. he/him. May also use @mindsocket@aus.social
Sydney
Joined June 2009
- Tweets4.6K
- Following1.4K
- Followers1.1K
- Likes2.3K
Roger Barnes retweeted
"Let’s plan the roadmap for next quarter” is the modern day equivalent of “let’s fax everyone the strategy.”
We're going into q4 planning and it makes my brain hurt. Roadmaps existed because software was expensive to build. You needed a bunch of people. Meetings. Someone moving little boxes around Jira for three months from now. It makes no sense and I'm trying to work out what we call the replacement. Maybe just "Continuous Compilation", ideas just compile to working product. I want a list of ideas that we want to continuously compile. That's the roadmap now.
The cheapest way to figure out whether something is a good idea is often to just build the fucking thing.
Here’s how I work now. I've done this weekly over the last few months and it works. My current napkin math is that I can usually build 6 months of old-school roadmap in a week. Sometimes more. I've also hit a wall sometimes. It happens.
When we have an idea, I usually 10x the ambition and then write a prompt, not more than a page long, that basically says:
- here’s the ambitious goal
- here are a few use cases
- here’s roughly how I think we should build it in terms of where it fits into code base, design considerations, etc..
- here’s how we’ll know if it actually works
- now go fucking surprise me
Agents build all night. Not even with a crazy factory or complex agent or agents. The base models are just too good for that now.
In the morning I look at it. Ok, they usually build in a few hours. Usually some of it is great. Some of it is stupid. Some of it exposes that my original idea was wrong.
And almost every time it gives me 5 new ideas I couldn’t have planned upfront. So we throw shit out. Who cares? We learned something.
Then we change direction and send them off again. It usually takes 3 rounds before the shape appears and we've learned about the gremlins and possibilities.
95% of the time I end up building something with 10x the scope of what somebody had carefully spread across the next quarter in Jira.
“What should we put on the roadmap for next quarter?”
My brain now translates that to: “Oh, you're stuck in the 1500s”
Replying to @mattpocockuk
Plan driven development? Your skills are not quite the same as plan mode in Claude Code, but more similar than different.
Replying to @Wayland_Six @NousResearch
You urgently need a different project name, or to at least stop actively avoiding mentioning who you aren't in important places like your web site and bio.
Replying to @NousResearch @karpathy
I'm finding the single wiki config per instance limiting. I have multiple wikis for quite different topics. Config should be at agent and/or directory level. I already map telegram topics to context directories separately.
Replying to @NousResearch @karpathy
I like it! I'm finding the (expected) differences in interpretation of @karpathy 's guidance interesting. I've built flexible but deterministic schema validation with llm skills. I'm working on integrating these as complementary to other skills. github.com/mindsocket/struct…

