Notes from the build
Ideas to innovate, and lessons we've learned while using it to build the platform.
Build a product team that didn't exist yesterday
Nobody hands you a Product Lead or a roster of Feature Engineers pre-cast. Imagine who you'd actually want running point, then write them into being.
Release v0.33: A smoother handshake, and a subscription that finally adds up
This release makes sure a brand-new context actually gets Claude Code wired up from the start, fixes extra contexts showing the wrong plan, and adds a quiet nudge when a new version is ready.
Loop engineering: the real skill isn't the prompt, it's the loop
A single great prompt gets you one good answer. A well-designed loop — with its own trigger, interval, and exit condition — gets you a process that keeps working after you've stopped watching.
Release v0.32: A sturdier lock, and a few loose ends tied up
This release closes a real local-tampering gap in your plan and usage limits, fixes two DocViewer regressions, brings a shared visual flourish to the client app, and folds the Status Report hub's scratch workspace into something more permanent.
Why good ideas get shelved before anyone decides they're bad
Most ideas aren't rejected for being bad — they're rejected on a cost estimate, and the real measure of a new tool is how many of those estimates it quietly proves wrong.
Can you use more than one AI CLI in the same project?
DF Code never hard-codes which AI CLI an agent runs — pick one as the install-wide default, then override it per workspace, so one project's Reviewer can run on a different tool than its Engineer without rebuilding anything.
How to know what happened across every project overnight — without opening any of them
A scheduled agent can quietly check every workspace you're running and leave one digest waiting for you, so catching up stops meaning opening ten different projects one at a time.
What comes after the IDE?
An IDE was built around one assumption — one person, at one keyboard, working on one file at a time — and that assumption, not the editor itself, is the first thing worth questioning.
Release v0.31: Real logins, real downloads, and a place to ask questions inside your own docs
This release swaps placeholders for the real thing across the board — real GitHub login, real desktop installers, real email delivery — and lets you ask a question about a specific passage in a doc without leaving it.
How to save a multi-agent setup so you're not rebuilding it every time
A Strategy captures a set of agent roles once — triggers, prompts, and workspace scope included — so a pattern like Watcher/Addresser or Engineer/Reviewer can be instantiated again with one call instead of rebuilt by hand.
Release v0.30: A front door, and a sturdier foundation
This release gives DF Code a public home, a way to back up your whole setup, and a friendlier on-ramp for anyone starting fresh.
How to stop starting every morning triaging the same GitHub issues
A scheduled agent can check your repo for new issues on its own, then hand each one through a triage-reproduce-fix pipeline of its own threads — so the chore that used to eat the first twenty minutes of your day happens before you've opened your laptop.
Why "save time" is the wrong way to think about AI
Every generation gets tools that make the old work faster — the real question is what work becomes possible that wasn't before.
The assistant that remembers your research
Long research threads lose their best insights to scroll-back. Give the good parts a permanent home.
Watch the feedback, so you don't have to
A Watcher/Addresser pair turns pull request comments into fixes before you've finished your coffee.
A co-founder for your side project
Solo builders rarely have someone to push back on their own work. An Engineer/Reviewer pair fills that gap.
Five ideas, one afternoon
Why exploring a fork in a decision is cheaper than arguing about it — just build both and see.
Domains: giving every agent a memory it can trust
A place for what your codebase has already taught you, so no agent has to learn it twice.
The Conductor pattern: one agent that never writes code
How one agent keeps an entire roadmap moving forward — without ever opening a single file.
Introducing DF Code
Why I built a place for your ideas to keep moving, instead of one more chat window that forgets everything overnight.