Notes from the build
Ideas to innovate, and lessons we've learned while using it to build the platform.
Release v1.8.0: Two instruments, one studio
Codex CLI now runs inside Frontier the same way Claude Code does, and wiring up either one is a single step you can redo whenever you like. Same workspaces, same agents, same memory. Your choice of instrument.
Release v1.7.1: A quieter kind of motion
The website's scroll animations get simpler, section labels get a small flicker of static as they arrive, and the wordmark loses a little weight. Nothing new to learn — everything just moves better.
Release v1.7.0: Thirteen real places to start
Every example on the site now applies against a service you already have an account with. Two fixes in flight never collide anymore. And the wordmark has a small new mark.
Release v1.6.1: The handshake that never happened
A small release with two changes: the bridge between Frontier and your terminal was missing a piece in the v1.6.0 installers, and trying an example from the website now asks where you want it.
Release v1.6.0: Meet Frontier
A new name for the same idea, a link you can click from the website that builds a working setup inside the app, and four examples to start from.
Release v1.5.0: Bring your work with you
Pull any repository off GitHub without touching a terminal, find your way around a screen you have never opened before, and start the thing an empty list is asking you to start.
Release v1.4.0: One timeline for everything that happened
A single feed of every conversation, change, and memory across your entire setup, a revision history that remembers what a workspace used to be, and macros you can drop into a message just by typing a curly brace.
Release v1.3.0: The parts you never see, working harder
A new foundation under every workspace and thread, replay you can actually read, and a handful of rough edges sanded down.
Release v1.2.0: Replay any message, and a few blind spots closed
This release lets you replay a single message's tool calls instead of a whole thread, fixes a workspace with more than one repo only exposing the first one, and makes scheduled runs recover instead of silently dropping a message.
How to work on 10 things at once (or more)
A roadmap workspace and one Conductor agent can carry ten separate improvements through their own build-review-merge cycle, one after another, so the only thing left for you to do is add the next item to the list.
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 v1.1.5: 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 v1.1.0: 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.
Release v1.0.0: A front door, and everything real behind it
Frontier's first tagged release: a public home on the web, an identity that syncs across machines, and real logins, downloads, and email delivery in place of every placeholder that came before.
Can you use more than one AI CLI in the same project?
Frontier 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.
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.
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 Frontier
Why I built a place for your ideas to keep moving, instead of one more chat window that forgets everything overnight.