Agents can do anything.They still need you to decide
Introducing crafters.ai, the human-in-the-loop engine for AI work.
More of your agents' output, at the quality you'd sign.
You've managed to put so much intelligence to work.
Your human attention is now the bottleneck.
Let's empower you to make the most of it
Twelve AI sessions stream walls of text. One ends with four decisions whose context is buried two screens up; answering them carefully takes so long that more sessions keep asking, and the queue never ends. With Crafters, each question lands on the work it is about, with its context: a product page, a checkout, a slide, an email, a code diff. You decide in place, collect your decisions, and send them all at once; every agent goes back to work.
Any agent. Any craft.One place to judge
- Claude Code
- Codex
- Specialist agents
- Any model
- Scripts
- Product
- Data
- Deck
- Campaign
- Contract
- Film
Decide once.Everything downstream knows
- Screens follow it
- Tests assert it
- Agents inherit it
- Next arc starts from it
- Foreman guards it
Ask less, every time.Autonomy is earned
Your picks become rules. Rules become checks.
Everyone on the same canvas.People and agents, live
Your machine.Your keys stay on it
Every identity, repo and key you connect stays local. Each arc sees only its slice.
Shipped isn't done.It keeps watching
- DecidedBottom bar on phone
- ShippedArc 12 merged
- HeldDay 3
- HeldDay 9
- DriftedChange #538 moved it back. One point for you.
The whole vision.Shipped in arcs
We build Crafters with Crafters. Here is what you get, and when.
- The studio, on your machine
- Points pinned on the work, a tour, keyboard triage
- Decide, defer, gate, in place and in batches
- UI lab: judge screens before they're built
- Claude Code and Codex, your own subscriptions
- Every decision on record
- Schema and logic labs: data and flows, judged before the build
- Phone companion: triage from anywhere
- Live multiplayer, people and agents
- One feed across every arc
- Earned autonomy: picks become checks
- Every craft: decks, campaigns, contracts, writing, games
- Context hub: your mail, docs and chats, scoped per arc
- The foreman, watching decisions after they ship
- Always on: a hosted daemon, if you want one
- Declare a craft: the studio renders it. Plugin marketplace
Not fewer humans in the loop.Humans at full bandwidth
AI made execution unlimited. It did not make our judgment any faster. Judgment is what lets our intent shine through in what we craft. AI hands us an endless block of marble; judgment is the chisel.
Today we and our agents talk to each other mostly in text. They describe the work instead of showing it, with the questions that need us buried in paragraphs. We answer by describing our feedback instead of placing it where it belongs, right in the work. Our attention goes into translation, not judgment. And attention is now the scarcest thing in the loop.
So we judge too late. We review the finished work, where every objection costs a rebuild, and where there is too much to catch anyway. We skim, we tire, we let things slide. That is how slop ships, and how intent gets lost.
We think judgment belongs during the build, on the artifacts that come before it: the screens, the data, the flows, the rules. That's where a decision is still cheap. AI should do the legwork to get us there: show the work, bring us to the exact spot that needs a call, with the options and its pick, and let us answer in place, in batches.
Not fewer humans in the loop. Humans in the loop at full bandwidth, deciding while it still matters, and understanding what gets built and why.
Only what needs you
A private beta for polymath crafters. We'll write once, when your seat is ready.