Built for one task.
A model that only knows your task can be small and fast.
The easiest way to own your AI models.
Facet builds, runs and improves a custom AI model for your product.
Open in
@Facet every email our users get goes through a frontier model to decide if it needs a reply. It is most of our AI bill. Can you build a model for it?
reply-check reads one email and returns whether it needs a reply, who it is from and what they ask.
Up to $9, about 20 min.
Building reply-check v1. I'll post here when it's live.
@Facet it missed a question buried in a forwarded thread. Those need a reply.
I added an eval: Catches asks inside forwarded threads. v1 gets 3 of 20 right on it.
The fix is 40 new examples and a retrain. Up to $3, about 6 min.
client.chat.completions.create(
model="reply-check",
messages=[email],
)A model that only knows your task can be small and fast.
Approve a price and step away.
Every correction makes the next version better.
Frontier labs build one model for everyone. Facet builds yours.
Read the essayFacet, made by Halfspace, builds a custom AI model for a task your product repeats, such as reading every email or routing every support ticket. You describe the task in plain words and Facet does the rest. The model is small, so each call costs less than the same call on a large frontier model. You call it with the OpenAI SDK, and Facet keeps it right as you correct it.
Facet is for narrow text tasks that run often, such as routing tickets, extracting fields, sorting text into categories, redacting personal data, rewriting in a house style, or grading text against your rules. Facet handles text today.
No. A few real inputs help, but Facet writes the instructions and the examples itself. You describe the task and agree on what a good answer looks like, and you can open and edit anything Facet wrote.
Yes. Facet has an MCP server at https://facet.halfspacelabs.com/mcp that works with Claude, Cursor, ChatGPT, Codex and VS Code, so your agent can build a model, ask for fixes and call it, while you approve anything that costs money.
Every account starts with $15 of free credit, once, with no expiry: it pays for drafting, training and calls. After that, calls cost from $0.04 per million input tokens, every build is quoted before it starts, and most first versions cost $1 to $3. Every rate is on https://halfspacelabs.com/pricing.
No. Every build shows its price before it starts, and that price is a cap it never goes past. A monthly spending limit, on by default, stops new work and calls when it's reached; Facet emails your workspace's Owners as spend nears it, and an Owner can raise it.
Yes. Export it any time, free, with its model files and instructions in a standard open format, and run it on your own servers.
Facet is open to invited teams first. Join the waitlist at https://halfspacelabs.com/waitlist with the task you have in mind, then sign in with the email we invite.