Docs
OfficialJev Guides & Articles
Quick Start
Everything you need to make your first request: install an SDK, get an API key, and send state plus typed questions.
- Format
- Docs
- Reading time
- 2 min
- Published by
- TypeSafe AI
- Last verified
- Sep 2026
Works forJev for Scoring
Used inJev for Software & DevTools
Highlights
- POST https://api.typesafe.ai/v1/systemone with a Bearer token; the Python SDK installs via pip install typesafe-sdk and needs Python 3.10+.
- TypeSafeClient reads TYPESAFE_API_KEY from the environment and defaults to the jev-latest model alias.
- Responses echo a concrete model version such as jev-1.13.0 and report usage.input_tokens and usage.output_tokens.
- Score answers include a legend mapping each numeric level back to its criteria text, alongside probabilities and confidence.
Quickstart
python
from typesafe_sdk import Noul, TypeSafeClient
client = TypeSafeClient()
response = client.system_one(
state="My Stripe integration keeps failing. Please help ASAP.",
questions={
"is_urgent": Noul(instructions="Does this message express urgency?"),
},
)
print(response.answers["is_urgent"].noul)Watch out
The Python SDK requires Python 3.10 or newer and reads TYPESAFE_API_KEY from the environment, so the key must be set before the first call.
Questions about this entry
Short answers drawn from the linked project or page.
An SDK install and an API key. The Python SDK installs with pip install typesafe-sdk and needs Python 3.10 or newer, and TypeSafeClient reads TYPESAFE_API_KEY from the environment, so set the key first.
A concrete model version such as jev-1.13.0, usage.input_tokens and usage.output_tokens, and for Score answers a legend mapping each numeric level back to its criteria text, alongside probabilities and confidence.
Open the Playground and log in, paste any text as the state, and add questions; the quickstart mixes a Noul, a Choice, and a Score in one call and shows all results at once.
POST to https://api.typesafe.ai/v1/systemone with an Authorization: Bearer <API_KEY> header and Content-Type: application/json; the API key is created in the dashboard.
A support message about a Stripe integration failing for three days that ends "I'm losing sales. Please help ASAP.", evaluated for department, frustration, and urgency.
Yes. The quickstart's request body carries a Choice for department, a Score for frustration, and a Noul for urgency, and returns a typed answer for each of them.
Use the Claude Code plugin commands, or run npx skills add typesafe-ai/skills --skill typesafe-ai for other agents; installation is project-local by default, and -g installs it globally.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
X: Getting started: install the skill
More Jev resources like this
Guidance on how Jev fits coding agents: it is not a drop-in agent model, so the page routes readers to routing, rubric scoring, and truth checks instead.
Jev Guides & ArticlesDocs#official#docs#coding-agent
Official
The raw HTTP contract behind every SDK: POST a state plus typed noul, choice, and score questions to /v1/systemone, and get one answer per question, with error codes and retry guidance.
Jev Guides & ArticlesDocs#official#docs#api
Official
The idea behind Jev: models that return typed decisions and probabilities instead of generated text, named after Kahneman's fast-thinking System 1, with confidence to route around uncertainty.
Jev Guides & ArticlesDocs#official#docs#architecture
Official
The canonical introduction: Jev is TypeSafe's flagship model and the first System One model. Send state and typed questions, get structured answers your code can use directly.
Jev Guides & ArticlesDocs#docs#official#primitives
Official
The Jev Day release post: Jev 1.14.0 under jev-preview plus three danger-zone features — composable images on both models, the box question type on 1.14 only, and opt-in 262k context.
Jev Guides & ArticlesArticle#official#release#vision
Official
OpenAI's API documentation page for Decisions, a hosted endpoint that returns bounded answers rather than generated text; the captured page is its header, pointing to the docs index at llms.txt.
Jev Guides & ArticlesDocs#community#openai#docs
Community
From the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.