Démarrage rapide

Tu préfères te lancer directement ? Voici tout ce qu’il te faut pour commencer tout de suite.

Essaie-le : le Playground

1. Ouvre le Playground et connecte-toi.
2. Colle n’importe quel texte comme état.

État d’exemple

Hi, I've been trying to connect my Stripe account for 3 days and the integration keeps failing. I'm losing sales. Please help ASAP.

3. Ajoute une question. Essaie une question Noul : "Does this message express urgency?"

{
  "urgency": {
    "type": "noul",
    "instructions": "Does this message express urgency?"
  }
}

4. Ajoute d’autres questions. Mélange Noul, Choice et Score dans un seul appel et vois tous les résultats d’un coup.

Appelle-le : l’API

1. Récupère ta clé d’API depuis le tableau de bord
2. Envoie une requête POST à l’endpoint de l’API
3. Consulte la Référence de l’API pour tous les détails.

POST https://api.typesafe.ai/v1/systemone
Authorization: Bearer <API_KEY>
Content-Type: application/json

Exemple de commande cURL

curl -X POST https://api.typesafe.ai/v1/systemone \
  -H "Authorization: Bearer $TYPESAFE_API_KEY" \
  -H "Content-Type: application/json" \
  -d @- <<'EOF'
  {
    "state": "Hi, I've been trying to connect my Stripe account for 3 days and the integration keeps failing. I'm losing sales. Please help ASAP.",
    "model": "jev-latest",
    "questions": {
      "urgency": {
        "type": "noul",
        "instructions": "Does this message express urgency?"
      }
    }
  }
EOF

Corps de la requête

{
  "state": "Hi, I've been trying to connect my Stripe account for 3 days and the integration keeps failing. I'm losing sales. Please help ASAP.",
  "model": "jev-latest",
  "questions": {
    "department": {
      "type": "choice",
      "instructions": "Which team should handle this",
      "criteria": {
        "billing": "Payment or subscription issues",
        "technical": "Bugs or integration problems",
        "sales": "Pricing or account questions"
      }
    },
    "frustration": {
      "type": "score",
      "instructions": "How frustrated the customer appears",
      "criteria": [
        "Calm, just stating facts",
        "Frustrated but civil",
        "Very angry, strong language"
      ]
    },
    "is_urgent": {
      "type": "noul",
      "instructions": "The message conveys urgency or time-sensitivity"
    }
  }
}

Corps de la réponse

{
  "model": "jev-1.13.0",
  "answers": {
    "department": {
      "type": "choice",
      "choice": "technical",
      "confidence": 0.78,
      "probabilities": {
        "technical": 0.85,
        "sales": 0.0,
        "billing": 0.15
      }
    },
    "frustration": {
      "type": "score",
      "score": 1.0,
      "confidence": 1.0,
      "legend": {
        "0": "Calm, just stating facts",
        "1": "Frustrated but civil",
        "2": "Very angry, strong language"
      },
      "probabilities": {
        "0": 0.0,
        "1": 1.0,
        "2": 0.0
      }
    },
    "is_urgent": {
      "type": "noul",
      "noul": 1.0
    }
  },
  "usage": {
    "input_tokens": 392,
    "output_tokens": 65
  }
}

Vois la Référence de l’API pour tous les détails.

Code-le : le SDK Python

1. Installe le SDK (nécessite Python >= 3.10).

Avec pip

pip install typesafe-sdk

Avec uv

uv add typesafe-sdk

2. Utilise le SDK. Le client lit TYPESAFE_API_KEY dans l’environnement et appelle jev-latest par défaut.

from typesafe_sdk import Choice, Noul, Score, TypeSafeClient

client = TypeSafeClient()

ticket = "Hi, I've been trying to connect my Stripe account for 3 days and the integration keeps failing. I'm losing sales. Please help ASAP."

response = client.system_one(
    state=ticket,
    questions={
        "department": Choice(
            instructions="Which team should handle this",
            criteria={
                "billing": "Payment or subscription issues",
                "technical": "Bugs or integration problems",
                "sales": "Pricing or account questions",
            },
        ),
        "frustration": Score(
            instructions="How frustrated the customer appears",
            criteria=[
                "Calm, just stating facts",
                "Frustrated but civil",
                "Very angry, strong language",
            ],
        ),
        "is_urgent": Noul(
            instructions="The message conveys urgency or time-sensitivity",
        ),
    },
)

print(response.answers["department"].choice)  # "technical"
print(response.answers["frustration"].score)  # 1.0
print(response.answers["is_urgent"].noul)     # 1.0

Vois les SDK clients pour les options d’installation et un usage détaillé.

Fais-le au vibe : le skill d’agent

1. Installe le skill TypeSafe avec le plugin Claude Code ou npx skills add typesafe-ai/skills --skill typesafe-ai. Tu peux aussi lire SKILL.md sur GitHub.

claude plugin marketplace add typesafe-ai/skills
claude plugin install typesafe@typesafe-ai

npx skills add typesafe-ai/skills --skill typesafe-ai

Install the TypeSafe skill. If you're in Claude Code, run `claude plugin marketplace add typesafe-ai/skills`, then `claude plugin install typesafe@typesafe-ai`. If you're in another agent, run `npx skills add typesafe-ai/skills --skill typesafe-ai` and select your agent. Use one installation method. You can read the skill directly at https://github.com/typesafe-ai/skills/blob/main/skills/typesafe-ai/SKILL.md (raw: https://raw.githubusercontent.com/typesafe-ai/skills/main/skills/typesafe-ai/SKILL.md). Then use the TypeSafe skill when working on this project.

2. Dis à ton agent de codage d’utiliser le skill TypeSafe pendant que tu construis !

Prompt pour l’agent de codage

Let's build a simple CLI that uses the TypeSafe API to evaluate a set of supplied documents on multiple dimensions. Use the TypeSafe skill to understand how to use the TypeSafe API and how to structure the system. Ask me questions about what kinds of documents I want to evaluate and on what dimensions.

Vois la page Skill d’agent pour plus de détails.