Want to watch before you enforce? You can install the SDK and observe
every tool call in the decision feed without minting mandates or blocking
anything — then turn on enforcement once you’ve seen the traffic. See
Generalize from observation.
Prerequisites
- An Inviolet workspace (sign up free)
- Node 20+ (or any language — see the REST flow for non-Node stacks)
- Five minutes
1. Sign up + get an API key
Sign up at app.inviolet.ai/sign-up. On first login you’ll see the dashboard’s onboarding panel; pick a scenario (AI-native app dev, AI-assisted workflows, or data governance). Open Developer → API Keys and create a key. Save it asINVIOLET_API_KEY in your env.
2. Install the SDK
@inviolet/agent-sdk-core under the hood, and they all expose the same
Inviolet client:
@inviolet/agent-sdk-anthropic@inviolet/agent-sdk-openai@inviolet/agent-sdk-fetch@inviolet/agent-sdk-langchain@inviolet/agent-sdk-llamaindex@inviolet/agent-sdk-mcp-client
3. Create an intent card
Open Gallery → Intents and click New intent card. Name your purpose, scope the operations + resources, and set a default response strategy (start withdeny; promote to allow_with_redact or defer
later).
Example for a customer-support copilot:
4. Mint a mandate + guard a tool call
Mint one mandate at the start of a session, then guard every tool call against it.There is no first-party Python package — the Python path calls the gateway’s
REST API directly. See the REST reference for every field.
5. Watch it land in the dashboard
Open app.inviolet.ai/dashboard. Within seconds you’ll see your call in the Decision Feed with the full forensic chain — prompt → mandate → tool call → outcome — plus the cascade’s reasoning trail under “Why was this picked?”.What’s next
- Read The 5 Principles to understand the doctrine.
- Set up credential brokering so the agent never holds the real Postgres password.
- Promote your intent card from
deny→allow_with_redactafter a week of shadow-mode observation.