U
Protocol

Unauthenticated AI Integration

Connect Unauthenticated to BeforeQuery for grounded AI answers and agent actions across Protocol.

Connect Unauthenticated
What is it?

About Unauthenticated

Unauthenticated is one of the Protocol platforms BeforeQuery connects to. Once linked, the platform's data becomes a first-class source for grounded AI answers and a target for policy-gated agent actions — the same identity, approval, and audit-log guarantees every other integration ships with.

Setup

How to connect Unauthenticated

  1. Step 01

    In the BeforeQuery dashboard, go to Integrations → Protocol and select Unauthenticated.

  2. Step 02

    Sign in to Unauthenticated with an account that has permissions to grant BeforeQuery the Protocol scopes required.

  3. Step 03

    Confirm the connection. Unauthenticated is now available as a source and action target for every playbook in your workspace.

Explore

Related integrations

MS
MCP Server OAuth2

MCP Server OAuth2 is one of BeforeQuery's Protocol integrations. Connect it once and every agent in your workspace can read, reason over, and act on MCP Server OAuth2 data with your policies + audit trail.

PA
Private API

Private API is one of BeforeQuery's Protocol integrations. Connect it once and every agent in your workspace can read, reason over, and act on Private API data with your policies + audit trail.

How BeforeQuery uses Unauthenticated

What the agent does with your Unauthenticated connection

  • 01

    Extend BeforeQuery to any system that speaks Unauthenticated, without a hand-written connector.

  • 02

    Bidirectional: read from and write to Unauthenticated-compliant services from any playbook.

  • 03

    Bring your own AI clients — expose BeforeQuery via Unauthenticated so external tools can query the Context Graph.

  • 04

    Long-tail coverage: reach the systems no vendor built a connector for yet.

Use cases

What teams actually do with the Unauthenticated integration

Bring your own client

Any Unauthenticated-compatible AI IDE or chat tool can query BeforeQuery for grounded answers. Cursor, Windsurf, Claude Desktop, any custom client — all speak Unauthenticated, all get the same grounded retrieval + citations.

Connect the long tail

Your internal tool speaks Unauthenticated but no BeforeQuery connector exists. Point BeforeQuery at the endpoint, describe the schema, and playbooks can read + write against it — no code required.

Federate agents

Multi-agent workflows across teams or vendors, connected via Unauthenticated. Each agent stays sovereign; the protocol coordinates.

Answer questions grounded in Unauthenticated

Employees and customers ask Unauthenticated-related questions in Slack, Teams, or the widget — BeforeQuery answers with the exact Unauthenticated record shown alongside the response. No context switching, no "log into Protocol to check" round-trips.

Unauthenticated — Frequently Asked Questions

Common questions about connecting BeforeQuery to Unauthenticated.

Every compliant client. BeforeQuery's Unauthenticated surface is standards-conformant — if your client speaks the spec, it works. No client-specific configuration required.
Standard OAuth 2.0 where Unauthenticated supports it, otherwise API-key or bearer-token auth. Credentials are stored encrypted at rest (AES-256-GCM) per workspace, never shared across customers, and rotated on request. The connection is scoped to the least-privilege set of scopes each playbook needs — you approve the scope list on install.
No. Your Unauthenticated data feeds only your workspace's own agents and answers. Nothing is used to train a shared model, and nothing crosses workspace boundaries. Bring-your-own-model is available on Enterprise if you want to pin inference to your own OpenAI / Anthropic / self-hosted deployment.
Yes. Every Unauthenticated integration is scoped at install time — you pick which resources, users, or record types are visible. You can further restrict per-playbook: a single playbook only touches the specific Unauthenticated objects it needs. Scope changes take effect on the next sync.
Every write is logged with the acting user, the playbook that fired it, the exact operation, the target entity IDs, and the timestamp — all in the immutable audit log. Writes are rehearsable in simulation mode against a copy of live data before they touch Unauthenticated for real.

Ready to connect Unauthenticated?

Start free. No credit card required. Connect your first integration in under 5 minutes.

Get started free