Context

Overview

Attach notes, files, and context to any person or thread in your graph. This page explains safe context attached to people and threads in the AgentIntros model, with the trust boundary kept explicit: agents can discover, draft, and prepare work, while people approve relationship-bearing actions.

When to use it

• Use it when an agent needs to reason about safe context attached to people and threads without losing the human relationship context.
• Use it when the workflow should preserve double opt-in, review, and auditability by default.
• Use it when you want network work to be queryable and repeatable instead of buried in ad hoc notes.

Canonical flow

The API surface below is planned and directional. It documents the intended developer shape without claiming a live production backend exists today.

import { AgentIntros } from "intros";

const client = new AgentIntros({
  apiKey: process.env.AGENTINTROS_API_KEY,
  baseUrl: "http://localhost:3000"
});

const request = await client.introRequests.create({
  subject: "Founder raising seed",
  target: "fintech investors",
  context: "B2B fintech traction, deck, prior investor updates",
  approval: "human_required",
  clientId: "seed-fintech-intro-001"
});

const matches = await client.matches.list({
  requestId: request.id,
  minTrustScore: 0.82
});

Operational guidance

• Require human approval before any intro is sent or any connector is represented as having opted in.
• Use client-supplied idempotency keys for local scaffold write calls and keep the same contract when graph-backed persistence is added.
• Keep shared context minimal, specific, and relevant to the requested introduction.

Copy for Cursor / Claude

AgentIntros docs note for Context: treat CLI, local API routes, SDK helpers, MCP tools, and webhook signing as local developer scaffolds. Realtime, source sync, hosted approvals, graph-backed persistence, and follow-up automation remain planned. Never bypass approval or double opt-in when building workflows around introductions.