Product/Agentic context

Give your agent perception of the customer.

Agents cannot read raw events. Agentic context hands an agent a customer's recent activity as JSON or a short narrative, current as of this session.

14 days · no card · no sales call
Your app → Signalstool call
// inside the agent's tool call
const context = await signals.getContext({
  key: { user_id: "u_48213" },
  format: "narrative"
});
Illustrative. Ask through the Python or Node.js SDK, the REST API, or the MCP server from any agent framework.
Signals → your app● 6ms later
{
  "narrative": "Returning customer. Four minutes on the checkout page without progressing. Three failed searches for 'returns policy' this session. Basket of 184.20 has been idle for seven minutes.",
  "attributes": {
    "showing_price_hesitation": true,
    "failed_searches_session": 3
  },
  "as_of": "2026-09-14T09:45:12.088Z"
}
Shaped from the same event streamJSON for tool calls, narrative for a system prompt
The problem

The agent answers well. It knows nothing about the customer.

An agent cannot read raw events, and a CRM record says who the customer is, not what they are doing. So it opens with "how can I help?" while the customer has spent four minutes stuck on one page.

How it works

The same events. Shaped for a model. Read at the moment the agent needs it.

01 · Event in

The same SDKs and the same events that power attributes and triggers.

Nothing extra to instrument. Schema-validated on the way in.

02 · Shaped

Recent session activity becomes a compact context.

Structured JSON for a tool call, or a short narrative a model reads directly. Same source, your choice of shape.

03 · Read

The agent asks mid-conversation and answers with what it now knows.

Python or Node.js SDK, REST API, or the MCP server. Pair it with live attributes so the agent knows both the pattern and the moment.

Capabilities

Recent activity, shaped so a model can use it.

01

JSON or narrative

Structured for a tool call, or written out for a system prompt. Same source, your choice of shape.

02

Current as of this session

Built from the same event stream as attributes and triggers, so it reflects the last few minutes, not last night.

03

Pairs with live attributes

Combine recent activity with computed attributes so the agent knows both the pattern and the moment.

04

Any agent framework

Python and Node.js SDKs, the REST API, or the MCP server. Ask for a customer's context as one tool call.

05

Keyed on any entity

A user, a session, an account or a basket. Whatever the conversation is about.

06

Stays in your cloud

Customer activity never leaves your deployment on the way to the model.

Collect. Define. Serve.

Add the SDK, define one attribute, and watch it change while you click around your own product. 14 days, no card, no sales call.