Signals

A signal is a named time series: a key plus a stream of timestamped values. Signals are the platform's data atoms — every segment, pipeline, forecast, and goal ultimately reads from them.

There is no schema to declare and no create step. Push one value to a new key and the signal exists:

curl -X POST "$API_BASE/v1/signal/push" \
  -H "Authorization: Bearer $TOKEN" \
  -H "X-Workspace-Id: $WORKSPACE_ID" \
  -H "Content-Type: application/json" \
  -d '{ "key": "daily_sales", "value": 12841.5 }'

from predictai import PredictAI

client = PredictAI(token="pa_live_…", workspace_id="ws_…")

data = client.signals.post_signal_push(json={"key": "daily_sales", "value": 12841.5})

import { PredictAI } from "@predictai/sdk";

const client = new PredictAI({ token: "pa_live_…", workspaceId: "ws_…" });

const data = await client.signals.postSignalPush({ json: { key: "daily_sales", value: 12841.5 } });

{ "status": "ok" }

That's it — daily_sales now shows up in /v1/signal, in the segment builder, and in every analysis endpoint.

In this section

Bringing data in at volume — connectors, file uploads, scheduled jobs — lives in Ingestion. Turning signals into the exact table a model trains on is Segments. Training on them is Pipelines; letting the platform find what drives a target is Goals.