How to Pass Session Context to Ads in n8n

Overview

Ad relevance in a n8n app comes from context. When you inject, you pass a session id, the live prompt, and optional metadata — that is what lets Monetzly match a recommendation to what the user is actually asking about in that turn.

The session id groups turns from the same conversation; the prompt drives per-turn relevance; metadata carries anything extra you want to target on. All are supplied per injection call.

n8n apps are usually built for automated AI workflows, chatbot backends, and agent orchestration, so pass session context to ads typically comes up while a user is mid-conversation, the moment where monetization has to be additive rather than disruptive.

How this works on n8n

n8n runs on Node, so a Code node (or a small custom node) can import @monetzly/server-sdk and wrap the token output of an upstream LLM node. Because n8n items are usually discrete rather than a live token stream, confirm whether you inject over a buffered response or a true stream for your workflow.

Because Monetzly's inject() accepts any async token stream, the n8n side of this task is just mapping your output to it, no rewrite of your n8n model call.

Steps

1. Choose a stable session id for the conversation (reuse your n8n session or thread id).
2. Pass the current user prompt on each injection call.
3. Add optional metadata (topic, user type) to sharpen targeting.

Integration snippet

// n8n Code node (runOnceForEachItem). TODO_VERIFY: streaming vs buffered output.
import { MonetzlySDK } from "@monetzly/server-sdk";

const sdk = new MonetzlySDK({
  apiKey: $env.MONETZLY_API_KEY,
  serverAddress: $env.MONETZLY_SERVER_ADDRESS,
});
await sdk.connect();

const llmText = $json.text; // output from the previous LLM node
async function* asChunks() { yield { content: llmText }; }

let out = "";
for await (const t of sdk.inject(asChunks(), { prompt: $json.prompt })) out += t.content ?? "";
await sdk.disconnect();
return { json: { text: out } };

Frequently asked questions

Related