ChatGPTMoneyLower billsAI score · 68/100AI-assisted edit · no obvious prompt-injection riskn8n.io

Build a Telegram Financial AI Agent with n8n

Input: Telegram message or Chat trigger → Processing: AI Agent calls transaction/balance tools → Output: Telegram reply and financial report

Some experienceStepsWorkflowTip
Who
Individuals or small businesses who need bookkeeping and already use n8n
You get
Record income/expenses, check balances, and get AI financial advice via Telegram chat
You need
n8n · telegram · postgres · supabase

Constraints

Requires an n8n instance (self-hosted or n8n Cloud with community nodes enabled). Prerequisites: Supabase PostgreSQL database with three tables (transactions, balances, memoria_chat), OpenAI API Key, Telegram Bot Token, and two supporting tool workflows (Register Tool / Balance Tool). The source does not provide the tool-workflow JSONs; obtain or build them separately.

What they did

Author Bruno Dias published a financial AI Agent template on the n8n marketplace. The template receives user messages via Telegram Trigger or Chat Trigger, normalizes them through a Normalize node, and passes them to an AI Agent. The AI Agent uses OpenAI GPT-4.1/GPT-4 as the language model, Postgres Chat Memory for conversation context, and two toolWorkflow nodes (Register Transaction, Balance report) to interact with an external database, finally returning results through a Telegram node.

How it went

The author states the template can automatically record and categorize income/expenses, provide personalized financial analysis and tips, and generate balance reports via Telegram (adaptable to WhatsApp, Instagram, etc.). No quantitative results are provided; the above is an author_report.

Worth knowing

1. The template description requires two supporting tool workflows (Register Tool / Balance Tool), but their JSONs are not included in the current snapshot, creating a core-dependency gap. 2. All node parameters in workflow.json are empty objects; actual operation requires manual configuration inside the n8n editor. 3. Requires self-hosted n8n or n8n Cloud with community nodes enabled. 4. This site has not tested the workflow; reproduction status is not_tested.

n8n workflow template

Structure checked · Not run-tested

Use “Import from File” in n8n, or copy the JSON and paste it into the editor. Connect your own accounts, then try test data. The template is inactive by default.

Download JSONOriginal template

Setup and test checklist

Credentials to connect

  • After import, connect your own credentials on auth-required nodes; author secrets are not included.

Configuration to replace

  • Source template is n8n public workflow #5259 (~9 nodes). Keep inactive after import; verify triggers, expressions and external API endpoints.
  • Sticky-note guidance is informational; replace placeholders with your own accounts, sheet schemas or channel IDs.

Test input and expected output

  • Manually run the main path once in a test workspace and confirm credentialed nodes authenticate without errors.
  • Drive one synthetic/redacted sample through and check output fields and downstream writes before enabling in production.

Template changes

  • Author credential bindings, webhookId and execution data are removed; the workflow is inactive. Nodes, connections and original prompts are preserved. Not run-tested in n8n.
  • No business-logic edits; verify keys, quotas and privacy compliance before use.

Template retrieved: 2026-10-24

Steps

  1. Prepare database and credentials

    Create a PostgreSQL database in Supabase and set up three tables: transactions (for each income/expense), balances (daily/user consolidated balance), and memoria_chat (conversation history). Then configure credentials in n8n: OpenAI API Key, Supabase API Key and URL, PostgreSQL Connection String, and Telegram API Token.

  2. Configure webhook and tool connections

    Set the webhook path in the Telegram Trigger node to receive messages. Ensure the main workflow (Financial | AI Agent) is correctly connected to the two supporting workflows: Financial | AI Agent | Register Tool and Financial | AI Agent | Balance Tool. If the supporting workflows are missing, import them from the n8n template gallery or create them manually.

  3. Import and activate the workflow

    Import the main workflow JSON into n8n and verify node connections: Telegram Trigger / Chat → Normalize → AI Agent → Telegram; AI Agent also connects to OpenAI Chat Model, Postgres Chat Memory, Register Transaction, and Balance report. Activate the workflow and send a test message to the Telegram Bot.

Prompt you can copy

Setup guidance · Editorial suggestion。Give to setup assistant; confirm inputs and permissions first

This block is the prompt. Ads are never placed here.

You are an n8n workflow setup assistant. The user wants to replicate a Telegram financial AI Agent. First confirm whether the user already has: 1) an n8n instance; 2) a Supabase database with the three required tables; 3) an OpenAI API Key; 4) a Telegram Bot Token; 5) the two supporting tool workflows (Register Tool / Balance Tool). If the tool workflows are missing, warn the user that the source template does not include their JSON and they must source or build them separately. Then guide the user to import the main workflow, configure credentials, set the webhook, and test.

Check 5 prerequisites before importing the main workflow; warn if tool workflows are missing.

Source

💰 Financial AI agent Telegram and WhatsApp · brunodias · n8n.io · 2025-06-24

Comments & feedback

Tried this method? Share results, problems or improvements. Comments appear after moderation. Please avoid sensitive information.

Loading…

    Related