Templates / WhatsApp expense tracker with PostgreSQL database & AI-powered reports

WhatsApp expense tracker with PostgreSQL database & AI-powered reports

Needs changes

by Roshan Ramani ✓ · 3,065 views · created 2025-05-17 · Personal Productivity, AI Chatbot

Needs changes. This template uses 1 thing(s) that n8n 3.0 removes: AI Agent v1 (old agent modes). 1 breaking item(s) found. Static check, last run 2026-10-19.

What this workflow does

This AI workflow has 45 nodes and runs on a schedule (every day) (plus 1 other trigger). Along the way it connects OpenRouter Chat Model, Postgres and WhatsApp Business Cloud.

How it runs

Trigger: On a schedule (every day) (plus 1 other trigger).

  1. Build Daily Report Query (AI Agent): runs an AI agent, with model: OpenRouter Chat Model
  2. Message Intent Classifier (AI Agent): runs an AI agent, with model: OpenRouter Chat Model; 1 tool (Date and time)
  3. Transform Custom Query for Postgres (Code): runs custom JavaScript code
  4. Route by Intent (Switch): routes items into branches
  5. Execute Daily Report Query (AI Agent): runs an AI agent, with model: OpenRouter Chat Model; 1 tool (Postgres); output parser: Structured Output Parser
  6. Build Custom Report Query (AI Agent): runs an AI agent, with model: OpenRouter Chat Model; 1 tool (Date and time)
  7. Parse & Validate Transaction (AI Agent): runs an AI agent, with model: OpenRouter Chat Model; 1 tool (Date and time); output parser: Structured Output Parser
  8. simple conversation (AI Agent): runs an AI agent, with model: OpenRouter Chat Model; 1 tool (Date and time)
  9. Build Daily Financial Summary (AI Agent): runs an AI agent, with model: OpenRouter Chat Model; 1 tool (Calculator)
  10. Transform Custom Query for Postgres (Code): runs custom JavaScript code

…plus 13 more steps. See the full node list below.

Services it uses

OpenRouter Chat ModelPostgresWhatsApp Business Cloud

Before you upgrade to n8n 3.0

1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:

  • AI Agent v1 (old agent modes) in Message Intent Classifier (v1.9), Parse & Validate Transaction (v1.9), Build Confirmation Message (v1.9)…: replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.

Rather not rewrite it? Many of these flows can be rebuilt in Make (free plan).

Removed in 3.0Replace with
AI Agent v1 (old agent modes)
Message Intent Classifier (v1.9), Parse & Validate Transaction (v1.9), Build Confirmation Message (v1.9), Build Daily Report Query (v1.9), Execute Daily Report Query (v1.9), Build Daily Financial Summary (v1.9), Build Custom Report Query (v1.9), Build Custom Financial Summary (v1.9), simple conversation (v1.9)
Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.

Nodes used (14)

From the author

Track Personal Finances with WhatsApp and AI Assistant Transform your WhatsApp into a powerful personal finance command center. This AI-powered workflow converts natural language messages into structured financial data, automates record-keeping, and delivers…

Excerpt from Roshan Ramani's description on n8n.io.

View the original on n8n.io → Check your own copy

Get the weekly “what broke” email

New templates, newly broken ones, and n8n release changes. One short email a week.

Form not loading? Subscribe here.