Run budget-capped client AI agents with OpenAI and n8n data tables

by Alexander Englund ✓ · 4 views · created 2026-10-02 · CRM, AI Chatbot

What this workflow does

This AI workflow has 44 nodes and runs when an HTTP POST request hits its webhook URL (plus 3 other triggers). Along the way it connects OpenAI Chat Model.

How it runs

Trigger: When an HTTP POST request hits its webhook URL (plus 3 other triggers).

1. Settings (Edit Fields (Set)): sets 10 fields: system_message, max_output_tokens, max_iterations…
2. Sweep settings (Edit Fields (Set)): sets 1 field: reservation_ttl_minutes
3. Monthly settings (Edit Fields (Set)): sets 3 fields: keep_months, summary_email_to, summary_email_from
4. Load clients (Data table): get
5. Validate request (Code): runs custom JavaScript code
6. Find open reservations (Data table): get
7. Load last month's ledger (Data table): get
8. Load ledger for period (Data table): get
9. Valid request? (If): checks a condition and branches into true / false
10. Pick stale reservations (Code): runs custom JavaScript code

…plus 28 more steps. See the full node list below.

Services it uses

OpenAI Chat Model

Before you upgrade to n8n 3.0

Nodes used (12)

• Webhookn8n-nodes-base.webhook
• Edit Fields (Set)n8n-nodes-base.set
• Coden8n-nodes-base.code
• Ifn8n-nodes-base.if
• Respond to Webhookn8n-nodes-base.respondToWebhook
• Data tablen8n-nodes-base.dataTable
• AI Agent@n8n/n8n-nodes-langchain.agent
• OpenAI Chat Model@n8n/n8n-nodes-langchain.lmChatOpenAi
• Calculator@n8n/n8n-nodes-langchain.toolCalculator
• n8nn8n-nodes-base.n8n
• Send Emailn8n-nodes-base.emailSend
• Schedule Triggern8n-nodes-base.scheduleTrigger

From the author

Quick overview For agencies and freelancers who run one AI agent for several paying clients. Each client has a monthly budget, a pause switch and its own instructions in an n8n Data table. A run starts only if the client can afford it, and the tokens used are…

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