ai control tower agent and call query tool and google big query
Configured with Agent, Chat Trigger, Execute Workflow Trigger, Google Big Query, and additional nodes. Review the connections and setup before adapting this template.
Node categories in this workflow
- AI & models
- Subworkflow
- Data store
- Trigger
- Code
Icons describe general node roles, inferred from node types. Inspect the parameters for the configured action.
Drag to pan; use + and − to zoom. Reconstructed from the exported node positions; nothing runs here. Dashed lines represent non-main connections. Full node names and notes appear below.
How it works
The exported workflow contains the following configured nodes. Their connections are shown above; inspect the JSON for the complete logic, expressions, and external actions.
| Node | Category | Type | Operation |
|---|---|---|---|
| OpenAI Chat Model | AI & models | OpenAI Chat Model | See node parameters |
| AI Control Tower Agent | AI & models | Agent | See node parameters |
| Call Query Tool | Subworkflow | Tool Workflow | See node parameters |
| Query Database | Data store | Google Big Query | See node parameters |
| Trigger Executed by the AI Tool | Trigger | Execute Workflow Trigger | See node parameters |
| Sanitising the Query | Code | Code | See node parameters |
| Chat Memory | Data store | Memory Buffer Window | See node parameters |
| Chat with the User | Trigger | Chat Trigger | See node parameters |
Setup
- Download the JSON and import it into an isolated n8n instance. Leave the workflow inactive.
- Connect your own credentials through n8n’s credential store. Replace
REPLACE_WITH_*values with your resource identifiers. - Inspect API destinations, Code nodes, database queries, file paths, and outbound actions.
- Run with synthetic data and harmless destinations. Enable triggers only after checking the actual outputs.
Requirements
An n8n instance with the listed node types and compatible versions. Service-connected workflows may require accounts, credentials, or paid APIs.
Credential types declared in the source
None declared. HTTP requests and Code nodes may still need configuration.
Workflow notes
1. Workflow Trigger with Chat
1. Workflow Trigger with Chat
This workflow uses a simple chat window as a trigger. You can replace it with Telegram, Slack, Teams or a webhook trigger linked to your chat.
How to setup?
Nothing to do.
2. AI Agent equipped with the query tool
2. AI Agent equipped with the query tool
In order to have more control on the input of the BigQuery node, we don't use the BigQuery tool. Instead we have a set of nodes to retrieve the SQL query, clean it and send it to a BigQuery Node.
How to setup?
- AI Agent with the Chat Model:
- Add a chat model with the required credentials (Example: Open AI 4o-mini)
- Adapt the name of your BigQuery table in the system prompt (Example: transports.shipments)
- Adapt the tables fields explanation in the system prompt Learn more about the AI Agent Node
- Copy and past the nodes in the yellow sticker in another workflow. Point the query tool to this workflow. Learn more about the Custom n8n Workflow Tool node
3. Big Query Workflow
3. Big Query Workflow
Execute the SQL query generated by the AI agent in Big Query. Retrieve the results and send them back to the AI Agent.
How to set up?
- Paste these nodes in a separate workflow so you can use it with multiple agents.
- Google BigQuery API:
- Add your Google Translate API credentials
- The project in which your table is located Learn more about the Google BigQuery Node
4. Do you need more details?
4. Do you need more details?
Find a step-by-step guide in this tutorial 🎥 Watch My Tutorial
ai control tower agent and call query tool and google big query
ai control tower agent and call query tool and google big query
Purpose and structure
This folder contains the ai control tower agent and call query tool and google big query workflow. Its executable nodes use agent, chatTrigger, code, executeWorkflowTrigger, googleBigQuery, lmChatOpenAi, memoryBufferWindow, toolWorkflow. The table and connection map below are derived from the JSON, not an inferred guarantee of behavior.
Setup
Import inactive. Configure your own credentials and replace REPLACE_WITH_* values. Review external destinations and Code nodes before running.
Entry points
Trigger Executed by the AI Tool, Chat with the User
Verification
Sanitized source candidate; not runtime-tested. This overview is generated from node metadata. Read the folder README for the connection map, credential types, and license.
Attribution
https://github.com/Zie619/n8n-workflows/blob/94007c1445d9258a7da116646b79473e7c7c3282/workflows/Googlebigquery/0806_Googlebigquery_Stickynote_Automate_Triggered.json MIT; preserve source notices.