Manage Google and Trustpilot reviews with OpenAI and Slack
Needs changesWhat this workflow does
This AI workflow has 19 nodes and runs on a schedule (every hour) (plus 1 other trigger). Along the way it connects OpenAI Chat Model and Slack. It also calls mybusiness.googleapis.com and api.trustpilot.com over HTTP.
How it runs
Trigger: On a schedule (every hour) (plus 1 other trigger).
- Fetch Google Reviews (HTTP Request): calls mybusiness.googleapis.com
- Fetch Trustpilot Reviews (HTTP Request): calls api.trustpilot.com
- Notify Ops (Slack): uses Slack
- Combine Sources (Merge): merges the data from its input branches
- Dedupe New Reviews (Code): runs custom JavaScript code
- Any New Reviews? (If): checks a condition and branches into true / false
- Process Each Review (Loop Over Items (Split in Batches)): loops over the items in batches
- Draft Reply (AI Agent) (AI Agent): runs an AI agent, with model: OpenAI Chat Model; output parser: Structured Output Parser
- Negative Review? (If): checks a condition and branches into true / false
- Escalate to Owner (Slack): uses Slack
…plus 3 more steps. See the full node list below.
Services it uses
HTTP calls to: mybusiness.googleapis.com, api.trustpilot.com
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 Draft Reply (AI Agent) (v1.7): 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 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) Draft Reply (AI Agent) (v1.7) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (12)
- Schedule Trigger
n8n-nodes-base.scheduleTrigger - HTTP Request
n8n-nodes-base.httpRequest - Merge
n8n-nodes-base.merge - Code
n8n-nodes-base.code - If
n8n-nodes-base.if - No Operation, do nothing
n8n-nodes-base.noOp - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - AI Agent
@n8n/n8n-nodes-langchain.agent - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - Slack
n8n-nodes-base.slack - Error Trigger
n8n-nodes-base.errorTrigger
From the author
Quick overview This workflow runs hourly to fetch new Google Business Profile and Trustpilot reviews, deduplicates them, uses OpenAI via a LangChain agent to draft sentiment-aware replies, escalates negative reviews in Slack, and routes positive replies to…