Skip to content
ExpertEnterpriseChatbots & Conversational AIWebhook trigger31 nodes

Run an assistant workflow: Notion + AI agent

Fires the moment a webhook arrives across Notion, Microsoft Teams and Google Sheets, looks the answer up in a vector store, then hands the decision to an AI agent. Built for faq bots, around a "Normalize Conversation Payload" step, in 31 documented nodes.

Run an assistant workflow with Microsoft Teams and log the results. An original, ready-to-import n8n workflow built around the 'AI Agent' pattern for customer support. It fires on a webhook and orchestrates 31 nodes across Notion, Microsoft Teams, Google Sheets. It uses n8n's LangChain AI nodes (Agent/Chain + chat model). Retry-on-fail is enabled on external calls. Import the JSON, add your credentials, and adapt the parameters. Your team sees the right data at the right time.

Key benefits

  • Keeps Notion and Microsoft Teams in step for faq bots, without anyone re-typing a row
  • Safe to re-run: records already in Notion or Microsoft Teams are skipped, across all 31 nodes of this faq-bots build
  • A failed Notion or Microsoft Teams call is retried rather than dropped, at any of the 31 nodes in this faq-bots build
  • Every faq-bots run leaves an audit row behind, alongside Notion
  • The faq-bots AI step is isolated from Notion, so models swap without touching the other 31 nodes

Use cases

  • Teams keeping Notion and Microsoft Teams aligned by hand for faq bots
  • Answering faq-bots questions from your own indexed documents, then replying in Notion
  • Faq bots work that needs a judgement call per item before it reaches Notion
  • Pushing faq-bots events into Notion and Microsoft Teams the moment they land, not on the next poll

Integrations

NotionMicrosoft TeamsGoogle SheetsHTTP / REST APIAnthropic

Workflow preview (31 nodes)

The template's actual node layout and connections. Node parameters and credential slots unlock with the download.

Receive Inbound WebhookWebhookNormalize Conversation …CodeAnswer from Knowledge B…AgentAnthropic Chat ModelLm Chat AnthropicKnowledge Base RetrieverVector Store QdrantQuery EmbeddingsEmbeddings Open AiRerank Retrieved ChunksReranker CohereGrounded Answer Found?IfReturn Answer (HTTP 200)Respond To WebhookLog Knowledge GapGoogle SheetsFlag Gap to KB OwnersMicrosoft TeamsFingerprint for Idempot…CodeDrop Already-Processed …Remove DuplicatesSerialize Run Output (C…Convert To FileArchive Row SnapshotNotionOffload to Post-Process…Execute WorkflowRecord Sub-workflow Res…Execution DataLoad Previous SnapshotGoogle SheetsCompute Drift vs Snapsh…CodeEnrich with Reference D…Http RequestFold In Enrichment Fiel…SetStamp Completion TimeDate TimePersist Run MetadataExecution DataSort Conversations Newe…SortCap Batch VolumeLimitSummarize Run StatsSetAppend Audit Row (Notio…NotionSend Summary to Microso…Microsoft TeamsCapture Failure ContextSetEscalate Failure to Mic…Microsoft TeamsPark in Dead-Letter Que…Notion

What's inside (31 nodes)

A look at the node types this workflow uses. No purchase required — full parameters and credentials are yours after you buy.

AgentCodeConvert To FileDate TimeEmbeddings Open AiExecute WorkflowExecution DataGoogle SheetsHttp RequestIfLimitLm Chat AnthropicMicrosoft TeamsNotionRemove DuplicatesReranker CohereRespond To WebhookSetSortVector Store QdrantWebhook

Agent tools included (1)

An AI Agent is only as capable as the tools wired into it. These are read from the template's own graph — every one is a real node in the file you download.

  • Knowledge Base Retriever · Vector Store Qdrant

This agent runs without conversation memory - each run starts from the incoming request.

From download to running in 3 steps

  1. 1
    Import. In n8n, open Workflows → menu → “Import from File” and pick the downloaded JSON.
  2. 2
    Connect. Add your own credentials on the app nodes - n8n highlights exactly which ones need them.
  3. 3
    Activate. Run it once to test, then toggle Active. The automation is live.

What you'll learn

Architect level

The deepest tier - sub-workflow delegation, state snapshots, and full observability.

  • Moving data between Google Sheets, Microsoft Teams and Notion in a single run
  • Normalising timestamps before anything downstream compares them
  • Adding retries and an explicit error path to external calls

Every node carries its own documentation on the canvas, plus notes explaining why the architecture was built this way, a credential setup guide, troubleshooting, and three practice exercises. Sample data comes pinned to the trigger, so you can hit Execute and watch data flow before connecting a single account.

Common questions

What exactly do I get?

The complete, ready-to-import n8n workflow as a JSON file, delivered instantly after payment. Import it into your own n8n (cloud or self-hosted), add your credentials, and it runs.

How do I import it into n8n?

In n8n, open Workflows, click the three-dot menu, choose “Import from File”, and select the downloaded JSON. Then connect your own app credentials on the highlighted nodes.

Do I need anything else for it to work?

You need your own n8n instance and accounts/credentials for the apps this workflow connects to (Notion, Microsoft Teams, Google Sheets, HTTP / REST API). No coding is required.

What if it doesn't work for me?

If the file is faulty, won't import, or isn't as described, contact us within 7 days and we'll fix it or refund you - see our refund policy.

Can I modify or resell it?

You can freely adapt and use it in your own or your clients' projects. Reselling or redistributing the template file itself is not permitted.

Original n8n workflow template created and owned by WorkflowCrate. After purchase you receive the ready-to-import JSON file and a license to use and adapt it in your own projects.