Skip to content
ExpertPremiumAI AgentsWebhook trigger23 nodes

Run an AI agent task: Google Sheets & Telegram

Fires the moment a webhook arrives across Google Sheets, Telegram and Slack, looks the answer up in a vector store, then hands the decision to an AI agent. Built for research assistant, around a "Answer from Knowledge Base" step, in 23 documented nodes.

Run an AI agent task with Telegram in real time for Research Assistant. An original, ready-to-import n8n workflow built around the 'AI Agent' pattern for AI & automation. It fires on a webhook and orchestrates 23 nodes across Google Sheets, Telegram, Slack. 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. The result is a hands-off process that just works.

Key benefits

  • Keeps Google Sheets and Telegram in step for research assistant, without anyone re-typing a row
  • Safe to re-run: records already in Google Sheets or Telegram are skipped, across all 23 nodes of this research-assistant build
  • A failed Google Sheets or Telegram call is retried rather than dropped, at any of the 23 nodes in this research-assistant build
  • Bad input stops the run for research assistant instead of landing in Google Sheets
  • The research-assistant AI step is isolated from Google Sheets, so models swap without touching the other 23 nodes

Use cases

  • Teams keeping Google Sheets and Telegram aligned by hand for research assistant
  • Answering research-assistant questions from your own indexed documents, then replying in Google Sheets
  • Research assistant work that needs a judgement call per item before it reaches Google Sheets
  • Pushing research-assistant events into Google Sheets and Telegram the moment they land, not on the next poll

Integrations

Google SheetsTelegramSlackGoogle Gemini

Workflow preview (23 nodes)

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

Receive Inbound WebhookWebhookRequired Fields Present?IfAbort — Malformed InputStop And ErrorAnswer from Knowledge B…AgentGoogle Gemini Chat ModelLm Chat Google GeminiKnowledge Base RetrieverVector Store QdrantQuery EmbeddingsEmbeddings Google GeminiGrounded Answer Found?IfReturn Answer (HTTP 200)Respond To WebhookLog Knowledge GapGoogle SheetsFlag Gap to KB OwnersSlackFingerprint for Idempot…CodeDrop Already-Processed …Remove DuplicatesLoad Previous SnapshotGoogle SheetsCompute Drift vs Snapsh…CodeSerialize Run Output (C…Convert To FileArchive Row SnapshotGoogle SheetsSummarize Run StatsSetAppend Audit Row (Googl…Google SheetsSend Summary to TelegramTelegramCapture Failure ContextSetEscalate Failure to Tel…TelegramPark in Dead-Letter Que…Google Sheets

What's inside (23 nodes)

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

AgentCodeConvert To FileEmbeddings Google GeminiGoogle SheetsIfLm Chat Google GeminiRemove DuplicatesRespond To WebhookSetSlackStop And ErrorTelegramVector 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

Production level

Production-grade: idempotency, dead-letter handling, and reconciliation included.

  • Moving data between Google Sheets, Slack and Telegram in a single run
  • Failing loudly on a bad run instead of letting it pass silently
  • 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 (Google Sheets, Telegram, Slack). 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.