Bear Brown
← All N8N workflows
AI & researchAgentAggregateChain LLMCodeFilter

Deep Research Report Generation Using Open Router, Google Search, Webhook/Telegram and Notion

Configured with Agent, Aggregate, Chain LLM, Filter, and additional nodes. Review the connections and setup before adapting this template.

Download workflow JSONView files on GitHub ↗37 nodes · MIT
Workflow preview
TriggerTelegram TriggerTelegram TriggerData storeSimple MemoryMemory Buffer WindowTransformStructured OutputParserOutput Parser StructuredRoutingSwitchSwitchAI & modelsStrategy AgentAgentAI & modelsSearch Query AgentAgentTransformStructured OutputParser1Output Parser StructuredTransformSplit OutSplit OutRoutingLoop Over QueriesLoop Over ItemsWeb / APIHTTP RequestHTTP RequestTransformEdit FieldsEdit FieldsAI & modelsOpenAIOpen AiWeb / APIHTTP Request1HTTP RequestTransformAggregateAggregateAI & modelsAI AgentAgentAI & modelsOpenAI1Open AiIntegrationNotionNotionIntegrationNotion1NotionWeb / APIHTTP Request2HTTP RequestTransformConvert to HTMLMarkdownTransformHTML to ArrayEdit FieldsTransformTags to ItemsSplit OutAI & modelsNotion Block GeneratorChain LLMAI & modelsGoogle Gemini ChatModelLM Chat Google GeminiTransformParse JSON blocksEdit FieldsRoutingValid BlocksFilterRoutingFor Each Block...Loop Over ItemsIntegrationGet Existing RowNotionCodeCodeCodeTransformAggregate1AggregateAI & modelsOpenRouter Chat ModelLM Chat Open RouterAI & modelsOpenRouter Chat Model1LM Chat Open RouterAI & modelsOpenRouter Chat Model2LM Chat Open RouterTriggerWebhookWebhookWeb / APIRespond to WebhookRespond To WebhookWeb / APIRespond to Webhook1Respond To WebhookWeb / APIHTTP Request3HTTP Request

Node categories in this workflow

  • Trigger
  • Data store
  • Transform
  • Routing
  • AI & models
  • Web / API
  • Integration
  • 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.

Workflow node names, types, and operations
NodeCategoryTypeOperation
Telegram TriggerTriggerTelegram TriggerSee node parameters
Simple MemoryData storeMemory Buffer WindowSee node parameters
Structured Output ParserTransformOutput Parser StructuredSee node parameters
SwitchRoutingSwitchSee node parameters
Strategy AgentAI & modelsAgentSee node parameters
Search Query AgentAI & modelsAgentSee node parameters
Structured Output Parser1TransformOutput Parser StructuredSee node parameters
Split OutTransformSplit OutSee node parameters
Loop Over QueriesRoutingLoop Over ItemsSee node parameters
HTTP RequestWeb / APIHTTP RequestPOST
Edit FieldsTransformEdit FieldsSee node parameters
OpenAIAI & modelsOpen AiSee node parameters
HTTP Request1Web / APIHTTP RequestPOST
AggregateTransformAggregateSee node parameters
AI AgentAI & modelsAgentSee node parameters
OpenAI1AI & modelsOpen AiSee node parameters
NotionIntegrationNotiondatabasePage
Notion1IntegrationNotiondatabasePage / update
HTTP Request2Web / APIHTTP RequestPATCH
Convert to HTMLTransformMarkdownSee node parameters
HTML to ArrayTransformEdit FieldsSee node parameters
Tags to ItemsTransformSplit OutSee node parameters
Notion Block GeneratorAI & modelsChain LLMSee node parameters
Google Gemini Chat ModelAI & modelsLM Chat Google GeminiSee node parameters
Parse JSON blocksTransformEdit FieldsSee node parameters
Valid BlocksRoutingFilterSee node parameters
For Each Block...RoutingLoop Over ItemsSee node parameters
Get Existing RowIntegrationNotiondatabasePage / getAll
CodeCodeCodeSee node parameters
Aggregate1TransformAggregateSee node parameters
OpenRouter Chat ModelAI & modelsLM Chat Open RouterSee node parameters
OpenRouter Chat Model1AI & modelsLM Chat Open RouterSee node parameters
OpenRouter Chat Model2AI & modelsLM Chat Open RouterSee node parameters
WebhookTriggerWebhookSee node parameters
Respond to WebhookWeb / APIRespond To WebhookSee node parameters
Respond to Webhook1Web / APIRespond To WebhookSee node parameters
HTTP Request3Web / APIHTTP RequestPOST

Setup

  1. Download the JSON and import it into an isolated n8n instance. Leave the workflow inactive.
  2. Connect your own credentials through n8n’s credential store. Replace REPLACE_WITH_* values with your resource identifiers.
  3. Inspect API destinations, Code nodes, database queries, file paths, and outbound actions.
  4. 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

Workflow Overview

Workflow Overview

This workflow automates the process of research planning, query generation, web search, content extraction, and report creation. It integrates with Webhook, Notion, OpenAI, and external APIs.

Main Steps

  1. Trigger: Starts from a Telegram message or Webhook.
  2. Strategy Agent: Asks the user for a research topic and clarifies requirements.
  3. Query Generation: Generates SERP queries for the research topic.
  4. Web Search: Uses Tavily API to fetch search results for each query.
  5. Content Extraction: Extracts content from the most relevant URLs.
  6. Report Generation: Uses AI to synthesize a detailed report in markdown.
  7. Notion Integration: Saves the report and metadata to a Notion database.
  8. Notification: Notifies the user when the report is ready.

Key Nodes

  • Trigger: Listens for new messages.
  • Strategy Agent: Handles user interaction and planning.
  • Search Query Agent: Generates search queries.
  • HTTP Request: Fetches search results and extracts content.
  • OpenAI/AI Agent: Processes and synthesizes information.
  • Notion: Stores the final report.
  • Sticky Note: Use this to add or update instructions.

Tips

  • Update credentials for all API nodes before running.
  • You can edit or move Sticky Notes for better documentation.
  • Use the Switch node to handle user confirmations and feedback.
  • Optionally use Telegram or any other third party integration to trigger the workflow.
Deep Research Report Generation Using Open Router, Google Search, Webhook/Telegram and Notion

Deep Research Report Generation Using Open Router, Google Search, Webhook/Telegram and Notion

Purpose and structure

This folder contains the Deep Research Report Generation Using Open Router, Google Search, Webhook/Telegram and Notion workflow. Its executable nodes use agent, aggregate, chainLlm, code, filter, httpRequest, lmChatGoogleGemini, lmChatOpenRouter, markdown, memoryBufferWindow, notion, openAi, outputParserStructured, respondToWebhook, set, splitInBatches, splitOut, switch, telegramTrigger, webhook. 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

Telegram Trigger, Webhook

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/Deep/2054_Deep_Research_Report_Generation_With_Open_Router_Google_Search_Webhook_Telegram_and_Notion.json MIT; preserve source notices.

More in AI & research

"Hey Siri, Ask Agent" workflow#️⃣Nostr #damus AI Powered Reporting + Gmail + Telegram(G) - Email Classification