This article provides a complete, practical walkthrough of the Splitout Comparedatasets Create Triggered n8n agent. It connects HTTP Request, Webhook across approximately 1 node(s). Expect a Intermediate setup in 15-45 minutes. One‑time purchase: €29.

What This Agent Does

This agent orchestrates a reliable automation between HTTP Request, Webhook, handling triggers, data enrichment, and delivery with guardrails for errors and rate limits.

It streamlines multi‑step processes that would otherwise require manual exports, spreadsheet cleanup, and repeated API requests. By centralizing logic in n8n, it reduces context switching, lowers error rates, and ensures consistent results across teams.

Typical outcomes include faster lead handoffs, automated notifications, accurate data synchronization, and better visibility via execution logs and optional Slack/Email alerts.

How It Works

The workflow uses standard n8n building blocks like Webhook or Schedule triggers, HTTP Request for API calls, and control nodes (IF, Merge, Set) to validate inputs, branch on conditions, and format outputs. Retries and timeouts improve resilience, while credentials keep secrets safe.

Third‑Party Integrations

• HTTP Request
• Webhook

Import and Use in n8n

1. Open n8n and create a new workflow or collection.
2. Choose Import from File or Paste JSON.
3. Paste the JSON below, then click Import.
4. Show n8n JSON

   Title:  
   Automating Sales Intelligence: How CallForge Uses n8n to Process and Analyze Gong Calls  
   
   Meta Description:  
   Discover how CallForge leverages n8n to enrich and analyze Gong sales call data using OpenAI, Notion, and Google Sheets integrations. See how AI-driven transcript processing enhances sales insights.
   
   Keywords:  
   n8n, Gong, CallForge, sales automation, AI transcript processing, OpenAI, Notion API, Google Sheets API, CRM automation, sales intelligence, sales call analysis
   
   Third-Party APIs Used:
   
   1. Gong API – To fetch call recordings and metadata.
   2. Google Sheets API – To retrieve integration data for enriching AI prompts.
   3. Notion API – To access competitor and call database information.
   4. OpenAI API (Referenced indirectly via “Call Processor”) – To generate structured insights and summaries from transcripts.
   
   —
   
   Article:
   
   Harnessing Sales Intelligence with n8n: Inside CallForge's Automated Gong Call Processor
   
   In today’s fast-paced sales landscape, AI-powered solutions like CallForge offer next-level automation for extracting value from customer interactions. Built using the low-code automation platform n8n, CallForge seamlessly pulls sales call data from Gong, enriches it with integration and competitor info, and then uses AI to generate structured insights. The result? A clean, scalable platform that empowers sales and product teams to understand prospect feedback, sales rep performance, and market trends with little to no manual work.
   
   Let’s explore how this powerful automation flows through n8n, transforming raw call data into actionable intelligence.
   
   Step 1: Triggering the Workflow
   
   The workflow begins with an n8n Execute Workflow Trigger node—listening for an external event or manual start. Once initiated, it orchestrates the following tasks in parallel:
   - Fetch the latest Gong call data.
   - Query Google Sheets for a list of integrations associated with the product.
   - Access a Notion database that maintains structured competitor information.
   
   This multi-source data collection ensures that the AI prompt used in later stages has sufficient context, which is key for accurate analysis and summarization.
   
   Step 2: Aggregating and Enriching Data
   
   From the Gong API, sales call records from the past 48 hours are pulled. These call datasets are combined using aggregation nodes along with product integrations from Google Sheets and competitor details from Notion. The integrations and competitor names are then formatted into comma-separated strings for use in prompt construction.
   
   This is important not just for generating accurate AI feedback, but also for sanity-checking the transcript—catching common data entry issues such as misspellings of competitor names or integrations.
   
   Step 3: Deduplicating with Notion
   
   Before any AI processing begins, the workflow ensures it doesn’t process any call twice.
   
   A query to a second Notion database compares existing call IDs that have already been summarized. These are extracted by isolating the Gong call ID from the “Sales Call Summaries Demo” database.
   
   n8n’s Compare Datasets node then filters out already-processed call IDs from the new dataset, efficiently avoiding redundant work and saving on compute time and AI processing costs.
   
   Step 4: Looping Over Calls for Processing
   
   With a clean, enriched batch of new Gong calls to process, the workflow loops through each call in batches. Using the built-in splitInBatches node, it sends these call objects to a nested “Transcript Processor” workflow.
   
   Here, a “Call PreProcessor” flow cleans the transcript—turning it into a readable, continuous string while stripping noise. This preparation step reduces the burden on OpenAI by reducing prompt size and standardizing the input format.
   
   Step 5: AI Transcript Analysis
   
   Once the transcript is cleaned, it is handed off to what the workflow calls the “Call Processor,” which likely wraps an OpenAI GPT model. The prompt contains the transcript along with competitor and product integration context, allowing the AI to:
   - Detect competitor mentions.
   - Flag any confusion about integrations.
   - Summarize key takeaways.
   - Output structured JSON suitable for Notion insertion or downstream BI tools.
   
   Step 6: Final Aggregation
   
   Once all calls are analyzed, data flows through final receive and processing nodes where results can be logged, stored in Notion, or sent elsewhere. This modular approach ensures each part of the workflow can scale independently or be reused in other n8n automations.
   
   The Value of Low-Code + AI
   
   CallForge exemplifies the power of combining AI with modern, no-code/low-code workflows. It's a system that:
   - Enhances sales insights with minimal human intervention.
   - Enriches transcripts with real-time product and market data.
   - Uses cleanly structured logic to enable scalability and error-proofing.
   - Facilitates collaboration across sales, product, and data teams through consistent formatting and source systems like Notion and Google Sheets.
   
   With tools like n8n, non-engineering teams can now build sophisticated pipelines that would once require full-stack software engineering resources.
   
   Conclusion
   
   CallForge isn’t just a transcript processor—it's an intelligent co-pilot for sales teams, driven by n8n and API integration. Leveraging tools like Gong, Notion, and OpenAI, it turns unstructured sales calls into structured gold, ready to be mined by marketers, sales reps, and product leaders alike.
   
   This is no longer the future of sales automation—it’s the present.
   
   —  
   Written by your AI tech assistant  
   For more automation ideas, visit n8n.io or explore community workflows.

5. Set credentials for each API node (keys, OAuth) in Credentials.
6. Run a test via Execute Workflow. Inspect Run Data, then adjust parameters.
7. Enable the workflow to run on schedule, webhook, or triggers as configured.

Tips: keep secrets in credentials, add retries and timeouts on HTTP nodes, implement error notifications, and paginate large API fetches.

Validation: use IF/Code nodes to sanitize inputs and guard against empty payloads.

Why Automate This with AI Agents

AI‑assisted automations offload repetitive, error‑prone tasks to a predictable workflow. Instead of manual copy‑paste and ad‑hoc scripts, your team gets a governed pipeline with versioned state, auditability, and observable runs.

n8n’s node graph makes data flow transparent while AI‑powered enrichment (classification, extraction, summarization) boosts throughput and consistency. Teams reclaim time, reduce operational costs, and standardize best practices without sacrificing flexibility.

Compared to one‑off integrations, an AI agent is easier to extend: swap APIs, add filters, or bolt on notifications without rewriting everything. You get reliability, control, and a faster path from idea to production.

Best Practices

• Credentials: restrict scopes and rotate tokens regularly.
• Resilience: configure retries, timeouts, and backoff for API nodes.
• Data Quality: validate inputs; normalize fields early to reduce downstream branching.
• Performance: batch records and paginate for large datasets.
• Observability: add failure alerts (Email/Slack) and persistent logs for auditing.
• Security: avoid sensitive data in logs; use environment variables and n8n credentials.

FAQs

Can I swap integrations later? Yes. Replace or add nodes and re‑map fields without rebuilding the whole flow.

How do I monitor failures? Use Execution logs and add notifications on the Error Trigger path.

Does it scale? Use queues, batching, and sub‑workflows to split responsibilities and control load.

Is my data safe? Keep secrets in Credentials, restrict token scopes, and review access logs.