HTTP Request and Zendesk integration

This workflow creates an automated Product Intelligence Engine that continuously collects signals from multiple product sources and generates structured PRD updates using AI. It ingests conversations, feedback, support tickets, analytics, and design comments, standardizes them, analyzes them with an AI PRD Agent, and automatically updates a Google Doc with structured PRD recommendations. Instead of manually reviewing Slack threads, Zoom calls, Jira comments, support tickets, and customer forms, this workflow centralizes everything into one intelligent PRD analysis system. High-Level Architecture - The workflow runs in 4 layers: Signal Ingestion Layer Captures product signals from: • Slack (channel messages + app mentions) • Customer Form submissions • Zoom recordings (scheduled) • Jira comments (scheduled) • Zendesk tickets (scheduled) • Figma comments (file updates) • Platform analytics via webhook • (Extendable to Salesforce / HubSpot) Standardization Layer Each source passes through a Format Node that: • Extracts relevant text • Normalizes metadata • Adds timestamps • Labels source type All inputs are converted into a unified "product signal" object. Intelligence Layer (AI PRD Agent) All signals are merged into a single stream using a Merge node. The PRD Analysis Agent then: • Extracts feature requests • Detects scope changes • Identifies risks and constraints • Evaluates priority signals • Detects target user shifts • Generates structured PRD updates PRD Governance Layer - output in a Google Doc The structured AI output is appended to a Google Doc, which is fully traceable. This creates a living PRD that continuously evolves based on real product signals. Required Credentials (And How To Add Them): You will need to configure the following credentials in n8n: Slack Used for Slack Trigger. Steps: Create a Slack App at api.slack.com Enable: app_mentions:read channels:history chat:write (optional if you want replies) Install app to workspace Copy Bot OAuth Token In n8n → Create Slack API credential Paste token Reference - https://www.youtube.com/watch?v=qk5JH6ImK0I Zoom (OAuth2) Used to fetch recordings. Steps: Create an OAuth App in Zoom Marketplace Add the Redirect URL from n8n Copy Client ID + Secret Add Zoom OAuth2 credential in n8n Connect account Reference - https://www.youtube.com/watch?v=BC6O_3LYgac Google Docs (OAuth2) Used to update PRD document. Steps: Create Google Cloud Project Add Doc URl to n8n Replace the example Google Doc URL with your own PRD document. Reference - https://www.youtube.com/watch?v=iieEHvu93dc Jira (Cloud) Steps: Generate API token from Atlassian Create Jira Software Cloud credential Enter: Email API token Domain Reference - https://www.youtube.com/watch?v=T4z7lzqSZDY Zendesk Steps: Generate API token Add Zendesk credential Enter: Subdomain Email API token Figma Steps: Generate a personal access token in Figma Add Figma credentials with the team ID Paste token Platform Analytics Webhook Replace: <PLACEHOLDER_VALUE__your_analytics_api_endpoint> With your real analytics endpoint. You can: • Send Mixpanel exports • Send Amplitude exports • Or POST custom JSON What Makes This Powerful • Eliminates product signal silos • Creates AI-driven PRD governance • Ensures traceability of decisions • Enables continuous PRD evolution • Scales across teams

Description This workflow is designed for B2B/SaaS teams who want to secure renewals before it’s too late. It runs every day, identifies all accounts whose licenses are up for renewal in J–30, enriches them with CRM, product usage and support data, computes an internal churn risk level, and then triggers the appropriate playbook: HIGH risk** → full escalation (tasks, alerts, emails) MEDIUM risk** → proactive follow-up by Customer Success LOW risk** → light renewal touchpoint / monitoring Everything is logged into a database table so that you can build dashboards, run analysis, or plug additional automations on top. How it works Daily detection (J–30 renewals) A scheduled trigger runs every morning and queries your database (Postgres / Supabase) to fetch all active subscriptions expiring in 30 days. Each row includes the account identifier, name, renewal date and basic commercial data. Data enrichment across tools For each account, the workflow calls several business systems to collect context: HubSpot → engagement history Salesforce → account profile and segment Pipedrive → deal activities and associated products Analytics API → product feature usage and activity trends Zendesk → recent support tickets and potential friction signals All of this is merged into a single, unified item. Churn scoring & routing An internal scoring step evaluates the risk for each account based on multiple signals (engagement, usage, support, timing). The workflow then categorizes each account into one of three risk levels: HIGH – strong churn signals → needs immediate attention MEDIUM – some warning signs → needs proactive follow-up LOW – looks healthy → light renewal reminder A Switch node routes each account to the relevant playbook. Automated playbooks 🔴 HIGH risk Create a Trello card on a dedicated “High-Risk Renewals” board/list Create a Jira ticket for the CS / AM team Send a Slack alert in a designated channel Send a detailed email to the CSM and/or account manager 🟠 MEDIUM risk Create a Trello card in a “Renewals – Follow-up” list Send a contextual email to the CSM to recommend a proactive check-in 🟢 LOW risk Send a soft renewal email / internal note to keep the account on the radar Logging & daily reporting For every processed account, the workflow prepares a structured log record (account, renewal date, risk level, basic context). A Postgres node is used to insert the data into a churn_logs table. At the end of each run, all processed accounts are aggregated and a daily summary email is sent (for example to the Customer Success leadership team), listing the renewals and their risk levels. Requirements Database A table named churn_logs (or equivalent) to store workflow decisions and history. Example fields: account_id, account_name, end_date, riskScore, riskLevel, playbook, trello_link, jira_link, timestamp. External APIs HubSpot (engagement data) Salesforce (account profile) Pipedrive (deals & products) Zendesk (support tickets) Optional: product analytics API for usage metrics Communication & task tools Gmail (emails to CSM / AM / summary recipients) Slack (alert channel for high-risk cases) Trello (task creation for CS follow-up) Jira (escalation tickets for high-risk renewals) Configuration variables Thresholds are configured in the Init config & thresholds node: days_before_renewal churn_threshold_high churn_threshold_medium These parameters let you adapt the detection window and risk sensitivity to your own business rules. Typical use cases Customer Success teams who want a daily churn watchlist without exporting spreadsheets. RevOps teams looking to standardize renewal playbooks across tools. SaaS companies who need to prioritize renewals based on real risk signals rather than gut feeling. Product-led organizations that want to combine usage data + CRM + support into one automated process. Tutorial video Watch the Youtube Tutorial video About me : I’m Yassin a Project & Product Manager Scaling tech products with data-driven project management. 📬 Feel free to connect with me on Linkedin

Analyze and Explore your ZenDesk Support Requests using AI-Powered Knowledge Graph This template helps you create an interactive InfraNodus knowledge graph for your ZenDesk tickets using any search criteria (e.g. after a certain date, specific status, sender, keyword) that will automatically be sent to a selected Slack channel. Here's an example of the InfraNodus graph that shows the main topics and gaps in ZenDesk support tickets: You can use the workflow to: Get an instant overview of the main topics your customers are talking about Generate business and product ideas based on the blind spots identified using the InfraNodus AI See which topics correlate to the negative / positive sentiment understanding the weak and strong sides of your product and support Receive daily notifications on the main topics your customers are talking about via Slack / Telegram / Email and other channels Perform detailed search using a password-protected web form for tickets filtered by a certain date, status, tag, sender, keyword. Use the interactive graph to explore specific topics and concepts your customers are talking about — a great way to engage with their concerns in a non-linear way, bypassing the boring tabular interface Use the graph to explore the support requests by specific segments — e.g. status, priority, sentiment, tags, urgency. Use the graph generated as an AI expert available to your AI agents in other n8n workflows via InfraNodus GraphRAG. For instance, you could connect your knowledge base to the support tickets graph and let the agent discover possible solutions to your customers' most typical problems. See an sample template here. How it works You can start this workflow manually, with a daily / weekly trigger, or via a password-protected web form, where you can provide search requests. Once started, it will perform a ZenDesk tickets search with the default or your custom criteria. Then it will use the search results to generate an InfraNodus graph (or add the new data to an existing one), and — finally — use the InfraNodus AI endpoints to generate a topical summary and a product business idea based on the blind spots identified. The results are delivered a channel of your choice. Here's a description step by step: Start the workflow (manually or on schedule) Assign values to variables (search criteria, graph name) Perform ZenDesk support tickets search Convert the data received and submit it to InfraNodus to generate a knowledge graph Generate topical summary with InfraNodus Generate a business idea with InfraNodus (you can also change the setting to generate a question instead) Send a notification via Slack / Telegram / Email or back to the webform How to use You need an InfraNodus API account and key to use this workflow. You also need a ZenDesk account. It takes about 5 minutes to set everything up. Create an InfraNodus account. Get the API key at https://infranodus.com/api-access and create a Bearer authorization key for the InfraNodus HTTP nodes. Add the authorization key to all the InfraNodus HTTP nodes in the template (Steps 3, 5, and 6). Generate a ZenDesk authorization token following the instructions in n8n's ZenDesk node (Step 3). Optionally: connect your Slack or Telegram or Gmail account to receive automated notifications with the link to the graph, once the workflow is ready (it takes about 30 seconds to run). Run it with using the form to play around with the search criteria that works best for you (you can leave everything empty at first), then choose the parameters you like and activate the Daily Trigger node to receive executive summaries to a channel of your choice. Open the graph in InfraNodus and use our customer feedback analysis guide to explore the graph and generate new insights. Requirements An InfraNodus account and API key A ZenDesk API key (Optional) — a Slack / Telegram / Gmail connection for notifications FAQ What are the best use cases to try? I love to set the graph to deliver me a daily visual briefing of what's happening in my support portal. It shows me the main topics and gaps and generates product ideas based on them. Great to keep the pulse on the business. I also really like generating a graph for the past week manually, using the form, and then exploring the graph in InfraNodus directly using the customer feedback analysis workflow to: discover main topics my customers are talking about? understand the topics that have the most negative connotation for them (using the sentiment filter)? discover some support tickets that need more attention or that talk about the topics I'm personally interested in and engage with the client identify the gaps in your customers' discourse based on the blind spots — useful for generating ideas, see the graph below with a demo of how it works: Why use the graph and not just AI summary? AI summary will just give you generic results. You'll see what you already know. Using the graph helps you deconstruct the discourse and get a much more nuanced understanding of the main pain points and interests of your customers. The auto-generated InfraNodus summary and business ideas have a direct explainable connection to the discourse, so you can always see where they are coming from and maintain the focus on all the topics, rather than the most prominent ones. Additionally, having an interactive graph opens a possibility to explore your customers' concerns in a more engaging way, finding the topics and concepts that are relevant to your interests or to your agents' expertise, helping you find the conversations that you'd otherwise have missed. Is my customers' data safe? Absolutely. InfraNodus' terms of use and privacy policy state that the customers' data and text graphs are not used in AI training and are not offered to any third parties. Its underlying API system uses the Open API which explicitly states that data is not used for training either. So all the customers' data are private and safe. As an extra precaution, you can always delete the graphs after you analyzed them, in which case there is no trace of this data left on the servers. Customizing this workflow Check out the complete setup guide for this workflow at https://support.noduslabs.com/hc/en-us/articles/20447530961308-Zendesk-Tickets-Summarization-Sentiment-Analysis-and-Slack-Integration-with-n8n-and-InfraNodus For support with this template, please, contact https://support.noduslabs.com For more InfraNodus n8n workflows, please, see our creators page: https://n8n.io/creators/infranodus/ To learn more about InfraNodus, GraphRAG, and knowledge graph analysis: https://infranodus.com

How it works This AI Customer Success Risk Prediction workflow revolutionizes customer retention by predicting churn risk 30-90 days before it happens. Here's the high-level flow: Daily Data Collection → AI Multi-Signal Analysis → Risk Scoring & Prediction → Smart Risk Routing → AI-Generated Personalized Interventions → CRM Updates & Team Alerts The system automatically gathers data from your product analytics, support system, billing platform, and email tools, then uses GPT-4 to analyze patterns and predict which customers are at risk. It creates personalized intervention strategies and routes them based on urgency level. Set up steps Time to set up: Approximately 45 minutes Prerequisites: Active accounts with your analytics platform, support system, billing provider, CRM, and AI provider Step 1: Import & Configure Workflow (5 minutes) Import the workflow JSON into your n8n instance Review the 3 comprehensive sticky notes for context Understand the AI analysis logic and intervention strategies Step 2: Set Environment Variables (10 minutes) Configure these critical variables: ANALYTICS_API_URL and ANALYTICS_API_KEY HIGH_RISK_SLACK_CHANNEL (for critical alerts) CS_TEAM_EMAIL (intervention sender) CRM_BASE_URL and CALENDAR_BOOKING_URL Step 3: Configure API Credentials (20 minutes) Set up secure credential connections for: OpenAI/Anthropic API (AI analysis engine) Analytics platform (Mixpanel/Amplitude/GA) Support system (Zendesk/Intercom) Billing platform (Stripe/Chargebee) HubSpot CRM (risk data storage) Slack API (team notifications) SMTP/SendGrid (email delivery) Step 4: Customize AI Prompts & Risk Thresholds (8 minutes) Review and adjust the AI analysis prompts for your business Modify risk score thresholds (Critical 90+, High 70-89, Medium 40-69) Customize intervention email templates and tone Set your specific risk factors (usage patterns, support indicators) Step 5: Test & Activate (2 minutes) Run a test execution with sample customer data Verify AI analysis generates appropriate risk scores Check that interventions are routed correctly Activate the daily cron schedule

This workflow syncs Zendesk tickets to Pipedrive contact owners. This workflow is triggered every day at 09:00 with Zendesk collecting all the tickets updated after the last execution timestamp and updating them according to Pipedrive contacts. It also adds Zendesk comments to the tickets as notes in Pipedrive. Prerequisites Pipedrive account and Pipedrive credentials Zendesk account and Zendesk credentials Note: The Pipedrive and the Zendesk accounts need to be created by the same person / with the same email. How it works Cron node triggers the workflow every day at 09:00. Zendesk node collects all the tickets updated after the last execution timestamp. If node checks if the channel in the ticket is an email, and if so, it continues the workflow. The Item Lists node removes duplicates to make search efficient. Pipedrive node searches persons by email. Set node renames and keeps only needed fields (email & person id) Merge by key node adds the Pipedrive contact id to Zendesk tickets. The HTTP Request node gets Zendesk comments for tickets and the Merge node adds them to tickets. Split node adds nodes in batches with each iteration. Item list node splits comments into separate items. Pipedrive node adds comment as notes. If node checks if the data processing is done and if not, goes back to the Split node. The Function Item node sets the new last execution timestamp.

This workflow automatically sends Zendesk tickets to Pipedrive contacts and makes them task assignees. The automation is triggered every 5 minutes, with Zendesk checking and collecting new tickets which are then individually assigned to a Pipedrive contact. Prerequisites Pipedrive account and Pipedrive credentials Zendesk account and Zendesk credentials Note: The Pipedrive and the Zendesk accounts need to be created by the same person / with the same email. How it works Cron node triggers the workflow every 5 minutes. Zendesk node collects all the tickets received after the last execution timestamp. Set node passes only the requester`s email and ID further to the Merge node. Merge by key node merges both inputs together, the tickets and their contact emails. Pipedrive node then searches for the requester. HTTP Request node gets owner information of Pipedrive contact. Set nodes keep only the requester owner's email and the agent`s email and id. Merge by key node merges the information and adds the contact owner to ticket data. Zendesk node changes the assignee to the Pipedrive contact owner or adds a note if the requester is not found. The Function Item node sets the new last execution timestamp.