Workflows
1–12 of 12,123
By Oneclick AI Squad
Quick overview This workflow receives Prometheus Alertmanager webhooks, uses an OpenAI-powered incident investigator agent to query logs and recent deployments, writes a root-cause analysis to Postgres, creates a ClickUp incident task, notifies a Slack channel, and pages PagerDuty for critical incidents. How it works Receives a POST webhook from Prometheus Alertmanager containing the firing alert details. Normalizes key fields (alert name, severity, affected service, description, start time) and derives a session ID from the alert fingerprint to keep follow-up alerts in the same investigation context. Uses an OpenAI agent with session memory to investigate the incident, optionally querying your log API and your CI/CD deployment API multiple times before returning a structured RCA JSON. Parses the agent’s JSON output into fields like root cause, confidence, evidence, likely deployment, severity, and recommended actions. Inserts the analysis into a Postgres incident_analyses table for audit history. Creates a ClickUp task for the incident and posts a formatted summary with the ticket link to a Slack DevOps channel. If the agent-assessed severity is critical, creates a PagerDuty incident to page the on-call engineer, then returns a JSON response to the original webhook caller. Setup Configure Alertmanager to send alerts to this workflow’s webhook URL (POST /alertmanager-incident). Add an OpenAI credential for the Chat Model (set to gpt-4.1) and ensure the agent can use it. Update the two HTTP tool endpoints (logs and deployments) and add any required authentication so they can query your log store (for example Loki/ELK/CloudWatch/Sentry) and your CI/CD or release-tracking system. Add Postgres credentials and create a public.incident_analyses table with columns matching the insert (alert_fingerprint, alert_name, affected_service, root_cause, confidence, evidence, likely_deployment, severity, recommended_actions, created_at). Add ClickUp credentials and set the target List ID where incident tasks should be created. Add Slack credentials and set the target channel (for example #devops-incidents), and add PagerDuty API token credentials plus a Service ID if you want critical paging enabled. An n8n automation workflow template by Oneclick AI Squad.
By Oneclick AI Squad
Quick overview This workflow triggers from a ClickUp webhook (or manual run), uses Anthropic Claude to generate structured mobile app test scenarios, creates ClickUp QA tasks for each scenario, then later reviews executed results and asks Claude to identify missing coverage and open a follow-up ClickUp task if gaps are found. How it works Receives a webhook request from ClickUp (or runs manually) with the requirement task ID. Fetches the ClickUp requirement details and queries the ClickUp testing list for any existing test tasks tagged to the same feature to avoid duplicates. Sends the requirement context, target platforms, and existing coverage to Anthropic Claude to generate new mobile test scenarios as JSON. Creates a ClickUp testing task for each generated scenario, including preconditions, steps, expected results, priority, and tags for platform/category/requirement. Waits for the configured number of days to give QA time to execute the scenarios. Pulls the latest statuses for all ClickUp testing tasks tagged to the requirement, summarizes pass/fail/blocked/pending results, and asks Anthropic Claude to flag any missing or untested scenarios. If gaps are found, creates a ClickUp follow-up coverage-gap task listing the missing scenarios; otherwise records the requirement as fully covered. Setup Add ClickUp API credentials with permission to read tasks and create tasks in your target lists. Add Anthropic (Claude) credentials using HTTP Header Auth (x-api-key) and ensure the Anthropic Messages API is accessible. Update the configuration values for your ClickUp requirement and testing list IDs, target platforms, and the QA results wait window. Copy the production webhook URL from the workflow and register it in ClickUp so new requirement tasks POST to the webhook path. Align your ClickUp task statuses/tags with the workflow’s expectations (platform tags like ios/android/both and statuses containing pass/fail/blocked) so results and gap analysis work correctly. An n8n automation workflow template by Oneclick AI Squad.
By Oneclick AI Squad
Quick overview This workflow listens for Kubernetes create requests in Slack (or runs manually), uses Anthropic Claude to generate a Kubernetes manifest, validates it against deterministic safety guardrails, requests human approval in Slack, then applies the manifest via the Kubernetes API and verifies rollout health with automatic rollback on failure. How it works Triggers from a Slack app mention or a manual run and captures a plain-English description of the Kubernetes resource to create. Uses Anthropic Claude to generate a Kubernetes resource manifest as structured JSON plus a short explanation. Parses the model output and deterministically validates the manifest against guardrails (allowed namespaces, required CPU/memory requests and limits, and blocked privileged/hostNetwork/hostPath usage). If validation fails, posts the specific violations back to Slack and stops. If validation passes, posts the manifest and explanation to Slack and waits for a human approve/reject decision. On approval, sends the manifest to the Kubernetes API to create the resource, waits briefly, then fetches status and evaluates readiness/availability. If the rollout is healthy, posts a success confirmation to Slack; if not, deletes the created resource via the Kubernetes API and alerts Slack about the rollback. Setup Create and connect credentials for Anthropic (Claude), Slack (bot/token with permission to post messages and receive app mentions), and an HTTP Header Auth credential that sends your Kubernetes API bearer token. Update the configuration values in the workflow for your Kubernetes API base URL, allowed namespaces, Slack target channel, and rollout grace/timeout values. Configure your Slack app to enable app mentions in the target channel and ensure the workflow’s Slack Trigger is subscribed to the correct channel. An n8n automation workflow template by Oneclick AI Squad.
By Oneclick AI Squad
Quick overview This workflow receives app store reviews via a webhook, uses Anthropic Claude to classify and deduplicate technical complaints, checks your bug tracker for an existing issue, then either updates the matched bug or creates a new ticket, posts an alert to Slack, and logs the outcome to a tracking API. How it works Receives a new app store review via a POST webhook and normalizes key fields like rating, text, platform, version, and reviewer handle. Uses Anthropic Claude to classify whether the review is a genuine technical complaint, assign an app area and severity, and generate a normalized issue summary. Filters out non-technical reviews, marks them as log-only, and skips ticket creation. For technical complaints, calls a complaint-search API to fetch similar recent issues and uses Anthropic Claude to decide whether the review matches an existing complaint cluster. Searches your bug tracker (via HTTP API) for an existing open issue that matches the complaint and selects the best match above a confidence threshold. If a match is found, updates the existing bug with the review as evidence and the reassessed severity; otherwise it creates a new engineering ticket in the bug tracker. Sends a Slack message to the routed engineering channel with the issue summary, severity, and review details, then logs the final outcome to a tracking-log API. Setup Configure the review source to send POST requests to this workflow’s webhook URL (path: /app-store-review-received) and include fields like reviewText, rating, platform, appVersion, and reviewUrl. Add an Anthropic credential and select a Claude chat model for the two AI agent steps. Set up HTTP header authentication credentials for the complaint-search API, bug-tracker search/update/create endpoints, and the tracking-log API, then update the base URLs in the configuration values. Add Slack credentials, ensure the target channels exist, and adjust the app-area-to-team/channel routing map and default channel as needed. An n8n automation workflow template by Oneclick AI Squad.
By Jessy Mariau
Quick overview Your voice agent ends a call, fires a webhook, and nobody reads it until the customer rings back annoyed. This one reads every call, works out which are actually urgent from the model's own fields, and puts those on the owner's WhatsApp. Everything gets logged. How it works Receives a POST webhook when a voice call ends, containing the call metadata plus an optional transcript and summary. Normalizes the incoming payload into consistent fields (call ID, end reason, transcript/summary text, and caller phone) and checks whether the call has usable text based on known failure end reasons. If the call is unprocessable (for example no transcript/summary or a failure end reason), creates an “unprocessable” record and appends it to the Google Sheets “Call Log” tab. If the call has usable text, sends the transcript/summary to OpenAI to extract structured facts such as caller name/phone, intent, sentiment, urgency, summary, requested action, and any follow-up date. Decides whether the call is urgent using the extracted urgency/sentiment plus keyword matching against your configured urgent keyword list. Appends the call to Google Sheets as either an urgent or routine record, and optionally sends a WhatsApp message to the business owner with the urgent call details. Setup Copy the webhook URL from the “Voice Call Ended” trigger and configure your voice agent platform to POST its end-of-call payload to that URL. Add an OpenAI credential for the extraction model and select the model you want to use. Add a WhatsApp Business Cloud credential, set your WhatsApp Business phone number ID, and fill in the business owner’s WhatsApp number in the handoff settings. Add a Google Sheets credential and replace the placeholder spreadsheet IDs and sheet/tab names for “Call Log”, “Urgent calls”, and “Routine calls” (or swap these logging steps for your CRM nodes). Review and customize the urgent keyword list and the WhatsApp auto-send switch in the handoff settings before activating the workflow. An n8n automation workflow template by Jessy Mariau.
By Jessy Mariau
Quick overview Most Stripe-and-bot setups catch the webhook, flip a flag, and quietly drift out of step with what people actually paid for. This one reads live subscription status every morning, compares it to the access it granted, and corrects anything that no longer matches. How it works Triggers on Stripe webhook events for checkout completion, subscription updates, and subscription deletions. Checks a Data Table ledger to skip Stripe events that have already been processed, then records new event IDs to enforce idempotency. Extracts the Telegram user ID and subscription details from Stripe metadata, maps the Stripe Price ID to a tier, and marks the user as active or inactive based on the event type. Upserts the user’s entitlement (tier, active flag, and Stripe IDs) into a Data Table keyed by Telegram user ID. Runs daily on a schedule, reads all entitlement rows, fetches each subscription’s live status from the Stripe API, and detects mismatches using a configurable grace period for past-due statuses. Updates drifted entitlement rows to match Stripe and posts a summary of the corrections to a Slack channel. Triggers on incoming Telegram messages, looks up the sender’s entitlement in the Data Table, and either sends the protected message or replies with a Stripe Payment Link prompt. Setup Add Stripe credentials for the Stripe Trigger and an HTTP Bearer Auth credential with your Stripe secret key for the Stripe subscription lookup request. Create two n8n Data Tables (one for entitlements and one for processed Stripe event IDs) and replace the placeholder table IDs in all Data Table steps. Add your Telegram bot credentials and ensure your Stripe checkout sets a telegramUserId in Stripe Customer or Checkout Session metadata so events can be linked to Telegram users. Set your Stripe Price ID→tier JSON mapping in both settings blocks, update the Stripe Payment Link URL and bot messages, and choose the Slack channel (and Slack credentials) for drift reports. An n8n automation workflow template by Jessy Mariau.
By Jessy Mariau
Quick overview I stopped trusting a model to add up its own numbers, so this one checks its work in plain code. It reads the table off a PDF, sums the line items in JavaScript, and only writes to your books when that sum matches the printed total. How it works Triggers when a new Gmail message arrives under a specific label and includes an attachment, downloading the attachment for processing. Filters to PDF attachments only and converts each PDF into plain text. Uses OpenAI with a structured output schema to extract the report title, currency, stated total (as printed), and all line-item rows from the PDF text. Calculates the sum of extracted line totals in JavaScript and compares it to the stated total using the configured absolute and percentage tolerances. If the totals reconcile, splits the extracted rows into individual line items and appends them to the “Line Items” tab in Google Sheets. If the totals do not reconcile (or no stated total is available), appends a summary row to the “Needs Review” tab in Google Sheets and posts a mismatch alert to a Slack channel. Setup Add credentials for Gmail, OpenAI, Google Sheets, and Slack (OAuth2) in n8n. Create or choose a Gmail label for incoming report emails and set its label ID/name in the Gmail trigger filter. Update the Google Sheets document URL and ensure it contains the “Line Items” and “Needs Review” tabs (or rename the sheet targets in the Report Settings). Set the Slack channel name for reconciliation alerts in the Slack message node. Review and adjust the tolerance values and default currency in Report Settings to match your reconciliation rules. An n8n automation workflow template by Jessy Mariau.
By Luka
Quick overview E-commerce researchers who need a variant-level price and availability register for a known public Shopify store, collection or product. Compare sizes, formats and SKUs without copying product details manually. How it works One bounded Apify snapshot supplies products with their variants. The workflow waits for the same run, checks source coverage and settled product charges, then verifies the complete dataset before writing one Sheet row per variant. Stable keys update existing observations on repeat. Unobserved rows remain, so check observation dates before decisions. Availability means public buyability, not inventory quantity. A blank compare-at price stays unknown. This workflow does not calculate price changes or alter a Shopify store. COMPLETE describes the declared source window; CAPPED is a labelled sample. Incomplete source data stops delivery. Verified empty results produce no rows. Setup Import the JSON into an empty n8n canvas. Select your Apify Header Auth credential on all five HTTP nodes and Google Sheets OAuth2 on Upsert review register. Create a Variant Review tab and import the exact CSV header. Set its spreadsheet ID and source URL in Review settings, then run manually. Requirements The template is free; Apify usage is paid per product with variants included. The default $1 cap is a ceiling, not a quoted price. Repeats may incur charges again. Customization Choose one public Shopify URL and up to 10 products. Delivery stops above 500 variants. Maximums are not promised minimums. Repeat sequentially with the same source URL to update existing keys. Setup details. Additional info. An n8n automation workflow template by Luka.
By Luka
Quick overview Give a community organizer an event-planning register for one city. Bring public Luma dates, timezones, venue information and registration requirements into Google Sheets without copying attendee profiles or sending invitations. How it works One bounded Apify run supplies source records, coverage and billing evidence. The workflow checks the complete dataset before Google Sheets delivery. Stable source keys update existing rows on repeat. Unobserved earlier rows remain, so the Sheet is a current review register, not a complete history. COMPLETE describes the declared source window; CAPPED remains a labelled sample. Source failures stop delivery. Verified empty results create no data rows. Keep UTC timestamps and the source timezone together. The review action highlights applications, sold-out events and dates that have already started. Empty price or availability fields remain unknown. Review the event page before making plans; the workflow does not register guests or book tickets. Setup Import the workflow into an empty n8n canvas. Use your own Apify account and a Header Auth credential on all five HTTP nodes. Connect Google Sheets OAuth2 on Upsert review register. Create the supplied tab and import the exact CSV header. Enter its spreadsheet ID in Review settings and run manually. Requirements The template is free; Apify usage is paid. The default $1 cap is a maximum, not a quoted price. Repeated results can incur charges again. Only Sheet delivery retries automatically. Customization Start with sf, then use another supported Luma city slug. Choose all, in_person or online events and all, free or paid pricing. Up to 100 events are supported. Keep settings stable and run sequentially to update the same scope. Setup details. Additional info. An n8n automation workflow template by Luka.
By Luka
Quick overview Give a local agency a reviewable list of businesses from a Google Maps search. Keep public phone numbers, website links and source evidence together, with clear reasons for manual review. How it works One bounded Apify run supplies source records, coverage and billing evidence. The workflow checks the complete dataset before Google Sheets delivery. Stable source keys update existing rows on repeat. Unobserved earlier rows remain, so the Sheet is a current review register, not a complete history. COMPLETE describes the declared source window; CAPPED remains a labelled sample. Source failures stop delivery. Verified empty results create no data rows. Listing contact evidence and website fetch results remain separate. An uncertain or failed website check becomes MANUALLY_VERIFY_WEBSITE, never proof that a business needs a new site. NO_SUPPORTED_WEBSITE_PITCH means the source does not support that offer. Public phone availability does not establish permission to contact someone. Setup Import the workflow into an empty n8n canvas. Use your own Apify account and a Header Auth credential on all five HTTP nodes. Connect Google Sheets OAuth2 on Upsert review register. Create the supplied tab and import the exact CSV header. Enter its spreadsheet ID in Review settings and run manually. Requirements The template is free; Apify usage is paid. The default $1 cap is a maximum, not a quoted price. Repeated results can incur charges again. Only Sheet delivery retries automatically. Customization Change the search, location and country. Up to 20 businesses are supported. The maximum is an upper limit, not a guaranteed result count. Keep settings stable and run sequentially to update the same scope. Setup details. Additional info. An n8n automation workflow template by Luka.
By Dzhabrail Khalilov
Quick overview Get a proposed fix for a GitHub issue from four independent AI reviewer roles. Choose your model provider during setup. Optional BVC decides whether another discussion round is worthwhile within a fixed call limit. A person reviews the resulting plan and audit. How it works A form receives the GitHub repository, issue number, source revision and one to six explicitly selected files. Use a full commit SHA for reproducible input. The workflow reads the issue and selected files through the GitHub API. All file reads use one fixed commit SHA; repository content is treated as untrusted evidence. Four roles of the chosen model review the same evidence: architect, developer, reviewer and tester. They cannot see each other's initial answers. With Use BVC checked, the original Xynapse planning algorithm decides whether disagreement justifies one extra critique round. Unchecked, it uses the SDK's fixed baseline when the budget permits. The configured limit is five or nine counted model attempts, including failed calls. One slot is reserved for synthesis. The workflow has no automatic provider retries. Synthesis produces a proposed bug-fix plan. Refused, truncated, malformed or unconfirmed final responses produce a failure report instead of a ready plan. The form displays the result and technical audit, including attempts, disagreements and stop reasons. The workflow never edits GitHub, creates pull requests or comments, or verifies a patch. Setup Import workflow.json into n8n 2.37.10 with JavaScript Code nodes enabled. Download the README, source and tests from the linked GitHub release for detailed setup instructions. Create a GitHub Header Auth credential using Authorization: Bearer YOUR_GITHUB_TOKEN. Grant only read access to contents, issues and metadata for the selected repositories, and bind it to all eight GitHub HTTP nodes. Choose the provider, exact API model ID and five- or nine-call limit in Configure approved input. Create the matching model Header Auth credential and bind it to all nine Model HTTP nodes. Your provider account pays for API calls. Supported API adapters include OpenAI, Claude, Gemini, DeepSeek, Yandex and trusted OpenAI-compatible endpoints. Yandex is optional and requires its Cloud folder ID. Provider and budget settings are controlled by the workflow owner, not by form input. Test the Discuss a GitHub issue form, then publish the workflow for its reusable form URL. Users need an authorized n8n login. Alternatively select Start manually and read Final report in execution output. Requirements An n8n installation with standard Code, HTTP Request and Form nodes; a GitHub read-only token; and your own supported model-provider API account. No Xynapse IDE or separate service is required. Customization Choose the provider and model during setup, set maxCalls to 5 or 9, and toggle Use BVC. The four reviewer roles use one selected model. Changing providers also requires rebinding the model credential. Additional info Skipping critique can avoid four calls; token savings, lower cost and better plans are not guaranteed. Local self-hosted n8n tests and live Yandex runs are documented; n8n Cloud and live calls to other providers remain unverified. verification = not_run. Source, README, tests and audit evidence: https://github.com/jabrailkhalil/xynapse/releases/tag/n8n-bvc-v0.1.0. An n8n automation workflow template by Dzhabrail Khalilov.
By Paras Gediya
Quick overview Searches Upwork every 15 minutes using the GraphQL API, loads matching preferences from a dynamic profile.md file, filters and scores new jobs with an AI chat model, sends high-scoring opportunities to Telegram, and stores processed jobs in an n8n Data Table to prevent duplicate alerts. How it works Runs every 15 minutes on a schedule. Loads a profile.md file over HTTP, extracts a JSON configuration block, and validates required fields and defaults. Builds one Upwork GraphQL search request per configured search lane and fetches the latest job postings using Upwork OAuth2. Normalizes job data, applies deterministic filters (age, budget floors, blocked keywords), deduplicates within the run, and skips jobs already stored in the upwork_seen_jobs n8n Data Table. On the first run with “seed” behavior or for deterministically rejected jobs, records the job as seen without sending any alert. For remaining jobs, prompts an OpenAI chat model to score fit and draft a proposal opening, then decides whether to alert based on the configured score thresholds. Sends a formatted HTML alert to Telegram for jobs above the threshold and upserts each processed job (alerted or not) into the upwork_seen_jobs table to prevent reprocessing. Setup The workflow automatically creates or reuses the upwork_seen_jobs Data Table when required. Host a profile.md file containing the required profile-config JSON block and enter its raw URL in Runtime Settings. Add your Upwork OAuth2 credential to the Upwork GraphQL request node. Add an OpenAI API credential, or connect another compatible chat model for scoring and proposal generation. Add your Telegram bot credential and enter the destination Telegram chat ID in Runtime Settings. Run the workflow manually once to verify profile loading, Upwork access, AI scoring, Telegram delivery, and Data Table storage before activating the schedule. Requirements An n8n instance with Data Tables and AI/LangChain nodes available. Upwork API access with OAuth2 credentials that can search marketplace job postings. An OpenAI API credential, or another compatible chat model configured in n8n. A Telegram bot credential and the Telegram chat ID where job alerts should be delivered. A publicly accessible raw URL for profile.md, such as a GitHub raw file URL. Customization Edit profile.md to define skills, experience, preferred job types, search queries, rates, budgets, and blocked keywords. Adjust AI scoring weights, minimum alert score, and high-priority score inside profile.md. Change the workflow schedule from the default 15-minute interval to your preferred monitoring frequency. Replace the included OpenAI chat model with another n8n-compatible AI model if preferred. Extend Telegram notifications to Slack, WhatsApp, email, Discord, or other notification channels. Change first-run behavior between seed mode, which records existing jobs silently, and alert mode. Additional info This workflow only monitors, filters, scores, and notifies users about Upwork job opportunities. It does not automatically submit proposals, spend Connects, contact clients, or perform other Upwork account actions. Freelancer-specific matching rules are stored in profile.md rather than hard-coded into the workflow, allowing the same template to be reused by different users. API keys, OAuth tokens, Telegram bot tokens, and other secrets should always be stored using n8n Credentials and never inside profile.md. The default first-run seed behavior prevents users from receiving a large number of alerts for jobs that existed before monitoring was enabled. An n8n automation workflow template by Paras Gediya.
