Feature Request Extractor
Every feature request in Slack becomes a structured Linear issue. Automatically.
Real-time AI triage for Slack feature requests. Detects, classifies, and creates structured Linear issues automatically — with priority, product area, and source link. Zero manual triage.
One Classifier. Real-Time Triage. Zero Manual Work.
Step 1 — Input Filter
Code Only
Slack Events API fires a webhook on every message posted in the configured channel. Bot messages and messages shorter than the configurable minimum length are filtered immediately — no LLM calls wasted on noise. The remaining messages are forwarded to classification. Zero LLM cost.
Step 2 — The Classifier
Tier 1 Reasoning
Opus 4.6 evaluates whether the message is a genuine feature request. If yes: extracts a structured title (action-verb format), description, priority (1–4), and product area from your configured taxonomy. Confidence threshold configurable (default 0.7). Chain-of-thought enforced. Non-requests exit immediately.
Step 3 — Issue Creator
GraphQL
Creates a structured Linear issue via GraphQL issueCreate mutation with all classified fields — title, description, priority, product area label, and a source link back to the original Slack message. Team and label IDs are cached for 24 hours via workflow static data — zero redundant API calls.
Step 4 — Notifier
HTTP
Adds a ✅ reaction to the original Slack message and posts a thread reply with the Linear issue link (e.g., "Feature request captured → ENG-142"). The thread reply confirms triage happened — no requests silently disappear.
What It Does NOT Do
Does not deduplicate feature requests across messages — each message is classified independently
Does not monitor DMs, threads, or multiple channels — single configured channel only
Does not update existing Linear issues — creates new issues only
Does not integrate with Jira, Asana, or other project tools — Linear only
The Complete Customer Success Bundle
9 files — workflow, system prompt, configuration guides, and complete documentation.
Tested. Measured. Documented.
Every metric is ITP-measured. The Feature Request Extractor classifies Slack messages in real time and creates Linear issues at $0.029/message blended with a single Opus 4.6 call.
Feature Request Extractor v1.0.0 — Technical Reference━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━Pipeline: Slack Events API Webhook → Input Extractor → Bot Filter → Short Message Filter → Classifier Prompt Constructor → The Classifier (Opus 4.6, CoT feature request detection) → Response Parser → Confidence Gate → Resolver (team/label cache, 24h TTL) → Issue Creator (Linear GraphQL issueCreate) → Reaction Adder (Slack ✅) → Thread Replier (Slack postMessage) → Success LoggerTopology: Real-time event-driven (per Slack message), single LLM call, dual output (Linear issue + Slack confirmation)Classification: Feature request detection with title extraction (action-verb format), description, priority (1–4), product areaConfidence: Configurable threshold (default 0.7) — messages below threshold exit without issue creationNode Count: 22LLM: Claude Opus 4.6 (Classifier, single call per message)Cost: $0.046/FR detected | $0.023/non-FR exit | $0.029 blended per messageITP: 20/20 records | 14/14 milestones PASS | Classifier consistency [0.97, 0.97, 0.97] variance=0BQS: 12/12 PASSCaching: Linear team/label IDs cached 24h via workflow static dataTool A: Slack (input — Events API webhook, message.channels)Tool B: Linear (output — GraphQL issueCreate mutation)Intelligence: Feature request detection and classificationCost Value: 0.029
What You'll Need
Platform
n8n 2.11.2+
Est. Monthly API Cost
$3–5/month
Credentials Required
- ▪Anthropic API
- ▪Slack Event API
- ▪Linear API
Services
- ▪Slack workspace
- ▪Linear account
Setup Track
Quick Start
~15 min
All credentials live, n8n running
Full Setup
1–2 hrs
Needs API config + tables
From Scratch
2–4 hrs
No n8n, no credentials
Feature Request Extractor v1.0.0
$199
one-time purchase
What you get:
- ✓Production-ready 22-node n8n workflow — import and deploy
- ✓Real-time Slack monitoring — every message evaluated as it arrives
- ✓Structured Linear issues with title, description, priority, product area, and source link
- ✓Configurable product area taxonomy — adapt to your domain
- ✓Confidence threshold tuning — control precision vs recall
- ✓24-hour team/label ID caching — zero redundant Linear API calls
- ✓Slack ✅ reaction + thread reply confirmation on every captured request
- ✓$0.046/FR detected, $0.023/non-FR exit, $0.029 blended per message
- ✓ITP test results with 20 fixtures and 14/14 milestones
- ✓All sales final after download
Frequently Asked Questions
How does it differ from Support Pattern Analyzer?+
Distinct products with zero overlap. SPA runs weekly, pulls Freshdesk tickets, clusters support patterns, and delivers a digest to Notion + Slack for CS teams. FRE monitors Slack in real time, classifies individual messages as feature requests, and creates Linear issues for PM/product teams. Different sources, cadences, outputs, and buyers.
What counts as a feature request?+
The Classifier evaluates each message for intent — explicit asks ("we need X"), implicit needs ("it would be great if..."), and enhancement suggestions. Bot messages, short messages, and general discussion are filtered before the LLM call. Confidence threshold (default 0.7) controls the boundary.
How is priority assigned?+
The Classifier assigns priority 1–4 based on message content: urgency language, customer tier indicators, scope of the request, and alignment with common product patterns. Priority maps directly to Linear issue priority levels.
How does product area classification work?+
You configure your product area taxonomy in the workflow — a list of areas with descriptions. The Classifier maps each feature request to the closest matching area. The guide includes example taxonomies for SaaS B2B, dev tools, and consumer apps.
How much does each message cost?+
ITP-measured: $0.046 per feature request detected (full classification + issue creation), $0.023 per non-feature-request (early exit after classification). Blended average across all messages: $0.029. Bot messages and short messages are filtered before the LLM — $0.00 cost.
What if the same feature request is posted twice?+
Each message is classified independently. The workflow does not deduplicate across messages — that is a Linear-side concern (search before creating). Duplicate detection across Slack messages is planned for v1.1.
Does caching persist across restarts?+
Team/label ID caching uses n8n workflow static data with a 24-hour TTL. Static data resets when the workflow is deactivated/reactivated or when n8n restarts. After a restart, the first run re-fetches team and label IDs from Linear (one extra API call).
Is there a refund policy?+
All sales are final after download. Review the Blueprint Dependency Matrix and prerequisites before purchase. Questions? Contact support@forgeworkflows.com before buying. Full terms at forgeworkflows.com/legal.
Related Blueprints
Customer Onboarding Intelligence Agent
Deal closes. AI builds the onboarding brief before CS picks up the phone.
Support Pattern Analyzer
AI reads your Freshdesk. Delivers a weekly support intelligence brief before standup.
Email Intent Classifier
AI reads inbound emails, scores buyer intent across 7 categories, and routes to Pipedrive — deals, activities, and notes created automatically.
Buying Signal Detector
Know which accounts just entered a buying window. Before your competitors do.