Email Intent Classifier
AI reads inbound emails, scores buyer intent across 7 categories, and routes to Pipedrive — deals, activities, and notes created automatically.
AI reads inbound emails, scores buyer intent across 7 categories, and routes to the correct Pipedrive pipeline stage. 30-node swarm. $0.116/email blended cost.
Four Agents. Seven Intents. Emails Routed to Pipedrive Automatically.
Step 1 — The Researcher
Tier 1 Reasoning
Receives inbound email data from Gmail and conducts web-based sender research — company intelligence, role seniority, and deal context from Pipedrive. Outputs a structured research payload that gives the Classifier the context it needs for accurate intent scoring.
Step 2 — The Classifier
Tier 1 Reasoning
Scores each email across 7 intent categories: DEMO_REQUEST, PRICING_INQUIRY, OBJECTION, RENEWAL_INTEREST, CHURN_SIGNAL, GENERAL_INQUIRY, and SPAM_OR_NOISE. Outputs intent classification with a confidence score (0–1.0) and chain-of-thought reasoning.
Step 3 — The Router
Conditional
Three-way confidence gate: high confidence (≥ 0.7) routes to Pipedrive CRM — deals, activities, and notes created based on intent category. Low confidence routes to human review with full classification context. SPAM/noise logs and skips with zero additional LLM calls.
Step 4 — The Syncer
Integration
Writes to Pipedrive based on intent: DEMO_REQUEST, PRICING_INQUIRY, and RENEWAL_INTEREST create Deals + Activities. OBJECTION and CHURN_SIGNAL create Notes on existing deals. GENERAL_INQUIRY creates an Activity. Non-blocking writes — pipeline never stalls on CRM errors.
What It Does NOT Do
Does not send reply emails — output is Pipedrive records and classification data
Does not process email attachments — classification is based on subject and body text only
Does not support CRMs other than Pipedrive in v1 — Pipedrive-specific deal, activity, and note creation
Does not handle email threading — each inbound email is classified independently
The Complete Customer Success Bundle
9 files. Workflow, 2 system prompts, intent taxonomy, threshold guide, and complete documentation.
Tested. Measured. Documented.
All values below are from ITP testing — not estimates, not projections. Measured across 20 test emails spanning all 7 intent categories, borderline confidence cases, and edge cases.
Workflow Nodes
30 specialized n8n nodes
Blueprint Quality Standard
BQS v2 — 12/12 PASS
Agent Roles
4 (Researcher, Classifier, Router, Syncer)
Credentials Required
Anthropic API + Pipedrive API + Gmail OAuth2
Bundle Files
9 files
Cost per Email (ITP-Measured)
$0.116 (ITP-measured blended average)
Inspection & Test Plan
EIC-01 through EIC-08 + U-01 through U-06 — 14/14 PASS
Classification Consistency (3 Runs)
Max variance 0.02 across 3 runs (threshold <= 1.0)
n8n Versions Tested
Self-hosted
Architecture: Modular Agentic Swarm (4 agents, linear-then-branching pipeline) Pipeline: Gmail Trigger → Researcher (web_search) → Classifier (7-class intent) → 3-Way Router → Pipedrive (Deals/Activities/Notes) or Human Review or Log Nodes: 30 specialized n8n nodes Reasoning: Tier 1 Reasoning for Researcher + Classifier Routing: Confidence threshold ≥ 0.7 for CRM action, < 0.7 for human review, SPAM/NOISE for log Intent Categories: DEMO_REQUEST, PRICING_INQUIRY, OBJECTION, RENEWAL_INTEREST, CHURN_SIGNAL, GENERAL_INQUIRY, SPAM_OR_NOISE Error Handling: 26 documented failure modes with retry, fallback, dead letter Test Evidence: ITP 14/14 PASS, 20/20 intent accuracy (100%) Cost: $0.116 per email (ITP-measured blended average) Platform: n8n (self-hosted) Quality Audit: BQS v2 — 12/12 PASS
Email Intent Classifier v1.0.0
$199
one-time purchase
What you get:
- ✓30-node n8n workflow (.json) — you own it
- ✓2 production-ready agent system prompts
- ✓8 SDC inter-agent schemas
- ✓Intent taxonomy with 7 categories and examples
- ✓Confidence threshold tuning guide
- ✓Error handling matrix (26 failure modes documented)
- ✓Dependency matrix with ITP-measured costs
- ✓README setup guide (15 minutes)
- ✓14-day refund policy
Frequently Asked Questions
What are the 7 intent categories?+
DEMO_REQUEST (meeting/demo requests), PRICING_INQUIRY (pricing/proposal discussions), OBJECTION (sales objections or pushback), RENEWAL_INTEREST (renewal or expansion signals), CHURN_SIGNAL (cancellation or downgrade threats), GENERAL_INQUIRY (other business emails), and SPAM_OR_NOISE (newsletters, recruitment, automated notifications).
What happens when confidence is below 0.7?+
Low-confidence classifications route to the human review path. The pipeline returns the full classification context — intent category, confidence score, reasoning, and sender research — so a human can verify and take action. No CRM records are created automatically for low-confidence emails.
How does the SPAM path save cost?+
SPAM_OR_NOISE emails are detected early in the pipeline. Once classified as spam, the pipeline logs the result and skips all downstream processing — no Pipedrive writes, no additional LLM calls. SPAM path executes in under 100ms with zero additional cost beyond the initial classification.
What Pipedrive records does this create?+
Depends on intent: DEMO_REQUEST, PRICING_INQUIRY, and RENEWAL_INTEREST create a new Deal + Activity + Note. OBJECTION and CHURN_SIGNAL add a Note to the existing deal. GENERAL_INQUIRY creates an Activity only. All Pipedrive writes include the intent classification, confidence score, and Researcher context.
What credentials are required?+
Three credentials: Anthropic API key (used by Researcher and Classifier agents), Pipedrive API token (for deal, activity, and note creation), and Gmail OAuth2 (for email trigger). The README includes step-by-step setup for all three.
How does the Researcher gather sender intelligence?+
The Researcher uses web_search with the sender email domain and name as anchors. It investigates the sender's company, role, recent news, and cross-references against existing Pipedrive contacts. Output includes a research confidence score — unknown senders get lower confidence but are still classified.
Can I change the confidence threshold?+
Yes. The threshold is a single value in the Router node (default: 0.7). Lower it to route more emails to CRM automatically, or raise it for stricter human review gating. The bundle includes a confidence threshold tuning guide with recommendations based on email volume.
What does this blueprint NOT do?+
It does not send reply emails — output is Pipedrive records and classification data. It does not process attachments — classification is based on email subject and body text. It does not support CRMs other than Pipedrive in v1. It does not handle email threading — each email is classified independently.
How much does each email classification cost?+
Approximately $0.116 per email (blended average). Actionable emails cost $0.134, SPAM emails cost $0.000 beyond initial classification. At 500 emails per month, total API cost is approximately $58. All costs are ITP-measured across 20 test emails.
What's the refund policy?+
14-day refund window from purchase date. You must demonstrate attempted deployment and identify a specific failure not covered by the documentation. Full terms at forgeworkflows.com/legal.
More Gmail Blueprints
Outbound Prospecting Agent
Apollo-sourced leads, AI-qualified and personally emailed — zero manual prospecting.
Contact Intelligence Agent
Automated CRM enrichment that researches, scores, and writes back to Pipedrive — zero manual lookup.
Inbound Lead Qualifier
Qualify inbound form leads with a 3-agent ILQ scoring pipeline — web research, 4-criteria scoring, and automatic Pipedrive routing.
Expansion Revenue Detector
AI monitors Stripe payment patterns, scores expansion potential across 5 signal categories, and routes upsell and at-risk briefs to Pipedrive automatically.
Powered by Anthropic
Autonomous SDR Blueprint
32-node agentic swarm that researches, qualifies, writes, and syncs — so your SDR team focuses on closing.
Meeting Briefing Generator
Automated pre-meeting intelligence for every call on your calendar.
RFP Intelligence + Response Agent
Qualify bids. Win more. Stop responding to RFPs you can't win.