Resource
Classify Support Tickets with AI
Billing, Technical, Account, How-To, Feature Request — ticket triage with definitions that decide the borderline cases for the model.
Intent Classification Prompt for Inbound Email
Sales, Support, Partnership, Press, Spam — route inbound email by intent, with a Strict "Other" so the weird ones reach a human.
Overview
Intent routing is where wrong labels hurt: a press inquiry routed to sales support dies quietly. This setup classifies inbound email into five intents under Strict ambiguity — if nothing clearly fits, the model returns "Other" instead of forcing the nearest label, because in routing, a forced wrong label is silent and an "Other" is visible. Definitions carry the borders (Support Request is "an existing customer asking for help" — prospects asking questions are Sales Inquiry), and high/medium/low confidence enables auto-routing the clear cases.
How to use this resource
-
Classify before any human reads
The prompt runs on the raw email; quoted history and signatures don't derail a label decision the way they derail extraction.
-
Let Other be the safety lane
Everything the model can't confidently place lands in one reviewable bucket instead of five wrong ones.
-
Tune the Support/Sales border
"Existing customer" is the deciding phrase — if your prospects also ask product questions, the definitions are where you encode that.
Why This Works
- Strict + Other converts silent misroutes into visible review items
- Customer-status-based definitions resolve the commonest routing confusion
- Confidence output lets you automate the clear 80% and human-review the rest
Best for
- Inboxes where misrouted mail dies quietly
- Teams that want auto-routing with a human fallback lane
- Intent sets where "existing customer vs prospect" decides the route
Not for
- Extracting the sender's details and request — that's the Extraction Prompt Generator
- Drafting replies — routing decides the desk, not the answer
Use cases
- Routing a shared inbox to sales, support, and partnerships
- Catching press inquiries before they rot in the wrong queue
- Filtering spam without a separate spam model
FAQ
How does this prompt tell a Support Request from a Sales Inquiry?
Customer status decides it, not the topic. The label definitions fence 'Support Request' as 'an existing customer asking for help with the product,' while 'Sales Inquiry' is 'interest in purchasing, upgrading, or pricing details' — so a prospect asking a product question lands in Sales. If your prospects also raise support-style questions, rewrite those two definitions in the generated prompt to move that border before you run it.
When will the model return 'Other' instead of picking the closest of the five intents?
It returns exactly 'Other' whenever no label clearly fits, under the Ambiguity Policy that 'a forced wrong label is not' a valid answer. That rule is deliberately routing-flavored: one 'Other' surfaces in a single reviewable bucket a human can catch, so treat it as your fallback lane rather than a classification failure. It never invents a label outside the six defined.
Which confidence level should trigger a human review before auto-routing?
Hold the 'low' bucket for a person. The CONFIDENCE section attaches high, medium, or low to every label, where 'low' explicitly means 'the best available choice among the labels' rather than a real fit, and 'high' means the text 'unambiguously fits the definition.' Auto-route high and usually medium; review low. That level is self-reported by the model, not a computed score.
How do I parse the output when I run this over emails in bulk in ChatGPT or Claude?
Read the 'label' and 'confidence' keys from one JSON object per email, exactly like {"label": "Sales Inquiry", "confidence": "high"}. The OUTPUT RULES forbid any text around it and ban markdown code fences, so a strict parser works directly. Labels come back verbatim from the defined values with no paraphrasing or abbreviation, so you can key a routing table on those exact strings.
More resources from Data Classification Prompt
Resource
Text Classification Prompt — the Anatomy
The blocks a reliable classification prompt needs: defined labels, classification rules, edge-case rules, an ambiguity policy, and a confidence contract.
Resource
Categorize Customer Feedback with AI
Praise, Complaint, Feature Request, Bug Report, Question — multi-label feedback categorization where one message can carry three signals.
Resources that pair well
Resource
Extract Data From Text with AI
Free text in, named fields out. The extraction prompt pattern that turns any unstructured text into consistent, parseable records.
Resource
Force JSON Output from AI
Stop getting 'Sure, here is the JSON…' — the output-contract pattern that forces models to return only parseable JSON: schema, example, and a strict rule block.
Resource
Fix Invalid JSON from AI
The JSON won't parse and you can't see why. Deterministic cause-sniffing — trailing commas, single quotes, unclosed brackets — and the repair prompt that fixes it.
Related tools
Tool
Data Classification Prompt
Build classification prompts that assign labels from a closed set — with label definitions and edge-case rules.
Projects that use this resource
Project
Build a Programmatic SEO Site with AI
The full path to pages that rank at scale, not penalty bait — map the intents, build the data set, structure it, template the page, then QA before publishing hundreds.
Workflows that use this resource
Workflow
AI Programmatic SEO Workflow
Generate many intent-matched SEO pages from a template without the thin-content spam — map the search intents, define the page variables, build the template, and QA before publishing at scale.