Operations

Route Sales Inquiries with AI Classification

Enterprise, SMB, Self-Serve, Partner — route inbound interest to the right sales motion, with Best Match because every inquiry needs a lane.

Open in Data Classification Prompt

Overview

Sales routing has a property moderation doesn't: every inquiry must go somewhere, now. This setup classifies inbound sales interest into four motions under Best Match ambiguity — the closest lane wins even on imperfect fit, because a slightly-wrong lane that responds beats a perfect lane that never hears about it. Definitions encode the routing signals (seats, security and procurement requirements → Enterprise; reseller or integration framing → Partner), and high/medium/low confidence tells the SDR team which auto-routes to double-check.

How to use this resource

Route on first touch

Best Match never refuses, so every inquiry gets a lane immediately — the speed your funnel actually needs.
Encode segment signals in definitions

Seat counts, procurement language, reseller framing — the definitions carry your segmentation playbook.
Spot-check medium and low

Confidence tells the SDR team which auto-routes deserve a second look before the rep invests time.

Why This Works

Best Match fits routing economics: a fast near-miss beats a slow perfect
Signal-bearing definitions make the routing auditable and tunable
Confidence creates a lightweight QA loop without slowing the funnel

Best for

Sales teams with distinct motions per segment
Inbound volume that outpaces manual routing
Funnels where response speed beats routing perfection

Not for

Qualification (Qualified/Nurture/Unqualified) — that's a different label set with Strict rules
Extracting the inquiry's details — extraction is the other tool

Use cases

Sending enterprise signals to enterprise reps on first touch
Keeping partner inquiries out of the customer pipeline
Routing every inquiry somewhere — fast — with a confidence trail

FAQ

How does this prompt decide between the Enterprise and Partner sales lanes?

By matching text against the definitions, not the label names: many seats or security and procurement requirements signal Enterprise, while a reseller, agency, or integration inquiry — "not a direct customer" — signals Partner. If two labels fit equally, it prefers the more specific definition. The data-classification-prompt outputs this classifier; the SDR team owns the final routing call, especially on medium and low confidence.

How should I read the confidence value before trusting an auto-route?

Confidence is self-reported, not computed: high means the text unambiguously fits, medium is a good fit with minor uncertainty, low is "the best available choice among the labels." Because the policy "never refuses," a low-confidence label is still a forced pick — spot-check medium and low before a rep invests time. It's a routing recommendation your team verifies, not a guaranteed segment.

Why does this classifier always pick a lane even when the inquiry is a poor fit?

Because routing needs every inquiry to go somewhere now. The AMBIGUITY POLICY says "Always return the closest label, even when the fit is imperfect. Never refuse to classify." If you instead want a Qualified/Nurture/Unqualified set with Strict rules that can withhold, notFor says that's a different label set to build in the tool.

Customize This Resource

Opens this setup in Data Classification Prompt. Generate to get the full classification prompt — then adjust the labels, ambiguity mode, and confidence output.

Open in Data Classification Prompt

Prompt Template

Copy it as-is, or use Open in Data Classification Prompt to load it pre-filled and customize it with your own context.

TASK
Route inbound sales inquiries to the right sales motion.
Assign exactly one of the labels defined below to the text in the input.

LABELS
- Enterprise: A large-organization inquiry — many seats, security or procurement requirements.
- SMB: A small-or-medium business inquiry with standard requirements.
- Self-Serve: An individual or small-team inquiry served by the standard signup flow.
- Partner: A reseller, agency, or integration partner inquiry — not a direct customer.

CLASSIFICATION RULES
- Read the entire text before deciding — the deciding signal may come late.
- Judge by content and intent, not by tone, length, or formatting.
- Match the text against the definitions, not just the label names.
- Use only the labels defined above — never invent a new label.

EDGE CASE RULES
- If the text fits more than one label, choose the one matching its primary purpose — what the writer mainly wants.
- If two labels fit equally, prefer the more specific definition over the more general one.

AMBIGUITY POLICY
- Always return the closest label, even when the fit is imperfect.
- Never refuse to classify.

CONFIDENCE
- With each label, report a confidence level: high, medium, or low.
- high = the text unambiguously fits the definition; medium = a good fit with minor uncertainty; low = the best available choice among the labels.
- Confidence reflects your certainty about the fit — it is self-reported, not computed.

OUTPUT FORMAT
Return your classification as a single valid JSON object with a "label" key and a "confidence" key.

EXAMPLE OF A VALID RESPONSE
{
  "label": "Enterprise",
  "confidence": "high"
}

OUTPUT RULES
- Return only the JSON object — no text before or after it.
- Do not wrap the output in markdown code fences.
- Return the label text exactly as defined above — no paraphrasing, no abbreviations, no new labels.

More resources from Data Classification Prompt

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.

Support

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.

Prompt Engineering

Resource

Categorize Customer Feedback with AI

Praise, Complaint, Feature Request, Bug Report, Question — multi-label feedback categorization where one message can carry three signals.

Product

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.

Prompt Engineering

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.

Prompt Engineering

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.

Engineering

Related tools

Tool

Data Classification Prompt

Build classification prompts that assign labels from a closed set — with label definitions and edge-case rules.

Structured Output

Tip: Save time by exploring related resources and tools that integrate with this resource.