> ## Documentation Index
> Fetch the complete documentation index at: https://docs.orbitforms.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# AI SDR Qualifying

> Automatically classify inbound leads into qualification buckets using AI. Get human-readable reasoning and recommended next actions for every submission.

## Overview

The AI SDR Qualifying node acts like an intelligent sales development rep. Instead of using rigid rules or point-based scoring, it analyzes each lead holistically and classifies them into meaningful qualification buckets with clear reasoning.

### What makes it different

<CardGroup cols={2}>
  <Card title="Classification, not scoring" icon="target">
    Assigns leads to qualification buckets instead of numeric scores. Sales knows exactly what action to take.
  </Card>

  <Card title="Human-readable reasoning" icon="zap">
    Every classification comes with clear explanations your team can understand and trust.
  </Card>
</CardGroup>

## How to Use

<Steps>
  <Step title="Add the SDR Agent node">
    In your workflow, click "Add Node" and select "SDR Agent" from the AI Processing category.
  </Step>

  <Step title="Connect it after enrichment (recommended)">
    For best results, place the SDR Agent after a Clay enrichment node so the AI has company data to analyze.
  </Step>

  <Step title="Define your ICP">
    Write a description of your ideal customer profile. Be specific about company size, industry, and characteristics you're looking for.
  </Step>

  <Step title="Add disqualifiers (optional)">
    List lead types that should be automatically excluded, like students, freelancers, competitors, or job seekers.
  </Step>

  <Step title="Use the outputs downstream">
    Access classification results via template variables like `{{agent.bucket}}`, `{{agent.reasoning}}`, and `{{agent.recommended_action}}`.
  </Step>
</Steps>

## Configuration

### ICP Description (Required)

A free-text description of your ideal customer profile. The AI uses this to evaluate fit.

```
Example: "B2B SaaS companies doing $1M–$50M ARR with internal marketing teams that actively run paid ads."
```

### Disqualifiers (Optional)

Binary exclusions the AI should treat as hard stops. Leads matching these are automatically disqualified.

Examples: Students, Freelancers, Consultants, Agencies, Competitors, Job seekers.

## Qualification Buckets

The AI classifies each lead into one of five default buckets. You can customize bucket names, but the intent should remain the same.

| Bucket                          | Signals                                                                                                                        | Action                                                              |
| ------------------------------- | ------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------- |
| **High-Intent ICP Match**       | Company size aligns with ICP, Relevant senior job title, Active paid ads or growth signals, Clear problem statement or urgency | Immediate SDR outreach (high priority)                              |
| **Good ICP, Low/Medium Intent** | Right company and role, Weak or ambiguous timing, Research-oriented behavior                                                   | Personalized follow-up, light qualification, short nurture sequence |
| **Potential Future Fit**        | Too small today but growing, Early-stage team, Adjacent use case                                                               | Long-term nurture, educational content, periodic re-evaluation      |
| **Wrong ICP**                   | Wrong industry, Wrong business model, Wrong customer type                                                                      | Do not route to sales. Optional polite response or redirect.        |
| **Disqualified**                | Matches a disqualifier, Spam-like submission, Competitor or job seeker                                                         | No outreach. Silent drop or auto-response.                          |

## Output Variables

| Variable                       | Description                                    |
| ------------------------------ | ---------------------------------------------- |
| `{{agent.bucket}}`             | The assigned qualification bucket              |
| `{{agent.confidence}}`         | Confidence score from 0.0 to 1.0               |
| `{{agent.reasoning}}`          | Array of reasons explaining the classification |
| `{{agent.risks_or_unknowns}}`  | Any uncertainties or missing information       |
| `{{agent.recommended_action}}` | Suggested next step                            |

## Best Practices

* Be specific in your ICP description — the more context, the better the AI can classify leads
* Use enrichment data from Clay before the SDR Agent for richer classification
* Route high-intent leads to immediate notifications (Slack, email) and CRM creation
* Use a Filter node after SDR Agent to branch based on bucket (e.g., only send "High-Intent" to Salesforce)
* Review classification results periodically to refine your ICP description

## Example Workflow

A typical lead qualification workflow using the SDR Agent:

**Flow:** Form Submission → Clay Enrichment → SDR Agent → Router

**Router conditions:**

* High-Intent ICP Match → Slack notification + HubSpot
* Good ICP → Email nurture sequence
* Potential Future Fit → Add to long-term list
* Wrong ICP / Disqualified → No action

## Next Steps

<CardGroup cols={2}>
  <Card title="AI SDR Summarizer" icon="sparkles" href="/guides/ai-nodes/summarizer">
    Generate AI summaries of submissions
  </Card>

  <Card title="All Node Types" icon="layers" href="/guides/workflows/nodes">
    Explore all workflow nodes
  </Card>
</CardGroup>