Build a Complete Sales AI Agent in O137: Step-by-Step Guide

Create an AI agent that automatically qualifies leads, proposes personalized offers, and hands off to sales reps? It's possible in 45 minutes with O137. This practical guide shows each step from zero to a production-ready workflow connected to your CRM.

---

Context: The Perfect SDR AI Agent

Goal: An autonomous agent that handles 80% of inbound leads:

• Detects real intent
• Qualifies via CRM data
• Proposes the right offer
• Follows up intelligently
• Hands off to the right rep

Input: CRM lead, site visit, inbound email Output: Qualified opportunity + assigned task

---

Step 1: Define Role and Triggers

Clear agent roles

O137 SDR Agent = qualification + nurturing + handoff
❌ Does NOT: price negotiation, closing, technical support
✅ Does: detect intent, score, first offer, first sequence

5 concrete triggers

1. New CRM lead (form, outbound, inbound)
2. Pricing/demo page visit (session >3min)
3. Unanswered email (>72h)
4. Asset download (case study, pricing)
5. LinkedIn mention (comment, like)

---

Step 2: Agent 1 - Enrichment & ICP Scoring

O137 connections to configure (5min)

CRM: Salesforce/HubSpot (lead data)
Data: Clearbit/Apollo (firmographics)
Site: GA4 (page views, time)
Language: auto-detect (FR/EN/DE...)

Enrichment logic

1. Fetch lead data (CRM)
2. Enrich (Clearbit → revenue, tech stack, employees)
3. ICP score (0-100):
   - Priority sector? +25pts
   - Revenue >€10M? +20pts
   - Aligned tech stack? +15pts
   - Target region? +10pts

O137 prompt example:

"Analyze this lead against our B2B SaaS ICP:
- Sectors: [list]
- Min revenue: €10M
- Tech: [stack]
Give 0-100 score + 3 strong/weak signals"

---

Step 3: Agent 2 - Intent Detection

4 sales intents to classify

URGENT (40pts): pricing, demo, "how much", "integration"
COMPARISON (30pts): "vs [competitor]", "open source"
DISCOVERY (20pts): blog, use case, "solution"
DISGUISED SUPPORT (10pts): "problem with", "bug"

Analyzed inputs

- Page views (pricing=40pts, /demo=35pts)
- Text message (NLP intent)
- Traffic source (Google=20, LinkedIn=25)
- Timing (Monday 10am=bonus)

---

Step 4-5: Handoff & Routing

# Routing
if Condition("intent.score > 0.8"):
    handoff_sdr()
else:
    nurture_sequence()

---

Ready-to-Clone O137 Template

Total time: 45min for first workflow Scale: 1000+ leads/month with no human intervention ROI: 3 virtual SDRs from month 2

🚀 Clone this O137 template:
1. Import JSON workflow (attached file)
2. Configure your APIs (3min)
3. Test 10 real leads
4. Go live

---

Result: 80% of leads qualified automatically, reps focused on high value, +30% pipeline capacity.