B2B SDR Agent Template

Turn any B2B export business into an AI-powered sales machine in 5 minutes.

An open-source, production-ready template for building AI Sales Development Representatives (SDRs) that handle the full sales pipeline — from lead capture to deal closing — across WhatsApp, Telegram, and email.

Built on OpenClaw, battle-tested with real B2B export companies.

Architecture: 7-Layer Context System

┌─────────────────────────────────────────────────┐
│              AI SDR Agent                        │
├─────────────────────────────────────────────────┤
│  IDENTITY.md   → Who am I? Company, role        │
│  SOUL.md       → Personality, values, rules     │
│  AGENTS.md     → Full sales workflow (10 stages)│
│  USER.md       → Owner profile, ICP, scoring    │
│  HEARTBEAT.md  → 10-item pipeline inspection    │
│  MEMORY.md     → 3-engine memory architecture   │
│  TOOLS.md      → CRM, channels, integrations    │
├─────────────────────────────────────────────────┤
│  Skills        → Extensible capabilities        │
│  Product KB    → Your product catalog           │
│  Cron Jobs     → 10 automated scheduled tasks   │
├─────────────────────────────────────────────────┤
│  OpenClaw Gateway (WhatsApp / Telegram / Email) │
└─────────────────────────────────────────────────┘

Each layer is a Markdown file you customize for your business. The AI reads all layers on every conversation, giving it deep context about your company, products, and sales strategy.

Quick Start

Option A: OpenClaw Users (1 Command)

If you already have OpenClaw running:

clawhub install b2b-sdr-agent

Done. The skill installs the full 7-layer context system, delivery-queue, and sdr-humanizer into your workspace. Then customize:

# Edit the key files for your business
vim ~/.openclaw/workspace/skills/b2b-sdr-agent/references/IDENTITY.md
vim ~/.openclaw/workspace/skills/b2b-sdr-agent/references/USER.md

# Or copy to your main workspace
cp ~/.openclaw/workspace/skills/b2b-sdr-agent/references/*.md ~/.openclaw/workspace/

Replace all {{placeholders}} with your actual company info, and your AI SDR is live.

Option B: Full Deployment (5 Minutes)

1. Clone & Configure

git clone https://github.com/iPythoning/b2b-sdr-agent-template.git
cd b2b-sdr-agent-template

# Edit the 7 workspace files for your business
vim workspace/IDENTITY.md   # Company info, role, pipeline
vim workspace/USER.md       # Your products, ICP, competitors
vim workspace/SOUL.md       # AI personality and rules

2. Set Up Deployment Config

cd deploy
cp config.sh.example config.sh
vim config.sh               # Fill in: server IP, API key, WhatsApp number

3. Deploy

./deploy.sh my-company

# Output:
# ✅ Deploy Complete: my-company
# Gateway:  ws://your-server:18789
# WhatsApp: Enabled
# Skills:   b2b_trade (28 skills)

That's it. Your AI SDR is live on WhatsApp and ready to sell.

What It Does

Full-Pipeline Sales Automation (10 Stages)

Stage	What the AI Does
1. Lead Capture	Auto-detect inbound messages (WhatsApp/Telegram/CTWA ads), create CRM records
2. BANT Qualification	Natural conversation to assess Budget, Authority, Need, Timeline
3. CRM Entry	Structured data capture — name, company, country, ICP score, product interest
4. Research & Enrichment	Jina AI web search + company website analysis, 3-layer enrichment pipeline
5. Quotation	Auto-generate PDF quotes, multi-language, send to owner for approval
6. Negotiation	Track counter-offers, recommend strategy, escalate when needed
7. Reporting	Daily 09:00 pipeline reports, 15:00 stalled alerts, weekly summaries
8. Nurture	Automated follow-ups, industry news, post-sale care, quarterly check-ins
9. Email Outreach	Personalized cold email sequences (Day 1/3/7/14), auto follow-up
10. Multi-Channel Orchestration	Cross-channel coordination (WhatsApp + Email + Telegram), auto-switching

Automated Scheduling (10 Cron Jobs)

Schedule	Task
Every 30 min	Gmail inbox scan for client replies
Daily 09:00	Pipeline report to owner via WhatsApp
Daily 10:00	AI lead discovery (market rotation: Africa/ME/SEA/LatAm)
Daily 11:00	Email follow-up sequence check
Daily 15:00	Stalled lead detection
Weekly Wed	Nurture campaign
Weekly Fri	Competitor intelligence gathering
Weekly Mon	Weekly summary report

Human-Like Conversations

Responds in the customer's language (auto-detected)
Natural message pacing with delivery-queue skill (3-90s delays, message splitting)
Timezone-aware sending (7 market timezone mappings)
Cultural adaptation (Middle East, Africa, SEA, LatAm, Europe)
Never reveals AI identity — presents as your sales consultant

Dynamic ICP Scoring

Initial score based on 5 weighted dimensions (purchase volume, product match, region, payment ability, authority)
Auto-adjusts based on interaction: fast reply +1, asks for quote +2, mentions competitor +2, 7d no reply -1
Hot leads (ICP>=7) auto-flagged, owner notified immediately

Smart Memory (3 Engines)

Supermemory: Research notes, competitor intel, market insights — queried before outreach
MemoryLake: Session context, conversation summaries — auto-recalled per conversation
MemOS Cloud: Cross-session behavior patterns — auto-captured

Anti-Amnesia System (NEW)

AI agents lose context in long conversations and across sessions. Our 3-layer anti-amnesia architecture solves this:

Layer	Engine	What It Does
L1: MemOS	Structured memory	Extracts BANT, commitments, objections every turn. Injects into System Prompt at conversation start.
L2: Proactive Summary	Token monitoring	Compresses history at 65% context usage. Zero information loss — numbers, quotes, commitments preserved verbatim.
L3: ChromaDB	Long-term RAG	Stores every turn as embeddings. Auto-retrieves when customer references past conversations or returns after 7+ days.

Result: Your AI SDR remembers every customer, every quote, every commitment — even after 100+ turns or weeks of silence.

See ANTI-AMNESIA.md for the full implementation spec with code, prompts, and deployment guide.

The 7 Layers Explained

Layer	File	Purpose
Identity	`IDENTITY.md`	Company info, role definition, pipeline stages, lead tiering
Soul	`SOUL.md`	AI personality, communication style, hard rules, growth mindset
Agents	`AGENTS.md`	10-stage sales workflow, BANT qualification, multi-channel orchestration
User	`USER.md`	Owner profile, product lines, ICP scoring, competitors
Heartbeat	`HEARTBEAT.md`	Automated pipeline inspection — new leads, stalled deals, data quality
Memory	`MEMORY.md`	3-tier memory architecture, SDR effectiveness principles
Tools	`TOOLS.md`	CRM commands, channel config, web research, email access

Skills

Pre-built capabilities that extend your AI SDR:

Skill	Description
delivery-queue	Schedule messages with human-like delays. Drip campaigns, timed follow-ups.
supermemory	Semantic memory engine. Auto-capture customer insights, search across all conversations.
sdr-humanizer	Rules for natural conversation — pacing, cultural adaptation, anti-patterns.
lead-discovery	AI-driven lead discovery. Web search for potential buyers, ICP evaluation, CRM auto-entry.
quotation-generator	Auto-generate PDF proforma invoices with company letterhead, multi-language support.

Skill Profiles

Choose a pre-configured skill set based on your needs:

Profile	Skills	Best For
`b2b_trade`	28 skills	B2B export companies (default)
`lite`	16 skills	Getting started, low-volume
`social`	14 skills	Social media-focused sales
`full`	40+ skills	Everything enabled

Industry Examples

Ready-to-use configurations for common B2B export verticals:

Industry	Directory	Highlights
Heavy Vehicles	`examples/heavy-vehicles/`	Trucks, machinery, fleet sales, African/ME markets
Consumer Electronics	`examples/electronics/`	OEM/ODM, Amazon sellers, sample-driven sales
Textiles & Garments	`examples/textiles/`	Sustainable fabrics, GOTS certified, EU/US markets

To use an example, copy it into your workspace:

cp examples/heavy-vehicles/IDENTITY.md workspace/IDENTITY.md
cp examples/heavy-vehicles/USER.md workspace/USER.md
# Then customize for your specific business

Product Knowledge Base

Structure your product catalog so the AI can generate accurate quotes:

product-kb/
├── catalog.json                    # Product catalog with specs, MOQ, lead times
├── products/
│   └── example-product/info.json   # Detailed product info
└── scripts/
    └── generate-pi.js              # Proforma invoice generator

Control Dashboard

After deployment, your AI SDR comes with a built-in web dashboard:

http://YOUR_SERVER_IP:18789/?token=YOUR_GATEWAY_TOKEN

The dashboard shows:

Real-time bot status and WhatsApp connection
Message history and conversation threads
Cron job execution status
Channel health monitoring

The token is auto-generated during deployment and printed in the output. Keep it private — anyone with the URL+token has full access.

Security note: Set GATEWAY_BIND="loopback" in config.sh to disable remote dashboard access. Default is "lan" (accessible from network).

WhatsApp Configuration

By default, the AI SDR accepts messages from all WhatsApp contacts (dmPolicy: "open"). This is the recommended setting for sales agents — you want every potential customer to be able to reach you.

Setting	Value	Meaning
`WHATSAPP_DM_POLICY`	`"open"` (default)	Accept DMs from anyone
	`"allowlist"`	Only accept from `ADMIN_PHONES`
	`"pairing"`	Require pairing code first
`WHATSAPP_GROUP_POLICY`	`"allowlist"` (default)	Only respond in whitelisted groups

To change after deployment, edit ~/.openclaw/openclaw.json on the server:

{
  "channels": {
    "whatsapp": {
      "dmPolicy": "open",
      "allowFrom": ["*"]
    }
  }
}

Then restart: systemctl --user restart openclaw-gateway

Deployment

Prerequisites

A Linux server (Ubuntu 20.04+ recommended)
Node.js 18+
An AI model API key (OpenAI, Anthropic, Google, Kimi, etc.)
WhatsApp Business account (optional but recommended)

Configuration

All configuration lives in deploy/config.sh. Key sections:

# Server
SERVER_HOST="your-server-ip"

# AI Model
PRIMARY_API_KEY="sk-..."

# Channels
WHATSAPP_ENABLED=true
TELEGRAM_BOT_TOKEN="..."

# CRM
SHEETS_SPREADSHEET_ID="your-google-sheets-id"

# Admin (who can manage the AI)
ADMIN_PHONES="+1234567890"

Managed Deployment

Don't want to self-host? PulseAgent offers fully managed B2B SDR agents with:

One-click deployment
Dashboard & analytics
Multi-channel management
Priority support

Get Started →

Contributing

Contributions welcome! Areas where we'd love help:

Industry templates: Add examples for your industry
Skills: Build new capabilities
Translations: Translate workspace templates to other languages
Documentation: Improve guides and tutorials

License

MIT — use it for anything.

Built with ❤️ by PulseAgent
Context as a Service — AI SDR for B2B Export