How to Automate Sales Deck Customization

This system automates sales deck customization by pulling prospect data from your CRM and generating tailored presentation slides. Every deck feels personal without manual work.

What You Need Before Starting

• Python 3.8+
• Claude or GPT API key
• Jinja2 for templating
• weasyprint for PDF generation

Step 1: Define Your Data Model

Set up the structure for sales decks records.

import json
import sqlite3
from datetime import datetime

def init_db():
    conn = sqlite3.connect("sales_decks.db")
    conn.execute("""CREATE TABLE IF NOT EXISTS sales_decks (
        id INTEGER PRIMARY KEY AUTOINCREMENT,
        deal_id TEXT, content TEXT, status TEXT DEFAULT 'draft',
        created_at TEXT, updated_at TEXT
    )""")
    conn.commit()
    return conn

Step 2: Pull CRM Context

Get deal and company data to populate your sales decks.

def get_context(crm_client, deal_id):
    deal = crm_client.get_deal(deal_id)
    company = crm_client.get_company(deal["company_id"])
    return {
        "deal_name": deal["name"],
        "company": company["name"],
        "industry": company["industry"],
        "amount": deal["amount"],
        "notes": deal.get("notes", ""),
    }

Step 3: Generate Content with AI

Use Claude to create customized sales decks content.

import anthropic

def generate_content(context):
    client = anthropic.Anthropic()
    message = client.messages.create(
        model="claude-sonnet-4-20250514", max_tokens=2000,
        messages=[{"role": "user",
            "content": f"Generate sales decks content for {context['company']} in {context['industry']}.\nDeal value: ${context['amount']:,.0f}\nNotes: {context['notes']}"}]
    )
    return message.content[0].text

Step 4: Format and Export

Create a professional output document.

def export_document(content, context, output_dir):
    filename = f"{context['deal_name']}_{datetime.now().strftime('%Y%m%d')}.md"
    path = os.path.join(output_dir, filename)
    with open(path, "w") as f:
        f.write(f"# {context['company']}\n\n{content}")
    return path

Step 5: Track and Measure

Log every document and track conversion.

def log_document(conn, deal_id, path, status="draft"):
    conn.execute(
        "INSERT INTO sales_decks (deal_id, content, status, created_at, updated_at) VALUES (?, ?, ?, ?, ?)",
        (deal_id, path, status, datetime.now().isoformat(), datetime.now().isoformat()))
    conn.commit()

What to Build Next

Track which slide combinations lead to the highest close rates.

Related Reading

• How to Automate Your Sales Pipeline Updates - automate sales pipeline updates
• Building Automated Sales Enablement Content - automated sales enablement content guide
• Cost of Manual vs Cost of Automated - cost manual vs automated operations