In partnership with

Compound Leverage

Today’s newsletter is brought to you by Artisan. Read more on Artisan, Automate Your Outbound Sales With an AI-First Platform Powered by AI Employees, learn more below my signature or by clicking the link.

You get this email because you subscribed to it at compoundleverage.com or are one of our THINK School, AI Scout, or Cut a Manual Task with AI customers or prospects.

If you no longer interested in receiving our emails, feel free to unsubscribe in the email footer anytime.

The other day, I was on a call with a client who runs a sales team.

His CRM records all sales calls and he's built a call scoring system, but doesn’t consistently review the calls.

They're sitting on a gold mine of insights.

He told me "I saw a demo call analysis with AI" he told me, I have the Loom video and want to share it with you.

I watched the video, it was a demonstration of a CustomGPT for sales call analysis.

CustomGPTs are great but it means uploading everything to ChatGPT without advanced AI skills

He wanted a better way - one that works where his data lives and shows patterns across all calls.

I explained to him how to build a sales call review agent with Claude Code that works where his data sits, Google Drive folders without manually uploading the files or building Zapier automations.

Here's the step-by-step process I walked him through:

Step 1: Task - Define Your Call Review Goals

Get clear on what you want from your call scoring:

• Track objection patterns

• Rate call quality against your scorecard

• Find successful closing techniques

• Spot missed opportunities

• Measure improvement over time

The clearer your goals, the better your agent will perform.

Step 2: Hypothesis - Design Your Claude Code Agent

This is where Claude Code shines over Custom GPTs:

1. Install Claude Code on your computer

2. Point it to your call transcript repository in your file system

3. Create your agent with:

4. Tell it about your call scoring system

5. Define what "good" looks like based on your team's standards

Step 3: Invest - Build Your Review Workflow

The key difference is how it fits into your workflow:

• Set up automatic analysis after calls end

• Create dashboards to track scores by rep

• Generate highlight reels of top techniques

• Feed insights back to your training system

Pro tip: Have your agent categorize objections and create a "cheat sheet" for handling each one.

Step 4: Network - Scale Across Your Team

Here's where you get the big wins:

• Compare performance across reps

• Identify what top performers do differently

• Create training modules from real calls

• Build a library of successful responses to objections

A client told me: "Now we know exactly why our top rep closes twice as many deals."

Step 5: Knowledge - Improve Your Process

The real magic is in the feedback loop:

• Update your call scripts based on what works

• Create targeted coaching for each rep

• Track improvement in specific areas

• Test new approaches and measure results

Unlike Custom GPTs that work in isolation, Claude Code creates a system that learns with each call.

The setup takes a little over an hour, but saves hours of listening and analysis time.

Your sales gold is waiting in those call recordings.

Why leave it buried?

If you spend too much time reviewing emails and taking meeting notes, check out our sponsor, Artisan. It creates AI Employees to handle outbound sales.

To inquire about sponsoring the newsletter hit reply.

Marvin

Try Artisan’s All-in-one Outbound Sales Platform & AI BDR

Ava automates your entire outbound demand generation so you can get leads delivered to your inbox on autopilot. She operates within the Artisan platform, which consolidates every tool you need for outbound:

• 300M+ High-Quality B2B Prospects, including E-Commerce and Local Business Leads

• Automated Lead Enrichment With 10+ Data Sources

• Full Email Deliverability Management

• Multi-Channel Outreach Across Email & LinkedIn

• Human-Level Personalization

Book a demo to see what Ava can do.