Guide to AI in sales

How Do I Use Claude in Sales? Built layer by layer

Claude does not replace sales. It becomes the thinking layer between your data, your channels and your team.

of sales professionals use AI several times a week

81%

of sales professionals use AI several times a week

Haufe/HdWM 2026
of companies use AI in sales

14%

of companies use AI in sales

Bitkom 2026
use a sales tool for it

< 2%

use a sales tool for it

Haufe/HdWM 2026

People already use AI. As a sales process, it is missing almost everywhere.

Portrait of Otto Lang, co-founder and managing director of Sales AutomationBy Otto LangReading time: about 9 minutes
The frameworkSales in five layers
  1. 1 · DataWho do you want to reach?
  2. 2 · ThinkingThis is where Claude works, with skills and MCP.
  3. 3 · ChannelsEmail, LinkedIn, phone that actually arrive.
  4. 4 · The person as conductorAsks, decides, holds the conversation.
  5. 5 · LearningMeasure what works.

What you learn flows back.

Self-test · 1 minute

Where does your sales team stand?

How does your sales team use AI today?

Chapter 1 of 7

Layer 1 · Data: Who do you want to reach?

Claude knows nothing about your customers until you tell it. So the start is not a prompt, but the question of who fits you.

Prompt to try

Here are our ten best customers with industry, size and region: [list]. What do at least seven of them have in common? Turn that into an ideal customer profile in three sentences and name two attributes you are unsure about.
A first ICP draft. More in the guide "How to create an ideal customer profile".

Next, it matters where your data lives. In a Salesforce vendor study, 44 percent of German sales organizations say disconnected systems slow down their AI projects.

Do it today

Write down your ten best customers and try the prompt above.

Chapter 2 of 7

Layer 2 · Thinking: Claude with skills and MCP

This is where Claude works. There are four ways to use it. Each builds on the one before, and not every team needs all of them.

Four ways to use Claude in sales
WayWhat happensExample
ChatYou ask, Claude answers.Summarize a company before the meeting.
SkillClaude follows a written-down process.Every research brief has the same structure.
MCPClaude works directly in your software.Find matching leads and create a list.
RoutineClaude handles tasks at set times.Every morning: new replies, sorted.

What is a skill?

A written work instruction for Claude, like the onboarding folder for a new colleague. Claude follows it the same way every time.

Example: the skill "Research before the first call"

When
"Prepare me for the meeting with company X."
Steps
Read the website and news, name three reasons to reach out, suggest two questions.
Limits
No figures without a source.
Result
One page, read in five minutes.

What is an MCP server?

An adapter that lets Claude work inside another application: search leads, create campaigns, read replies. The server decides what is allowed, not the AI.

How Claude works with your sales platform via MCP
  1. Step 1

    You ask

    "Find twenty machine builders in Bavaria with a new head of sales."

  2. Step 2

    Claude plans

    A skill sets out the steps.

  3. Step 3

    MCP server

    Checks permissions, runs only what is allowed.

  4. Step 4

    Platform

    Companies, contacts, campaigns, inbox.

  5. Step 5

    Result

    A list, ready for approval.

Simplified. The MCP server decides which actions are allowed.

MCP and API settings page in the Sales Automation platform with endpoints and instructions for connecting Claude
In the platform: MCP and API, with instructions for connecting Claude.

Key takeaway

A skill tells Claude how something is done. An MCP server lets Claude do it.

Chapter 3 of 7

Layer 3 · Channels: Why emails do not fail because of the text

Claude writes an email in seconds. Whether it arrives depends on domains, settings and limits.

If you cut corners here, you risk your own company domain. Then even proposals to existing customers land in spam.

Mailbox provider requirements for bulk senders
RuleGoogleYahooMicrosoft
SPF and DKIMrequiredrequiredrequired
DMARCat least p=noneat least p=noneat least p=none
One-click unsubscriberequiredrequiredrecommended
Complaint ratebelow 0.3%below 0.3%no number
  1. 1

    Separate sending domains

    Never run cold outreach on your main domain.

  2. 2

    Warm-up

    New mailboxes start small. This takes weeks.

  3. 3

    Clean addresses

    Verify before sending. Every bounce hurts.

  4. 4

    Limit volume

    More volume means more mailboxes, not more emails per mailbox.

  5. 5

    Monitor

    Keep measuring complaints and spam placement.

Interactive checklist

Are you ready to send?

Tick off what you have in place.

  • What does that mean?

    If a sending domain loses its reputation, your main domain stays clean.

  • What does that mean?

    Without them, mailbox providers cannot check that the email comes from you.

  • What does that mean?

    Google, Yahoo and Microsoft require at least p=none.

  • What does that mean?

    A fresh mailbox sending lots of emails looks like spam.

  • What does that mean?

    More volume through more mailboxes, not more emails per mailbox.

  • What does that mean?

    Hard bounces show that the list is out of date.

  • What does that mean?

    It also lowers the number of spam reports.

  • What does that mean?

    Google names 0.3 percent as the upper limit, better below 0.1 percent.

  • What does that mean?

    In Germany, the UWG and the GDPR apply. This item is not legal advice.

0/9

Basics first.

Before Claude writes the first email, the technology has to be in place.

Claude alone is not enough here

Domains, warm-up, limits and monitoring need a system that runs around the clock. In Germany, promotional emails fall under the UWG and the GDPR; clarify this with your legal advisor.

Chapter 4 of 7

Layer 4 · The person: Why it rarely fails because of the technology

The tools are there. What holds teams back is uncertainty, missing know-how and habit.

What holds companies back is law, cost and acceptance, not the technology.

Hurdles for companies that use AI · Multiple answers, 2026

  • Data protection66 %
  • Legal uncertainty56 %
  • Costs hard to predict54 %
  • Lack of team acceptance42 %
  • Poor results26 %

Source: Bitkom press release of 14 Sep 2026 (603 companies with 20+ employees)

Companies say they train. Little of it reaches the people.

AI training from two perspectives · 2026

  • Companies: "We train on AI"70 %
  • Employees: "I was trained"21 %
  • Employees: "There is no offer"37 %

Sources: Bitkom, 14 Sep 2026 and 28 Apr 2026

Our view: the salesperson becomes a conductor. They do not have to play every instrument, but they need to know when each one comes in. That takes good questions, analytical thinking and the will to keep learning.

  1. 1

    Start with one task

    Not "introduce AI" but: two weeks of call preparation with Claude.

  2. 2

    Capture your best people

    Write down your most successful colleague's process as a skill.

  3. 3

    Train for real

    Short and based on your own cases. The EU AI Act requires measures for AI literacy.

  4. 4

    Talk about roles openly

    What goes away, what becomes more important? Silence creates resistance.

Your question

If Claude took over all research tomorrow, what would your team do with the time?

Chapter 5 of 7

Layer 5 · Learning: measure and build routines

What works only shows in the numbers. Claude can read them for you every week.

  • Every morning: sort new replies by interest, question and rejection.
  • After every call: pull tasks and objections out of the transcript.
  • Every week: which audience replies, which reason to reach out works?

The capabilities are here. How many routines run at once is, in the end, a question of computing power.

Chapter 6 of 7

Where sales automation comes in

Claude is strong at thinking. A sales automation platform is strong at doing: data, sending, inbox. The two work together through its MCP server.

Who does what?
TaskClaudePlatformPerson
Target accountssuggests a profileprovides companies and contactsdecides
Researchsummarizesprovides signalschecks
Messageswrites draftssends safelyapproves
Repliessortscollects all channelsholds the conversation
Learninganalyzesmeasuresdraws conclusions
Lead database in the New search tab with columns for job title, employees, revenue and industries. Names are blurred.
The data Claude accesses via MCP. Names are blurred.

Strategy call

What would this look like for you?

We show you, using your own case, how data, Claude and sending work together. 30 minutes, no strings attached.

Chapter 7 of 7

Sources

Portrait of Otto Lang, co-founder and managing director of Sales Automation

About the author

Otto Lang

Co-Founder and Managing Director, Sales Automation GmbH

Otto Lang is co-founder and managing director of Sales Automation GmbH in Munich. He sold his first B2B sales automation company in 2022 and founded Sales Automation GmbH with Anton Lang in 2024.

He builds the platform this guide is based on and is available to customers in day-to-day projects. The examples and steps come from working with mid-sized B2B companies.

Frequently asked questions about Claude in sales

How do I use Claude in sales?

Layer by layer: first be clear about who you want to reach, write down good processes as skills, connect Claude to your sales platform via MCP and secure deliverability before volume goes up.

What is a skill in Claude?

A written work instruction for a recurring process. Claude loads it when the task fits and follows it the same way every time.

What is an MCP server?

MCP stands for Model Context Protocol, an open standard. An MCP server is an interface through which Claude works in another application, for example to search leads or create campaigns. The server decides what is allowed.

Can Claude send emails to prospects by itself?

Technically, yes. But cold outreach needs separate sending domains, warm-up, sending limits, one-click unsubscribe and monitoring. A sending platform that Claude works with via MCP handles that better.

What most often makes AI adoption in sales fail?

Rarely the technology. Companies name data protection, legal uncertainty, costs and a lack of acceptance in the team.

How does AI change the role in sales?

The salesperson becomes a conductor: they keep the overview, ask good questions and decide. Analytical thinking and continued learning become more important.

Next step

Would you like to see how we solve this?

In a strategy call, we show you, using your own case, how Claude, data and sending work together in the platform.