Complete AI Training
Sign inGet my AI kit

Your job's AI kit

Get your AI kit

Tell us who you are and what you do. We show you your kit right away and email you the link: skills, prompts, AI agents, MCP servers and courses for your job.

500+ jobs ready, and we make a kit for any other job. No payment needed to look.

Share

AI agent for crm managers

CRM Data Cleanup Agent

A clean, reliable CRM each week

CRM Data Cleanup Agent: what goes in, what the agent does and what you get

What it does

Clients rely on their CRM, but it gets messy fast with duplicates, blanks and stale contacts. On weekly cleanup day, this agent exports contacts and companies, then scans for duplicates, missing key fields, bad email formats and contacts with no activity in a long time. It proposes merges with evidence, such as a matching email or phone, and fills missing fields from email signatures or public company pages. Before applying more, it checks a sample of 20 proposed fixes. If the sample shows errors, it adjusts its matching rules and tries again. It keeps deletions separate from merges and fixes. The assistant approves merges, and the client approves every deletion. After applying approved changes, it recounts duplicates to confirm the cleanup worked and sends the client a log. Edge case: two contacts with the same name at different companies are never merged.

How it works

Follow the arrows from top to bottom. The orange dashed arrow is the loop: when a check fails, the agent goes back and tries again.

Start and resultWhat it doesA check on its own workWaits for your OKGoes back and retries
Yes, continueApprovedNo 1 STARTS WHEN Weekly cleanup day 2 USES A TOOL Export contacts and companies from the CRM 3 USES A TOOL Scan for duplicates, missing fields and bad formats 4 DOES Propose merges and field fixes with a reason foreach 5 CHECKS THE RESULT Is a sample of 20 proposed fixes correct? If not: adjust matching rules and propose again. Back tostep 4. 6 DOES Separate deletions from merges and fixes for review 7 YOU APPROVE Assistant approves merges, client approves deletions 8 USES A TOOL Apply approved changes and recount duplicates 9 RESULT Cleanup log sent to the client
Read the steps as a list
  1. Weekly cleanup day
  2. Export contacts and companies from the CRM
  3. Scan for duplicates, missing fields and bad formats
  4. Propose merges and field fixes with a reason for each
  5. Is a sample of 20 proposed fixes correct?If not: adjust matching rules and propose again. Back to step 4.
  6. Separate deletions from merges and fixes for review
  7. Assistant approves merges, client approves deletionsThe agent waits here for your OK.
  8. Apply approved changes and recount duplicates
  9. Cleanup log sent to the client

How it decides

It merges only when email or phone matches, and fills fields only from trusted sources.

  • Merge on email or phone match
  • Never delete without client approval
  • Inactive after 24 months flagged

Make it yours

Every agent is a starting point. You choose these settings for your own situation.

  • Match rules
  • Inactivity period
  • Fields to fill
  • Sample size

What keeps you in control

It always asks you first

  • Merges
  • Deletions

Hard limits

  • Never deletes records itself
  • Never adds contacts to mailing lists

It stops when

  • Done: cleanup applied
  • Stop: CRM access fails

Set it up

We guide you through the set-up, step by step

Members get the full set-up guide for this agent. No technical skills needed: you copy, paste and upload.

10 minto set it up in your AI
5 AIsChatGPT, Claude, Copilot, Gemini, Grok
  • One set of instructions to paste into your AI, with the clicks for ChatGPT, Claude, Microsoft 365 Copilot, Gemini and Grok
  • The agent then walks you through connecting your own data, one source at a time
  • A downloadable copy with the flow chart, the rules and the full guide
Get access to this agent

An example run

What happensThe Monday scan on August 11 found 180 possible duplicate contacts in the client's CRM. A 20-record sample check failed: 3 proposed merges joined people with the same name at different firms. The agent added a rule requiring a company match and proposed again. The new sample was clean. The assistant approved 141 merges and 60 phone format fixes. The client approved deleting 12 bounced contacts.

More agents for crm managers