Skip to main content
Intempt
Coming soon

Weekly CRM hygiene audit

Runs weekly filter queries across account and user records to surface stale records, missing required fields, and abandoned data for RevOps review.

Authored by Sid Chaudhary

Founder & CEO at Intempt

Agentic workflow

Coming soon

9 steps Blu runs end to end. It drafts a plan and nothing runs until you approve it.

  1. 1

    Turn cleanup into a routine

    Coming soon

    Blu builds a step

  2. 2

    Run it on Sunday night

    Coming soon

    Blu builds a step

  3. 3

    Find the duplicates

    Coming soon

    Blu builds a step

  4. 4

    Find the stale records

    Coming soon

    Blu builds a step

  5. 5

    Find the gaps

    Coming soon

    Blu builds a step

  6. 6

    Propose the merges

    Coming soon

    Blu builds a step

  7. 7

    Send the queue for approval

    Coming soon

    Blu builds a step

  8. 8

    Report the week's hygiene

    Coming soon

    Blu builds a step

  9. 9

    Publish and watch the trend

    Coming soon

    Blu builds a step

About this recipe

When to use it

CRM hygiene almost never happens on a schedule unless something forces it. This scans for duplicates, stale records, and missing fields every week and batches the fixes into a review queue.

What it delivers

Weekly, scans for duplicate accounts and users, stale records, missing required fields, and abandoned data, then AI-suggests merges and cleanups and batches them into an approval queue for RevOps review.

How you prompt this

Describe the outcome in your own words and Blu Agent maps it to this recipe, or run it by name. It drafts a plan first and nothing runs until you approve it.

Tell Blu Agent what you want

“Runs weekly filter queries across account and user records to surface stale records, missing required fields, and abandoned data for RevOps review.”

recipe.md preview

Built from the published catalog. Blu Agent's full step prompts load in your workspace when you run it.

Sign up to read the full recipe.md and run it with Blu Agent.

Sign up to see the full recipe

Inputs & outputs

What the recipe needs before it runs, and what it leaves in your workspace.

Inputs

  1. Nothing declared beyond an Intempt workspace. Blu asks for anything else it needs as it goes.

Outputs

    How the recipe runs

    Blu follows the steps in order and shows you each one before anything goes live.

    1. 01Turn cleanup into a routineCreate a workflow 'Weekly data quality audit' that scans the CRM for hygiene issues and produces a structured cleanup queue. Goal: replace the ad-hoc 'we should clean the CRM someday' problem with a continuous, low-effort hygiene program.
    2. 02Run it on Sunday nightThis step builds a workflow. Configure scheduled trigger: every Sunday night, run the full audit so the cleanup queue is ready for RevOps Monday morning. Skip if last audit completed within 5 days (avoid duplicate work). Use the result of "Turn cleanup into a routine".
    3. 03Find the duplicatesThis step builds a workflow. Configure find-records step that identifies likely duplicate Accounts (same domain, similar names, same legal name with different formatting) and likely duplicate Users (same email, same name+phone). Outputs: list of duplicate-candidate pairs/groups with similarity score. Use the result of "Turn cleanup into a routine", "Run it on Sunday night".
    4. 04Find the stale recordsThis step builds a workflow. Configure second find-records step for stale data: Accounts with no activity in 365+ days that aren't customers, Users with bounced emails older than 90 days, Deals stuck in early stages for 180+ days. These aren't always cuts (sometimes just need re-engagement) but they bloat reporting and slow segmentation. Outputs the staleness list with category labels. Use the result of "Turn cleanup into a routine", "Run it on Sunday night".
    5. 05Find the gapsConfigure third find-records step for incomplete records: Accounts missing industry / size / region, Users missing role / company, Deals missing close-date / amount. Outputs list of incomplete records by completeness category: informs whether to trigger enrichment workflows or queue for manual review. Use the result of "Turn cleanup into a routine", "Run it on Sunday night".
    6. 06Propose the mergesThis step builds a workflow. Configure AI research step that examines the duplicate candidates and suggests merge actions: which record is the survivor (most-complete, most-recent activity), what data to merge in from the duplicate, what conflicts to flag for human resolution (e.g. different industry classifications between dup records). Outputs structured merge-suggestions with confidence scores. Use the result of "Turn cleanup into a routine", "Find the duplicates", "Find the stale records", "Find the gaps".
    7. 07Send the queue for approvalConfigure webhook step that hands off the merge-and-cleanup queue to the bulk-update-review-workflow for human approval. Includes: total findings count, summary by category, AI-confidence distribution, links to the underlying records. RevOps reviews Monday morning, approves the high-confidence batch, manually handles the edge cases. Use the result of "Turn cleanup into a routine", "Propose the merges".
    8. 08Report the week's hygieneThis step builds a workflow. Configure Slack step posting the weekly hygiene report to #revops: duplicate count, stale count, incompleteness rate, week-over-week trends. Highlights celebrations (CRM completeness up 3%) and concerns (stale-record pile growing: symptom of slow follow-up upstream). Surfaces hygiene as an ongoing program, not a fire drill. Use the result of "Turn cleanup into a routine", "Propose the merges", "Send the queue for approval".
    9. 09Publish and watch the trendValidate and publish. Monitor: weekly run completion, find-volume trends (a growing pile suggests upstream issues: sales not closing out leads, no enrichment on signup), and post-cleanup CRM-completeness metric. The hygiene KPI nobody had before this workflow. Use the result of "Turn cleanup into a routine", "Report the week's hygiene".

    Install Intempt and run it

    1. 1

      Sign up

      Create a free Intempt workspace.

    2. 2

      Connect your data

      Add the sources this recipe reads from.

    3. 3

      Ask Blu

      Type /scheduled-data-quality-audit in Blu once this recipe is live there.

    4. 4

      Review and approve

      Blu builds each step and waits for your OK before anything goes live.

    Related recipes

    Sid ChaudharyDiscovery call qualification fieldsGenerates an AI summary for Discovery calls from meeting data using the qualification framework in the summary recipe.View recipe Sid ChaudharyPost demo nurtureKeeps a demo warm for 90 days with a playbook, a case study, an ROI calculator and a customer story, and pulls the AE in early if they bite.View recipe Sid ChaudharyReturn rate by categoryShows which product categories get returned most, and which ones have got worse since last quarter.View recipe

    More recipes by Sid Chaudhary

    Discovery call qualification fieldsGenerates an AI summary for Discovery calls from meeting data using the qualification framework in the summary recipe.View recipe Post demo nurtureKeeps a demo warm for 90 days with a playbook, a case study, an ROI calculator and a customer story, and pulls the AE in early if they bite.View recipe Return rate by categoryShows which product categories get returned most, and which ones have got worse since last quarter.View recipe

    Got a play worth sharing?

    Publish it to the Intempt Collective Marketplace and earn when other teams run it.

    Submit a recipe