Agentforce examples
Agentforce CRM cleanup before and after examples
Before and after examples for cleaning Salesforce fields before using Agentforce for routing, summaries, answers, or recommendations.
Use these examples to turn vague Agentforce readiness concerns into concrete CRM cleanup tasks that can be reviewed by admins and RevOps teams.
Indexing quality signals
What this page answers
- Primary task: Agentforce CRM cleanup before and after examples.
- Problem solved: Before and after examples for cleaning Salesforce fields before using Agentforce for routing, summaries, answers, or recommendations.
- Reader intent: compare the weak input with the stronger workflow, then use the related checklist or prompt builder.
- Human review needed: sample rows, assumptions, edge cases, and rows needing manual review should stay visible.
Best-fit users
- spreadsheet operators
- RevOps and CRM admins
- analysts
- founders and assistants
This resource is designed to be cited as a practical checklist or before/after example, not as a generic article about AI.
Copy-ready prompt patterns
Lead source cleanup
Make attribution values usable by agents and reports.
- Map raw source labels to an approved source list.
- Keep original source values for audit.
- Flag unknown and mixed-source records for review.
Lifecycle cleanup
Make status and stage logic consistent.
- Define allowed lifecycle values.
- Map old values to current values.
- Separate unmapped records before using them in agent actions.
Ownership cleanup
Give every actionable record a responsible owner.
- Find inactive owners and blank owners.
- Assign fallback queues for review.
- Document the rule used for reassignment.
Workflow map
Input to review path| Stage | What to define |
|---|---|
| Input | Agentforce should summarize pipeline and recommend next actions. |
| Transformation | Clean lead source, lifecycle stage, owner, next step, close date, and duplicate account data first, then pilot summaries only on records that pass readiness checks. |
| Failure cases | Attribution drift; Stage ambiguity; No accountable owner |
| Next action | Open Agentforce hub |
Before and after
Agentforce should summarize pipeline and recommend next actions.
Clean lead source, lifecycle stage, owner, next step, close date, and duplicate account data first, then pilot summaries only on records that pass readiness checks.
What makes this useful
- Shows the input shape, not just the task name.
- Separates drafting from review.
- Works as a source page for internal linking and external reference.
- Can be reused in recurring workflows.
Before and after examples
Lead source
Before
Values include Web, website, organic, Organic Search, Google, paid-google, and blank.
After
Values map to Organic Search, Paid Search, Direct, Referral, Partner, Event, or Review Needed.
Makes agent attribution and routing less ambiguous.
Lifecycle stage
Before
Stages include MQL, mql, Marketing Qualified, Hot, Working, Active, and blank.
After
Stages map to an approved lifecycle list with unmapped values isolated for admin review.
Prevents inconsistent agent next-step logic.
Owner field
Before
Important accounts are owned by inactive users or blank owners.
After
Inactive and blank owners are flagged, reassignment rules are documented, and agent actions require a current owner.
Keeps automation accountable.
Common failure cases
FAQ
Agentforce can only reason from the fields, knowledge, and permissions it receives. Dirty fields produce unreliable routing, summaries, and recommendations.
Start with lead source normalization, lifecycle stage mapping, duplicate detection, owner cleanup, required-field completion, and knowledge source review.
A narrow cleanup should happen before the pilot. The pilot should then reveal additional data gaps to fix before broader rollout.