Evidence the run may read
- Opportunity snapshot
- Required-field and stage policy
- Recent approved activity summary
production blueprint · sales & revenue operations
CRM hygiene review agent blueprint.
Identify incomplete, stale, and contradictory opportunity fields and prepare proposed corrections for the record owner.
Search intent: AI agent for CRM data hygiene
Published by a2a cloudProduct-source methodology →
01 · the contract
Start from a bounded job, not a blank chat box.
trigger
A scheduled CRM quality review or stage change occurs.
owner
sales owner
agent stops at
The opportunity owner approves every CRM mutation.
KPI · increase
complete active opportunities (percent). Measure active opportunities passing the approved quality checks.
outputs
Artifacts the run must produce
- Field quality report
- Proposed corrections
- Owner question list
02 · topology
Small specialists. Named handoffs. One accountable decision.
Each stage produces an artifact another stage can inspect. The final node is a person, not an autonomous write to an external system.
- 01
intake
Validate and normalize the crm hygiene review inputs.
- 02
record validator
Produce the field quality report.
- 03
activity reconciler
Produce the proposed corrections.
- 04
sales operations reviewer
Challenge the crm hygiene review result and prepare an approval packet.
- 05
sales owner
The opportunity owner approves every CRM mutation.
intake→ validated input packet →record-validator
record-validator→ Field quality report →activity-reconciler
activity-reconciler→ Proposed corrections →sales-operations-reviewer
sales-operations-reviewer→ approval packet with evidence references →human-approver
03 · authority
Grant the run only what this case needs.
Source material is read-only. Drafts land in a case-specific output path. Tools may read or propose; the human gate owns the external write.
case inputs
workspace/sales/crm-hygiene-review/inputs/**Read only the evidence attached to this workflow instance.
case outputs
workspace/sales/crm-hygiene-review/outputs/**Write drafts and evidence artifacts without modifying source records.
approved tools
sales:crm-hygiene-review:read-or-proposeInvoke only tools explicitly granted for this run; external writes remain gated.
04 · implementation
A private, bounded starting manifest.
The blueprint starts private, caps its DAG, disables replanning, and exposes no public endpoint. Add only the tools and data adapters this workflow has approved.
a2a.yamlsafe starting point
name: sales-crm-hygiene-review
version: 0.1.0
entrypoint: agent:BlueprintAgent
expose:
public: false
composition:
planning: deterministic_dag
max_nodes: 6
max_parallel: 1
max_replans: 005 · acceptance test
Pass only with evidence.
- 01
Evidence traceability
Every material conclusion cites an input artifact or a scoped tool result from this run.
- 02
Proposed values are grounded in approved source activity and never fabricate a customer commitment.
Proposed values are grounded in approved source activity and never fabricate a customer commitment.
- 03
Approval boundary
The run stops at a proposal and records the human decision before any external side effect.
failure containment
Stop small. Preserve the evidence.
Recent activity cannot be attributed to the opportunity or source systems disagree.
Containment: Return a partial result with unresolved items; do not broaden scope or perform an external write.
Operator: Attach the missing evidence, narrow the brief, or explicitly approve a new scoped run.
A required input or tool grant is unavailable.
Containment: Stop the affected branch and preserve completed artifacts in the case output workspace.
Operator: Grant only the missing resource or continue with that branch marked out of scope.
06 · proof
Sign the run facts. Keep money in the billing ledger.
Current platform receipts sign caller identity or classification, skill, bounded input evidence, verified grant IDs when present, outcome or result preview, and timing. Optional file, tool, artifact, handoff, evaluation, and review fields require separate instrumentation and are not populated by default. Price, fees, payouts, and later human approvals remain separate platform records.
The example uses only fields populated by the current platform sealing paths. It is illustrative, not a record of a real customer run.
ExecutionReceipt · selected fieldsEd25519 token
{
"receipt_id": "rcpt_01J...",
"schema_version": 1,
"agent_name": "sales-crm-hygiene-review",
"caller": "user:workflow-owner",
"task_id": "case_crm_hygiene_review",
"skill_name": "crm_hygiene_review",
"input_hash": "4d7c...9a2f",
"grant_ids": [
"grt_case_inputs",
"grt_tool_propose"
],
"status": "ok",
"result_preview": "Output prepared: Field quality report. Human decision remains separate.",
"elapsed_ms": 4218
}related blueprints
Keep the operating model consistent.
Sales & Revenue Operations
Inbound lead qualification
Normalize an inbound request, compare it with an approved fit model, and prepare a routed qualification brief.
Sales & Revenue Operations
Account research brief
Turn approved public and internal account evidence into a sourced, time-stamped briefing for a seller.
Sales & Revenue Operations
Sales meeting preparation
Assemble approved account, opportunity, and prior-interaction evidence into an agenda and decision-oriented prep packet.
put the pattern to work
Start private. Scope the authority. Require the decision.
Deploy the workflow as a bounded internal agent, verify its outputs and the receipt fields actually emitted, then expand only the scopes your acceptance test proves it needs.