Evidence the run may read
- Dashboard specification and query metadata
- Approved metric definitions
- Freshness, audience, and accessibility requirements
production blueprint · data & analytics
Dashboard quality review agent blueprint.
Review a dashboard against approved metric definitions, queries, filters, freshness, accessibility, and decision purpose.
Search intent: AI agent for dashboard quality assurance
Published by a2a cloudProduct-source methodology →
01 · the contract
Start from a bounded job, not a blank chat box.
trigger
A dashboard enters publication or scheduled recertification review.
owner
data owner
agent stops at
The metric and dashboard owners approve publication, recertification, or retirement.
KPI · increase
certified dashboards passing first review (percent). Measure dashboards accepted without a material metric or query correction.
outputs
Artifacts the run must produce
- Metric and query consistency report
- Usability and freshness checklist
- Publish or remediate recommendation
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 dashboard quality review inputs.
- 02
query and metric validator
Produce the metric and query consistency report.
- 03
visual decision reviewer
Produce the usability and freshness checklist.
- 04
business intelligence owner
Challenge the dashboard quality review result and prepare an approval packet.
- 05
data owner
The metric and dashboard owners approve publication, recertification, or retirement.
intake→ validated input packet →query-and-metric-validator
query-and-metric-validator→ Metric and query consistency report →visual-decision-reviewer
visual-decision-reviewer→ Usability and freshness checklist →business-intelligence-owner
business-intelligence-owner→ 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/data/dashboard-quality-review/inputs/**Read only the evidence attached to this workflow instance.
case outputs
workspace/data/dashboard-quality-review/outputs/**Write drafts and evidence artifacts without modifying source records.
approved tools
data:dashboard-quality-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: data-dashboard-quality-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
Every displayed metric maps to a governed definition and the dashboard states period, filters, freshness, and intended decision.
Every displayed metric maps to a governed definition and the dashboard states period, filters, freshness, and intended decision.
- 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.
Rendered behavior, query metadata, metric versions, or audience requirements are unavailable.
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": "data-dashboard-quality-review",
"caller": "user:workflow-owner",
"task_id": "case_dashboard_quality_review",
"skill_name": "dashboard_quality_review",
"input_hash": "4d7c...9a2f",
"grant_ids": [
"grt_case_inputs",
"grt_tool_propose"
],
"status": "ok",
"result_preview": "Output prepared: Metric and query consistency report. Human decision remains separate.",
"elapsed_ms": 4218
}related blueprints
Keep the operating model consistent.
Data & Analytics
Data quality incident triage
Correlate a data-quality alert with pipeline, lineage, freshness, and change evidence and prepare a bounded response packet.
Data & Analytics
Metric definition review
Compare a proposed metric with source fields, grain, filters, time rules, and existing definitions before governance approval.
Data & Analytics
Data lineage impact analysis
Trace a proposed upstream change through documented datasets, transformations, metrics, and owners and prepare an impact 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.