Evidence the run may read
- Stakeholder question and decision context
- Approved metric and data catalog
- Privacy, access, and delivery constraints
production blueprint · data & analytics
Analysis request scoping agent blueprint.
Turn a broad stakeholder question into a decision, metric, population, evidence, limitation, and delivery brief.
Search intent: AI agent for analytics request intake
Published by a2a cloudProduct-source methodology →
01 · the contract
Start from a bounded job, not a blank chat box.
trigger
A new analysis request enters the data team's queue.
owner
data owner
agent stops at
The stakeholder and analytics owner approve scope, definitions, access, and acceptance criteria.
KPI · increase
analysis requests accepted without rescoping (percent). Measure approved briefs completed without a material scope reset.
outputs
Artifacts the run must produce
- Decision-oriented analysis brief
- Data and definition requirements
- Limitations, owner, and acceptance criteria
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 analysis request scoping inputs.
- 02
question clarifier
Produce the decision-oriented analysis brief.
- 03
data feasibility mapper
Produce the data and definition requirements.
- 04
analytics lead reviewer
Challenge the analysis request scoping result and prepare an approval packet.
- 05
data owner
The stakeholder and analytics owner approve scope, definitions, access, and acceptance criteria.
intake→ validated input packet →question-clarifier
question-clarifier→ Decision-oriented analysis brief →data-feasibility-mapper
data-feasibility-mapper→ Data and definition requirements →analytics-lead-reviewer
analytics-lead-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/data/analysis-request-scoping/inputs/**Read only the evidence attached to this workflow instance.
case outputs
workspace/data/analysis-request-scoping/outputs/**Write drafts and evidence artifacts without modifying source records.
approved tools
data:analysis-request-scoping: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-analysis-request-scoping
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
The brief names the decision to inform and avoids promising causal or predictive conclusions unsupported by the design.
The brief names the decision to inform and avoids promising causal or predictive conclusions unsupported by the design.
- 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.
The decision, metric definition, population, required access, or delivery owner remains ambiguous.
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-analysis-request-scoping",
"caller": "user:workflow-owner",
"task_id": "case_analysis_request_scoping",
"skill_name": "analysis_request_scoping",
"input_hash": "4d7c...9a2f",
"grant_ids": [
"grt_case_inputs",
"grt_tool_propose"
],
"status": "ok",
"result_preview": "Output prepared: Decision-oriented analysis brief. 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
Dashboard quality review
Review a dashboard against approved metric definitions, queries, filters, freshness, accessibility, and decision purpose.
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.