Evidence the run may read
- Draft asset
- Approved brand language
- Product capability and evidence register
production blueprint · marketing
Brand and claim review agent blueprint.
Check draft copy against approved language, product evidence, and prohibited claims before it reaches publication.
Search intent: AI agent for marketing claim review
Published by a2a cloudProduct-source methodology →
01 · the contract
Start from a bounded job, not a blank chat box.
trigger
A customer-facing asset enters brand or product-claim review.
owner
marketing owner
agent stops at
Brand and relevant product owners approve the final claims.
KPI · decrease
unsupported claims published (claims). Count published claims later corrected for lack of product evidence.
outputs
Artifacts the run must produce
- Claim-by-claim evidence table
- Voice and terminology edits
- Unsupported claim 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 brand and claim review inputs.
- 02
claim extractor
Produce the claim-by-claim evidence table.
- 03
evidence matcher
Produce the voice and terminology edits.
- 04
brand reviewer
Challenge the brand and claim review result and prepare an approval packet.
- 05
marketing owner
Brand and relevant product owners approve the final claims.
intake→ validated input packet →claim-extractor
claim-extractor→ Claim-by-claim evidence table →evidence-matcher
evidence-matcher→ Voice and terminology edits →brand-reviewer
brand-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/marketing/brand-claim-review/inputs/**Read only the evidence attached to this workflow instance.
case outputs
workspace/marketing/brand-claim-review/outputs/**Write drafts and evidence artifacts without modifying source records.
approved tools
marketing:brand-claim-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: marketing-brand-claim-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 capability, number, and comparative statement is either evidenced, qualified, or removed.
Every capability, number, and comparative statement is either evidenced, qualified, or removed.
- 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 source of truth is contradictory or does not state the capability's deployment status.
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": "marketing-brand-claim-review",
"caller": "user:workflow-owner",
"task_id": "case_brand_claim_review",
"skill_name": "brand_claim_review",
"input_hash": "4d7c...9a2f",
"grant_ids": [
"grt_case_inputs",
"grt_tool_propose"
],
"status": "ok",
"result_preview": "Output prepared: Claim-by-claim evidence table. Human decision remains separate.",
"elapsed_ms": 4218
}related blueprints
Keep the operating model consistent.
Marketing
Source-backed content brief
Turn an approved topic, audience, and source set into a differentiated brief with claims and evidence mapped explicitly.
Marketing
Campaign quality assurance
Check campaign assets for message consistency, required links, approved claims, and channel-specific readiness.
Marketing
SEO content refresh
Compare a page with current first-party product truth and performance evidence and propose a focused refresh.
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.