Evidence the run may read
- RFP requirements and scoring rubric
- Supplier responses
- Authorized evaluator notes and scores
production blueprint · procurement
RFP evaluation packet agent blueprint.
Normalize evaluator evidence, surface scoring inconsistencies, and prepare a traceable decision packet for the sourcing committee.
Search intent: AI agent for RFP evaluation
Published by a2a cloudProduct-source methodology →
01 · the contract
Start from a bounded job, not a blank chat box.
trigger
Supplier RFP responses and authorized evaluator inputs are complete.
owner
procurement owner
agent stops at
The sourcing committee validates scores and makes the shortlist or award decision.
KPI · decrease
RFP evaluation rework (revisions). Count material score-matrix revisions after committee review begins.
outputs
Artifacts the run must produce
- Evidence-linked score matrix
- Scoring inconsistency report
- Committee decision packet
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 rfp evaluation packet inputs.
- 02
response mapper
Produce the evidence-linked score matrix.
- 03
score consistency analyst
Produce the scoring inconsistency report.
- 04
sourcing committee reviewer
Challenge the rfp evaluation packet result and prepare an approval packet.
- 05
procurement owner
The sourcing committee validates scores and makes the shortlist or award decision.
intake→ validated input packet →response-mapper
response-mapper→ Evidence-linked score matrix →score-consistency-analyst
score-consistency-analyst→ Scoring inconsistency report →sourcing-committee-reviewer
sourcing-committee-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/procurement/rfp-evaluation-packet/inputs/**Read only the evidence attached to this workflow instance.
case outputs
workspace/procurement/rfp-evaluation-packet/outputs/**Write drafts and evidence artifacts without modifying source records.
approved tools
procurement:rfp-evaluation-packet: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: procurement-rfp-evaluation-packet
version: 0.1.0
entrypoint: agent:BlueprintAgent
expose:
public: false
composition:
planning: deterministic_dag
max_nodes: 6
max_parallel: 3
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 packet preserves evaluator ownership and flags unsupported scores rather than averaging away disagreement.
The packet preserves evaluator ownership and flags unsupported scores rather than averaging away disagreement.
- 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.
Required responses, conflict disclosures, or evaluator evidence are incomplete.
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": "procurement-rfp-evaluation-packet",
"caller": "user:workflow-owner",
"task_id": "case_rfp_evaluation_packet",
"skill_name": "rfp_evaluation_packet",
"input_hash": "4d7c...9a2f",
"grant_ids": [
"grt_case_inputs",
"grt_tool_propose"
],
"status": "ok",
"result_preview": "Output prepared: Evidence-linked score matrix. Human decision remains separate.",
"elapsed_ms": 4218
}related blueprints
Keep the operating model consistent.
Procurement
Purchase request triage
Normalize a purchase request, identify missing business and approval context, and route it under the approved buying policy.
Procurement
Supplier discovery brief
Translate an approved sourcing need into neutral requirements, research questions, and a reviewer-controlled supplier discovery plan.
Procurement
Vendor comparison
Compare supplier responses against approved requirements and produce an evidence-linked matrix without choosing the winner.
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.