Evidence the run may read
- Submitted interviewer feedback
- Approved competency rubric
- Conflict and decision-process guidance
production blueprint · people operations
Interview evidence summary agent blueprint.
Organize submitted interviewer evidence by approved competency and surface missing or contradictory observations without recommending a hire.
Search intent: AI agent for interview feedback summaries
Published by a2a cloudProduct-source methodology →
01 · the contract
Start from a bounded job, not a blank chat box.
trigger
An authorized interview loop closes and submitted feedback is available.
owner
people operations owner
agent stops at
Authorized humans make and document every progression, selection, or rejection decision.
KPI · increase
decision meetings with complete evidence (percent). Measure authorized meetings with evidence for every reviewed competency.
outputs
Artifacts the run must produce
- Competency evidence matrix
- Missing and conflicting evidence list
- Decision-meeting question set
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 interview evidence summary inputs.
- 02
feedback normalizer
Produce the competency evidence matrix.
- 03
competency evidence mapper
Produce the missing and conflicting evidence list.
- 04
recruiting decision facilitator
Challenge the interview evidence summary result and prepare an approval packet.
- 05
people operations owner
Authorized humans make and document every progression, selection, or rejection decision.
intake→ validated input packet →feedback-normalizer
feedback-normalizer→ Competency evidence matrix →competency-evidence-mapper
competency-evidence-mapper→ Missing and conflicting evidence list →recruiting-decision-facilitator
recruiting-decision-facilitator→ 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/people-ops/interview-evidence-summary/inputs/**Read only the evidence attached to this workflow instance.
case outputs
workspace/people-ops/interview-evidence-summary/outputs/**Write drafts and evidence artifacts without modifying source records.
approved tools
people-ops:interview-evidence-summary: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: people-ops-interview-evidence-summary
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 summary preserves source attribution, excludes protected information, and provides no automated recommendation or score.
The summary preserves source attribution, excludes protected information, and provides no automated recommendation or score.
- 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.
Feedback lacks behavioral evidence, contains prohibited information, or was submitted outside the approved process.
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": "people-ops-interview-evidence-summary",
"caller": "user:workflow-owner",
"task_id": "case_interview_evidence_summary",
"skill_name": "interview_evidence_summary",
"input_hash": "4d7c...9a2f",
"grant_ids": [
"grt_case_inputs",
"grt_tool_propose"
],
"status": "ok",
"result_preview": "Output prepared: Competency evidence matrix. Human decision remains separate.",
"elapsed_ms": 4218
}related blueprints
Keep the operating model consistent.
People Operations
Role description review
Check a proposed role description for clarity, internal consistency, approved requirements, and accessible language before publication.
People Operations
Candidate intake completeness
Validate application completeness and scheduling prerequisites without ranking candidates or inferring suitability.
People Operations
Interview loop packet
Assemble an approved competency plan, interviewer assignments, and structured evidence forms for a recruiting coordinator.
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.