Evidence the run may read
- Meeting purpose and participants
- Approved account and opportunity context
- Prior notes and open actions
Assemble approved account, opportunity, and prior-interaction evidence into an agenda and decision-oriented prep packet.
Search intent: AI agent for sales meeting prep
A customer meeting reaches its preparation window.
sales owner
The account owner approves the agenda, claims, and customer-facing material.
meetings with explicit next step (percent). Measure reviewed meetings that end with an owner and dated next step.
Each stage produces an artifact another stage can inspect. The final node is a person, not an autonomous write to an external system.
Validate and normalize the sales meeting preparation inputs.
Produce the meeting brief.
Produce the proposed agenda.
Challenge the sales meeting preparation result and prepare an approval packet.
The account owner approves the agenda, claims, and customer-facing material.
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.
workspace/sales/sales-meeting-prep/inputs/**Read only the evidence attached to this workflow instance.
workspace/sales/sales-meeting-prep/outputs/**Write drafts and evidence artifacts without modifying source records.
sales:sales-meeting-prep:read-or-proposeInvoke only tools explicitly granted for this run; external writes remain gated.
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.
name: sales-sales-meeting-prep
version: 0.1.0
entrypoint: agent:BlueprintAgent
expose:
public: false
composition:
planning: deterministic_dag
max_nodes: 6
max_parallel: 1
max_replans: 0Every material conclusion cites an input artifact or a scoped tool result from this run.
The brief distinguishes confirmed customer facts, internal assumptions, and questions to validate live.
The run stops at a proposal and records the human decision before any external side effect.
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.
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.
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.
{
"receipt_id": "rcpt_01J...",
"schema_version": 1,
"agent_name": "sales-sales-meeting-prep",
"caller": "user:workflow-owner",
"task_id": "case_sales_meeting_prep",
"skill_name": "sales_meeting_prep",
"input_hash": "4d7c...9a2f",
"grant_ids": [
"grt_case_inputs",
"grt_tool_propose"
],
"status": "ok",
"result_preview": "Output prepared: Meeting brief. Human decision remains separate.",
"elapsed_ms": 4218
}Normalize an inbound request, compare it with an approved fit model, and prepare a routed qualification brief.
Turn approved public and internal account evidence into a sourced, time-stamped briefing for a seller.
Identify incomplete, stale, and contradictory opportunity fields and prepare proposed corrections for the record owner.
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.