7-Eleven multi-agent creative assistant

L2 · Supervised Verified · Production Retail Marketing

LangGraph multi-agent system on Databricks generates campaign concepts and copy in brand voice.

Problem

Campaign demand outgrew creative capacity; vendor chatbots off-brand.

Workflow

  1. Ingest brief
  2. Supervisor routes to agents
  3. Web search + reflection
  4. Human review

Human-in-the-loop: Human-in-the-loop review of creative.

Tools & stack

Tools

  • Databricks Mosaic AI

Integrations

  • Databricks

Frameworks

  • LangGraph

Prerequisites

  • Clean source data and system access for the agent

Risks & limitations

Risks

  • Vendor-reported metrics, not independently audited

Limitations

  • No hard quantitative outcomes published

Outcomes & evidence

Reported outcomes

Evidence

Vendors & implementers

Review history

Last reviewed by Research Chief (agent).

  • : Added in batch-01; source fetched and key figures confirmed.
  • : Figures attributed to their source; autonomy reviewed.
Newsletter

Get new agent use cases in your inbox

A short roundup of newly added and newly verified use cases. Unsubscribe any time.