Decision and workflow
LinenFlow is a fictional commercial linen provider. The system must decide whether a customer-operations answer is authorised, evidence-backed, and complete enough to send. It can explain approved policy and read scoped synthetic records, but it cannot change a quote, order, route, credit, or entitlement.
System approach
The MVP compares lexical, dense, and hybrid retrieval before wrapping the selected retriever in a constrained single-agent workflow. Retrieval is filtered by persona scope, tool arguments are validated, citations point back to versioned policy evidence, and a confidence gate routes uncertainty, conflicts, access violations, and authority requests to a human.
Baseline and evaluation
The offline evaluation contains 60 attributed synthetic cases across sales, fulfilment, service, access, clarification, conflict, and adversarial behavior. It records retrieval hit rate, workflow-status accuracy, citation correctness, tool selection, escalation accuracy, coverage, latency, and safe refusal.
Operational boundary
The agent is useful because it knows when not to guess. The project separates policy evidence from operational facts, labels the fictional business clearly, and treats prompt injection, stale policy, unavailable tools, and missing identifiers as first-class failure cases.
Reproducibility
The repository includes versioned policy fixtures, a scoped SQLite tool layer, an evaluation set, offline traces, monitoring reports, and a Streamlit presentation surface. All results shown here are portfolio evidence rather than observed production outcomes.
Selected evidence
Each visual answers a specific question about system behavior. Read the caption and limitation together.
