Skip to Content
ScenariosOverview

Scenarios

The feature pages tell you what each piece is. These pages show three of them working together on a real job, start to finish — the same three scenarios the build guide uses to justify the skeleton (BG §1.8). Each one is runnable today against the local simulator, with no Anypoint credentials and no real gateway, so you can watch the governance branch execute in your own terminal before it ever runs on a customer’s data.

ScenarioThe jobWhat it exercises
Support triageDraft replies to a queue of support tickets; one carries PIITyped refusals (PIIDetected), correlation IDs, OTel spans — the shipped LangGraph demo, end to end
Nightly batchEnrich 50,000 records overnight against a windowed budget, unattendedBudget pacing (pace() / wait_for_reset()) and resume, driven by the simulator’s budget scenario
Internal copilotAn internal assistant whose output must clear a content-safety guardrailContentSafetyBlocked via the donkey-sim/content-safety sentinel, plus per-run correlation

“Scenario” means two different things in these docs — don’t conflate them. These pages are the three product scenarios (a job you’d actually run). The simulator’s --scenario flag names three failure-injection rules (pii_block, budget, injection). The pages below use those rules as the engine, but the job is the story.

What’s runnable, and what’s honest about being blocked

Support triage runs completely today — it is the Phase-1 acceptance artefact (BG §1.8), timed in CI so its first-run experience can’t rot. The nightly-batch and internal-copilot walkthroughs run their governed-call and refusal-handling paths against the simulator now; where a step depends on a surface that is still blocked on verification — MCP tool access, agent identity, the kill switch — the page says so in the reader’s terms and shows the shape without inventing an endpoint (verification discipline). A “blocked” note here means known, deliberate, and tracked, never guessed.

Last updated on