What does a near-match customer problem look like during utility service set-up?
A utility connection task shows how an ambiguous customer match, handled wrongly, leads to a misdirected first bill and a concession applied to the wrong person.
A sales team lead approves a move-in application, APP-2187, for a residential electricity connection. The approval notes a concession card and a request for direct debit. The set-up officer's task is to turn that into a working service.
The agent searches for the customer and finds CUST-0932, a similar name at a previous address. The address differs and the date of birth field is blank, so the match is uncertain. The correct step is to create a new customer record, CUST-4410, and flag the near-match for review rather than merging.
It then opens service account SVC-7731 against premises reference PREM-5502, links the concession record, attaches a direct debit mandate MAND-0118 in pending status, and schedules the welcome notice for the billing team.
The state change is three new records, two links and one review flag, with no change to CUST-0932. In the failing variant, the agent merges into CUST-0932. The first bill then goes to the previous address and the concession is applied to the wrong person.
**What it teaches:**
- A near-match is a decision point that needs evidence, not a lookup that returns the top hit. - Consequences appear later, at billing, so a grader should inspect downstream state as well as the immediate writes. - Correct behaviour includes leaving existing records untouched.
Ambiguous matches are decisions, not lookups, and their consequences surface later in downstream state that a grader can inspect.
- Audience:
- Environment builders
- Content type:
- Scenario
- Buyer question:
- What it is and why it matters
Content release: r-a220eb6e099b243b
Related questions
- What is account set-up, and why does it matter for training and evaluating agents?
- What does a set-up decision look like when an applicant already exists in the system?
- Which signs show a set-up workflow is worth using for agent training or evaluation?
- Which upstream and downstream records does an agent link together during set-up?
- Why is account set-up harder for an agent than a single create call?
- How does set-up map onto an environment's entities, states and tool actions?