| name | intake-coordination-portal-audit |
| description | Produce the required normalized JSON audit for a Cedar Ridge Intake Coordination Portal task — patient access verification, referral readiness / referral-to-chart activation, dialysis transfer review, or program enrollment panel. Use when a task points at an intake-coordination portal base URL plus an answer_template.json and asks for a batch/roster/program-level JSON report of statuses, blockers, reason codes, and cohort counts. Covers how to discover the data, apply the classification rules, and emit template-conformant JSON. |
Intake Coordination Portal Audit
What this covers
A family of read-only clinical-operations audits served by an "Intake
Coordination Portal." Each task hands you:
- a prompt naming one target id — a roster, referral batch, transfer batch,
or program code — and a portal base URL (given as a placeholder such as
<TASK_ENV_BASE_URL>; read it from the task, never hardcode one);
- an
input/payloads/answer_template.json describing the exact JSON you must
return (required keys, per-item keys, allowed enum values, orderings, and
summary/count structure);
- an environment access note listing the portal's available read endpoints.
Your job is always the same shape: pull the target records plus their reference
data, classify each item into the template's controlled vocabulary, roll up
cohort counts, and return one JSON object, JSON only, no prose.
The five recurring task types and their per-type rules are in
reference/decision-rules.md. The portal's tables
and fields are in . Read the
matching playbook before writing code.
