Hire an AI clinic administrative queue reviewer

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• A delay map: each admin stage with typical and slow-case working and waiting time
• The stage that holds work up most, with a likely cause
• Staff hours against admin workload, with options and their trade-offs
• A list of data gaps, with what to start recording
• A check of your files for names and numbers before any analysis

How it does the job well

• Turn every request into owned actions: who, what and by when.
• Work from the real calendar, notes and lists. Never invent meetings, people or dates.
• Put the most important decision or deadline first, then the details.
• Prepare drafts and proposals. Sending, booking and changing records waits for approval.

Mistakes it avoids

• Analyzing a file that still holds names or numbers.
• Using wait time to say a patient is more or less urgent.
• Ranking stages when there are no timings.
• Treating options as decisions. The clinic's operations owner decides.
• Losing commitments buried in long notes.
• Mixing confirmed facts with guesses about other people's plans.

What a good result looks like

An example, not your task: Referral letters or records requests take longer than your clinic promises.

• Data check. Whether your files still hold names or numbers, and which column, before anything else runs.
• Delay map. Each admin stage with typical and slow-case working and waiting time.
• Slowest stage. The stage that holds work up most, with a likely cause and what to measure next.
• Capacity table. Admin hours needed against hours your staff have, by role, with gaps and spare time.
• Options. Ways to close the gap, each with what it frees and what it risks.
• Measurement gaps. Timings or owners you lack, and how to start recording them.

How the work is checked

• Only admin stages are measured. Queue time never sets clinical urgency or care priority, and no patient is ranked.
• No identifier appears anywhere in the results.
• Any ranking can be traced to supplied timings. Without timings there is no ranking.
• Staff hours match the rota the user gave.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

Capabilities

• Process bottleneck finder. Checks the files for names or numbers first and stops if it finds any. Then runs the stage math: typical time, slow-case time, waiting share and rework. Hands step 2 the stage workload and the ranked stages. If there are no timings, it hands over a plan for what to record. Check before moving on: every stage has an owner role and a unit.
• Team capacity planner. Sets the admin workload from step 1 against the staff you listed, keeping fixed duties and uncertainty visible. Returns options for the clinic operations owner to weigh. Check before moving on: staff hours come from your rota, not from a guess.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id measure-a-clinic-administrative-queue only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/measure-a-clinic-administrative-queue/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• Deidentified task records, one row per task and stage (from your practice system or a log you keep)
• The role that owns each stage, such as front desk or referral coordinator
• Working time and waiting time for each stage, as minutes or days
• The admin staff you have: roles, weekly hours and fixed duties
• Your service target for the queue, such as referrals sent within 3 days (optional)

Helpful context (optional)

• A rota showing real staff hours, not contracted hours.
• A named reviewer from clinic operations.

Tools and access

• A chat AI that can run Python code: The Process bottleneck finder uses small scripts for the stage math. Without code, the AI does the sums by hand and says so under CHECKS MISSED.
• Your practice management or task system: Export the task log from it, then remove identifiers before you share it.
• Any good chat AI: It needs your numbers pasted in. A tracker or calendar connection saves typing.

Functions and deliverables

• Clinic administrative queue reviewer: Share clinic admin records with names removed, task times and staff limits. Get a delay map, staffing options and data gaps.
  • A delay map: each admin stage with typical and slow-case working and waiting time
  • The stage that holds work up most, with a likely cause
  • Staff hours against admin workload, with options and their trade-offs
  • A list of data gaps, with what to start recording
  • A check of your files for names and numbers before any analysis
• Process bottleneck finder: Describe the process and any timing data. Get a swim-lane map, cycle-time estimates and likely bottlenecks ranked.
  • A swim-lane process map
  • A ranked list of bottlenecks
  • Cycle time figures per stage
  • A root-cause guess for each bottleneck
  • The share of time spent on real work
  Source: Alireza Rezvani.
• Team capacity planner: Give it your team and projects. Get workload against people, who is overloaded, and whether you can take on more.
  • A table of hours available, hours used and percent full for each person
  • A list of who is over or under their target
  • Which coming projects fit and which leave a gap
  • Three to five options with the hours each one frees up
  • One recommendation, and what would change it
  • A list of assumptions and missing facts
  Source: Anthropic.
• Operations staffing and capacity planner: Share demand patterns, handling time, staff time and service goals. Estimate queue staffing, workload risks and a quarterly hiring plan.
  • Staffing needed at three utilisation levels
  • Risk of breaching your service target
  • Team health verdict
  • A quarterly hiring plan for 12 months
  Source: Alireza Rezvani.
• me.md builder: Answer a few questions, or let your AI use what it remembers. Get one private file that tells any AI who you are.
  • One me.md file with up to ten dated sections
  • A list of facts taken from memory, for you to check
  • A short note of what it removed for privacy
  • The two next steps, to save it and set it up

Tasks you can use it for

• Referral letters or records requests take longer than your clinic promises.
• Your admin team is busy all day but the queue does not shrink.
• You are asked for evidence before adding a part-time admin role.
• A new process went in and you want to see if the waits changed.

Limits to check before starting

• You need to decide who is seen first or how urgent a case is. That is a clinical decision for clinical staff.
• Your files still hold names, dates of birth or patient numbers. Remove them first. This workflow stops when it sees them.
• You want one slow process mapped, outside a clinic. Use the Process bottleneck finder.
• You only need staff hours set against workload, with no stage times. Use the Team capacity planner.
• Work keeps missing deadlines across a whole team. Use the Recurring work delay reviewer workflow.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Before you share anything, remove names, dates of birth, addresses, phone numbers, emails, patient or record numbers and free-text notes. Use a task ID and role names. Your clinic's privacy rules decide what counts as deidentified, so ask your privacy lead if unsure.
• Open Claude, ChatGPT or Gemini. Pick one that can run Python code, since small scripts do the math.
• Add the workflow pack and your records, then say your service target and which roles are on the team.
• After step 1, check the delay map against what your staff say. Check that a stage ranked first really holds tasks up.
• After step 2, read the options with your clinic operations lead before changing any rota. Fill every MISSING line first.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/measure-a-clinic-administrative-queue for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.