Hire an AI appointment no-show analyst

Everything it can hand back

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

• A reconciled attendance table with the number each rate divides by
• A summary of 3 to 5 patterns in plain words, each with its numbers
• A note on how reminders line up with attendance, if you gave reminder records
• A list of gaps the records cannot answer
• A hand-back summary with one next step

How it does the job well

• Records must have names and contact details removed. If you see a name, phone number or email, stop and ask for a cleaned file. Do not copy it into any file you write.
• Never guess why someone did not come, and never profile people by age, gender, ethnicity, health or similar traits.
• Reminder links to attendance are correlation. Never write that reminders caused a change.
• Agree the question and the decision it supports before analysing.
• Check the data first: date range, grain, missing values, duplicates and definitions.
• Compare like with like: same period length, definitions and segments.
• Separate what the data shows from what it might mean, and give confidence levels.

Mistakes it avoids

• Reporting a change without checking whether tracking or definitions changed.
• Treating correlation as cause.
• Averages that hide important segments or outliers.

What a good result looks like

An example, not your task: Your calendar has gaps and you want to know which slots go empty most.

• Attendance table. Counts by group for booked, attended, no show, cancelled and rescheduled, with the base of each rate.
• Pattern summary. Three to five patterns in plain words, each with its numbers and group size.
• Reminder note. How reminder records line up with attendance, stated as correlation and not cause.
• Evidence gaps. What the records cannot show, such as why people missed a visit.
• Hand-back summary. Files saved, MISSING lines, checks missed and one next step.

How the work is checked

• Every rate states what it divides by.
• Cancellations and reschedules are not counted as no shows.
• No name or contact detail appears in any file you wrote.
• No sentence says reminders caused a change, or gives a reason for absence.
• 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

• Spreadsheet checker. Matches appointment IDs, statuses, dates and duplicate bookings. Applies only your definition of a no show and states each denominator. Hands the clean attendance table to the next step.
• Figures to plain pictures writer. Turns the checked table into plain words by the groups you gave. Shows what the numbers say without guessing why people missed visits or profiling anyone.

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 explain-appointment-no-show-patterns 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/explain-appointment-no-show-patterns/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

• Appointment records with names and contact details removed
• Your meaning of booked, attended, no show, cancelled and rescheduled
• The reporting period, such as the last 6 months
• Reminder records, if you send them (optional)
• The groups you want to compare, such as day, time or service (optional)

Helpful context (optional)

• Reminder send dates for each appointment.
• The status list from your booking system.

Tools and access

• A spreadsheet tool such as Excel or Google Sheets: Lets you open the attendance table and re-check a count. The AI cannot recalculate a workbook without one.
• Any good chat AI: Claude, ChatGPT and Gemini all handle a one-message prompt like this well.

Functions and deliverables

• Appointment no-show analyst: Check booking records and the rule for no-shows. Get a table and plain summary, with reasons left unknown unless supported.
  • A reconciled attendance table with the number each rate divides by
  • A summary of 3 to 5 patterns in plain words, each with its numbers
  • A note on how reminders line up with attendance, if you gave reminder records
  • A list of gaps the records cannot answer
  • A hand-back summary with one next step
• Spreadsheet checker: Check a spreadsheet for odd totals, broken formulas and messy data. Your original stays safe, and you get findings with proof and a new file.
  • A sheet inventory and scope
  • Findings with evidence locations
  • Data quality and formula issues
  • A new output file with your edits
  • Reconciliation results
  Source: Burhan Sebin.
• Numbers explainer: Turn the key figures in your talk into comparisons and counts of people your room can picture. Paste your figures and who will hear them.
  • The figures kept and set aside
  • A comparison, a count of people and a line to say for each
  • A test question for a non-expert
• Books reconciler and P&L narrator: Match your books to payment reports for the month. Flag mismatches, duplicate entries and missing receipts, then get a plain P&L story.
  • A list of mismatches
  • Flagged duplicates and missing receipts
  • A plain-language P&L summary
  • A step-by-step close checklist
  Source: Anthropic.
• Metric definition writer: Share a metric, calculation and business use. Get a YAML definition, validation results and questions for the data owner.
  • A filled metric, dimension or entity YAML
  • A validation report
  • dbt-ready field names
  • Notes on edge cases
  Source: Nimrod Fisher.

Tasks you can use it for

• Your calendar has gaps and you want to know which slots go empty most.
• You plan to change reminders and want a starting number to compare with.
• A manager asks whether Mondays or mornings are worse.
• Your booking system's no-show count and your own count do not match.

Limits to check before starting

• You want to judge or contact one person about a missed visit. Use your own records and your practice rules.
• You want proof that reminders cut no shows. This shows patterns only and cannot prove cause.
• Your records still have names and contact details. Remove them first. This workflow expects records with names removed.
• You only need to check a spreadsheet's totals. Use the Spreadsheet checker.

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.

• Download the handoff pack. It is a zip with HANDOFF.md and the skill files this workflow uses.
• Give the folder to Claude, ChatGPT or Gemini and say "Follow HANDOFF.md".
• Remove names, phone numbers and emails from the records. Keep one ID per appointment. Then attach them with your definitions.
• Read the attendance table first. Check the counts against what you know from your booking system.
• Use the patterns to choose one change to test, such as a reminder for the worst slot. Run it for a few weeks and compare.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/explain-appointment-no-show-patterns 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.