8080.AI
DesignReqsTasksUser FlowArchitecture
Log inSign up for free

onyx-section

bySujith A

# Section A — Core Reasoning Prompt ## System Prompt You are an appointment-risk reasoning agent for CareFirst Clinic. Your job is to assess whether a specific upcoming appointment is at risk of becoming a no-show and recommend an appropriate operational action for the front-desk coordinator, Meena. You must reason using **only the appointment data and other records returned by the available tools**. Do not use outside medical knowledge, demographic assumptions, or information that is not present in the data. ### Available signals Consider all relevant signals together: * Current appointment status * Appointment type * Appointment date and scheduled time * Patient's historical no-show count * Patient's historical reschedule count * How recently the appointment was confirmed * Whether the appointment has been confirmed at all * Expected consultation duration * Relevant information in the appointment notes * Other appointments or scheduling information returned by tools Do not treat any single field as automatically decisive. ### Reasoning rules 1. First gather the relevant data before making a recommendation. 2. Identify signals that increase the likelihood of a no-show. 3. Identify signals that decrease the likelihood of a no-show. 4. Look specifically for conflicting signals. 5. Give more weight to the **current appointment evidence** when historical and current information conflict, but do not ignore historical behavior. 6. If important information is missing, explicitly state what is missing and reduce confidence. 7. Never invent facts or probabilities that are not supported by the available data. 8. Do not recommend double-booking solely because an appointment appears risky. 9. Before recommending any scheduling action, inspect the relevant appointment/scheduling information returned by the tools. 10. If the available evidence is insufficient to make a reliable decision, escalate the case to Meena rather than guessing. ### Risk classification Classify the appointment into exactly one of: * **LOW RISK** — available evidence suggests the patient is likely to attend. * **MEDIUM RISK** — there are meaningful warning signals, but the evidence is mixed or incomplete. * **HIGH RISK** — multiple strong signals indicate a substantial attendance concern. * **UNCERTAIN — ESCALATE** — the available evidence is insufficient or contradictory enough that an automated decision would be unsafe. Risk classification must be evidence-based. Do not assign a risk level merely because one historical field is high. ### Action selection After determining the risk: * **LOW RISK:** No special intervention required. * **MEDIUM RISK:** Recommend confirmation/reminder follow-up. * **HIGH RISK:** Recommend proactive confirmation and flag the slot for Meena's attention. Consider whether the scheduling tools provide enough information to safely identify a replacement opportunity. * **UNCERTAIN — ESCALATE:** Do not automatically act. Explain what Meena needs to verify. A double-booking recommendation is allowed only when the available scheduling information supports it and the operational risk is acceptable. Never assume that a risky appointment can safely be double-booked. ### Output format Return a short briefing that Meena can act on: **Appointment:** [appointment ID] **Risk:** [LOW / MEDIUM / HIGH / UNCERTAIN — ESCALATE] **Confidence:** [High / Medium / Low] **Why:** * [Important positive signal] * [Important negative signal] * [Conflict or missing information, if applicable] **Recommended action:** [Clear action for Meena] **Escalation:** [State "No" or explain exactly what Meena needs to check] Do not output raw JSON, internal tool data, or unsupported claims. --- ## User Prompt Template Assess the following appointment. Appointment ID: {{appointment_id}} Use the available tools to retrieve any additional information required before making your decision. Follow the reasoning process in the system instructions. Pay particular attention to: 1. Historical attendance behavior 2. Current confirmation status 3. Recent confirmation activity 4. Rescheduling history 5. Appointment notes 6. Conflicting signals 7. Missing information 8. Whether any operational action can be taken safely Do not guess when the evidence is insufficient. If the case cannot be confidently resolved, classify it as **UNCERTAIN — ESCALATE** and explain what needs to be verified.

Appointment Risk Assessment
Appointment Risk Assessment

Comments (0)

No comments yet. Be the first!

System Requirements

System Requirement Document
Page 1 of 6

System Requirements Document for onyx-section

1. Introduction

The onyx-section project is designed for CareFirst Clinic to assess the risk of no-shows for upcoming appointments. The system will provide recommendations for operational actions to the front-desk coordinator, Meena, based on the assessment. The primary audience for this system includes appointment-risk reasoning agents and front-desk coordinators at CareFirst Clinic.

2. System Overview

The system will utilize available appointment data and records to determine the risk of a no-show for specific appointments. It will classify appointments into risk categories and recommend appropriate actions for Meena. The system will not use external medical knowledge or demographic assumptions, ensuring decisions are based solely on the data provided by the available tools.

2a. Product Interpretation and Delivery Boundary

The system is designed to operate within the boundaries of the CareFirst Clinic's appointment scheduling and management tools. It will not integrate external data sources or make assumptions beyond the provided data. The system will deliver risk assessments and recommendations directly to Meena, ensuring that all actions are evidence-based and within operational safety limits.

Page 2 of 6

2b. Source Content Inventory

Not applicable as there is no explicit content_source directive.

2c. Page Content and Component Coverage

Page 3 of 6

Appointment Risk Assessment

  • Information/State:

    • Appointment ID
    • Current appointment status
    • Appointment type
    • Appointment date and scheduled time
    • Patient's historical no-show count
    • Patient's historical reschedule count
    • Confirmation status and recent activity
    • Expected consultation duration
    • Appointment notes

  • Primary Actions:

    • Classify appointment risk (LOW, MEDIUM, HIGH, UNCERTAIN — ESCALATE)
    • Recommend operational action based on risk classification

  • Supporting Actions:

    • Retrieve additional appointment data using available tools
    • Identify conflicting signals and missing information

  • Domain Entities:

    • Appointment
    • Patient
    • Front-desk coordinator (Meena)

  • Component Responsibilities:

    • Data gathering and analysis
    • Risk classification
    • Action recommendation

  • States:

    • Loading: Retrieving appointment data
    • Success: Risk assessment completed
    • Error: Insufficient data or conflicting signals
    • Recovery: Escalation to Meena for further verification
Page 4 of 6

3. Functional Requirements

  • As an appointment-risk reasoning agent, I should gather relevant appointment data before making a recommendation. (explicit)
  • As an appointment-risk reasoning agent, I should classify the appointment risk into LOW, MEDIUM, HIGH, or UNCERTAIN — ESCALATE based on the evidence. (explicit)
  • As an appointment-risk reasoning agent, I should recommend an appropriate operational action for Meena based on the risk classification. (explicit)
  • As an appointment-risk reasoning agent, I should escalate cases to Meena when the evidence is insufficient or contradictory. (explicit)

4. User Personas

  • Appointment-Risk Reasoning Agent: Responsible for assessing appointment risks and recommending actions.
  • Meena (Front-Desk Coordinator): Receives risk assessments and operational recommendations to manage appointments effectively.

5. Core User Flows

  1. Appointment Risk Assessment Flow
    • Initiator: Appointment-Risk Reasoning Agent
    • Steps:
      1. Retrieve appointment data using available tools.
      2. Analyze data to identify risk signals.
      3. Classify the appointment risk.
      4. Recommend an action for Meena based on the classification.
      5. If evidence is insufficient, escalate to Meena with specific verification needs.
    • Outcome: Risk classification and action recommendation provided to Meena.
Page 5 of 6

6. Visuals Colors and Theme

[Default — not specified by user]

  • Primary Color: #0056b3 (Blue)
  • Secondary Color: #f0f0f0 (Light Gray)
  • Accent Color: #ffcc00 (Yellow)
  • Font Family: Arial, sans-serif
  • Type Scale: 1.0rem base, 1.25rem headings
  • Radius/Shape Language: 4px border radius
  • Spacing Rhythm: 8px grid
  • Imagery Style: Clean and professional

7. Signature Design Concept

The public entry page will feature a clean and professional layout with a focus on usability. The design will incorporate the primary blue color for headings and actions, with light gray backgrounds to ensure readability. The accent yellow will be used sparingly to highlight important actions or alerts.

8. Interaction Model & Motion Direction

  • Interaction Model: Static (direction)
  • Motion Tempo: Restrained
  • Hero Dimensionality: Flat
  • Landing Hero Motion Brief: The hero section will feature a static image of a calendar with highlighted appointment slots, emphasizing the focus on scheduling and risk assessment. The image will remain static to maintain a professional and straightforward user experience.
Page 6 of 6

9. Non-Functional Requirements

  • The system must ensure data privacy and security, adhering to relevant regulations and standards. (explicit)
  • The system should provide a response time of less than 2 seconds for risk assessment results. (basic_default)

10. Tech Stack

  • Frontend: React
  • Backend: Python/FastAPI
  • Database: PostgreSQL
  • Containerization: Docker
  • Orchestration: Kubernetes (if required for deployment)

11. Assumptions and Constraints

  • The system assumes that all necessary appointment data is accessible via the available tools.
  • The system will not integrate with external data sources beyond the provided tools.

12. Glossary

  • Appointment-Risk Reasoning Agent: The system component responsible for assessing appointment risks.
  • Meena: The front-desk coordinator at CareFirst Clinic who manages appointment scheduling and follow-ups.
  • No-Show: An appointment where the patient does not attend without prior cancellation or rescheduling.
Appointment Risk Assessment design preview
Appointment Risk Assessment: Gather appointment data
Appointment Risk Assessment: Identify risk signals
Appointment Risk Assessment: Classify appointment risk
Appointment Risk Assessment: Recommend operational action
Appointment Risk Assessment: Escalate to Meena
Appointment Risk Assessment design preview
Appointment Risk Assessment: Gather appointment data
Appointment Risk Assessment: Identify risk signals
Appointment Risk Assessment: Classify appointment risk
Appointment Risk Assessment: Recommend operational action
Appointment Risk Assessment: Escalate to Meena