implementation

Initialize Specialist Agents

Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.

Linked challenge: Oncology Decision Support Orchestration with OpenAI Agents SDK and o4-mini

Format

Text-first

Lines

Sections

Linked challenge

Oncology Decision Support Orchestration with OpenAI Agents SDK and o4-mini

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines

1 sections

No variables

0 checklist items

Using the OpenAI Agents SDK, define three agents: 'PathologyAgent', 'RadiologyAgent', and 'ClinicalLead'. The ClinicalLead should have a tool 'transfer_to_pathology' and 'transfer_to_radiology'. Configure all agents to use the 'o4-mini' model. Provide system instructions for each agent focused on gastric oncology.

Adaptation plan

Keep the source stable, then change the prompt in a predictable order so the next run is easier to evaluate.

Keep stable

Hold the task contract and output shape stable so generated implementations remain comparable.

Tune next

Update libraries, interfaces, and environment assumptions to match the stack you actually run.

Verify after

Test failure handling, edge cases, and any code paths that depend on hidden context or secrets.

Prompt diagnostics

Variables

Lists

Code blocks

Purpose

implementation

This prompt is mostly narrative and instruction-driven, so adapt examples and output constraints before you rewrite the structure.

Linked challenge

Oncology Decision Support Orchestration with OpenAI Agents SDK and o4-mini

Inspired by the 'Large Cancer Assistant (LCA)' research, this challenge tasks you with building a multi-agent clinical decision support system (CDSS). You will implement a model-agnostic orchestration layer using the OpenAI Agents SDK to coordinate specialized agents representing different clinical domains: an Oncology Strategist, a Pathology Analyst, and a Radiology Interpreter. Each agent must utilize the OpenAI o4-mini model to process complex gastric biopsy reports and suggest evidence-linked treatment pathways. Your system must handle unstructured biopsy data, extract relevant biomarkers (like H. pylori status or HER2 expression), and generate a unified clinical recommendation. The core technical hurdle is implementing a 'Model-Agnostic Orchestration' pattern that allows agents to hand off tasks based on the complexity of the clinical query, ensuring that every recommendation is backed by a specific evidence link found in the provided medical reports.

Open challenge

Related prompts

Browse library

Problem Definition and Requirements Gathering

To establish a clear understanding of the problem space and define comprehensive requirements for the AI solution.

AI Solution Architecture and Strategy

To create a comprehensive technical architecture and AI strategy that guides the implementation of the solution.

Implementation Plan and MVP Development

To provide a clear, actionable roadmap for implementing the AI solution from concept to deployment.