implementation

Agent System Architecture

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

Linked challenge: Aptamer-Seq Autonomous Metabolite Quantifier with OpenAI Agents & QA Wolf

Format

Code-aware

Lines

Sections

Linked challenge

Aptamer-Seq Autonomous Metabolite Quantifier with OpenAI Agents & QA Wolf

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines

1 sections

No variables

0 checklist items

Initialize an OpenAI Agent using the OpenAI Agents SDK. Define a 'MetaboliteScientist' agent that has access to two tools: 'calculate_concentration(sequence_data)' and 'generate_metabolite_report(data)'. Use the following import: 'from openai_agents import Agent, Runner'. Describe how the agent should handle ambiguous sequencing reads.

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 already mixes executable detail with instructions, so tune examples and interfaces before rewriting the scaffold.

Linked challenge

Aptamer-Seq Autonomous Metabolite Quantifier with OpenAI Agents & QA Wolf

Quantifying metabolites using structure-switching aptamers coupled to DNA sequencing is a breakthrough in molecular sensing. This challenge tasks you with building an autonomous agentic system using the OpenAI Agents SDK to process raw sequencing data and convert it into metabolite concentration profiles. Your agent will serve as an 'AI Scientist,' capable of selecting appropriate normalization methods, executing bioinformatics functions, and validating the resulting data visualizations. To ensure the reliability of the system's user interface, you will integrate QA Wolf for automated end-to-end testing of the generated metabolite dashboards. Participants must design a multi-turn conversation flow where the agent interacts with a data environment. The agent will use function calling to invoke DNA-sequencing analysis tools, perform structure-switching analysis, and output JSON-formatted metabolic profiles. This project mirrors the complexity of modern biotech labs where AI is used to bridge the gap between high-throughput sequencing and clinical metabolomics.

Open challenge

Related prompts

Browse library

Initial Assessment Prompt

planning

Content Classification Prompt

implementation

Problem Definition and Requirements Gathering

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