implementation

MCP Data Integration

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

Linked challenge: Build an Automated Model Evaluation Pod with LangGraph and GPT-5.3-Codex

Format

Text-first

Lines

Sections

Linked challenge

Build an Automated Model Evaluation Pod with LangGraph and GPT-5.3-Codex

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines

1 sections

No variables

0 checklist items

Write a Python script using the MCP SDK to create a server that serves evaluation rubrics. Connect this server to the LangGraph 'data_retrieval' node to pull evaluation criteria dynamically.

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

Build an Automated Model Evaluation Pod with LangGraph and GPT-5.3-Codex

Inspired by Deccan AI's focus on post-training evaluation and Meta's reorganization into AI-native pods, this challenge requires building a stateful agentic system for automated model assessment. You will design a LangGraph workflow where specialized agents evaluate the performance and safety of diverse model outputs. One agent generates responses to complex prompts, while an evaluator agent powered by GPT-5.3-Codex uses deep reasoning to score them against custom rubrics. The system integrates with the MCP to access external datasets and uses Ray Tune to automate the evaluation of different system prompt configurations. Finally, results are presented through a Softr-based dashboard and summarized via Resemble AI for voice-based reporting.

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.