Operator-ready prompt for reuse, tuning, and workspace runs.
This item is set up for developers who want to inspect the original language, fork it into Workspace, and adapt the evidence model without losing the source prompt structure.
Implementation handoffs, eval setup, and prompt tuning where you need the original structure intact.
Inspect first, copy once, then fork into Workspace when you want variants, notes, and model settings attached to the same run.
Swap domain facts, examples, and any hard-coded entities for your own context.
Tighten the evidence or verification requirement if this is headed toward production.
Decide which failure mode you want to evaluate first before you branch the prompt.
This prompt already carries implementation detail, tool context, and a final-output instruction. Keep that structure intact when you tune it, or your comparison runs get noisy fast.
Open this prompt inside Workspace when you want a live iteration loop.
Copy for quick reuse, or run it in Workspace to keep prompt variants, model settings, and prompt-history changes in one place.
Structured source with 1 active lines to adapt.
Already linked to a challenge workflow.
Sign in to keep private prompt variations.
Prompt content
Original prompt text with formatting preserved for inspection and clean copy.
Extend the agent's capabilities to orchestrate a content approval workflow using Ludwig. When a content piece fails initial review, the agent should be able to trigger a Ludwig workflow that involves a human expert for manual review and approval. Create a tool `trigger_ludwig_workflow(content_id: str, issues: list[str]) -> str`. Describe how this tool would interface with a Ludwig endpoint and how the agent would decide to use it. Provide the Python code for this new tool.
Adaptation plan
Keep the source stable, then branch your edits in a predictable order so the next prompt run is easier to evaluate.
Hold the task contract and output shape stable so generated implementations remain comparable.
Update libraries, interfaces, and environment assumptions to match the stack you actually run.
Test failure handling, edge cases, and any code paths that depend on hidden context or secrets.
Copy once for a pristine source snapshot, then move the prompt into Workspace when you want variants, run history, and side-by-side tuning without losing the original.
Prompt diagnostics
Quick signals for how structured this prompt already is and where adaptation work is likely to happen first.
This prompt is mostly narrative and instruction-driven, so you can adapt examples and output constraints first without disturbing the structure.
AI-Powered Enterprise Content Review Agent
Develop an advanced, multi-turn conversational AI agent system using the OpenAI Agents SDK to assist enterprises with content review, compliance checks, and monetization strategy. Inspired by recent headlines about AI-driven content and content monetization, this challenge focuses on building a robust agent that can interact with users to understand review criteria, analyze various content types, and propose strategic actions. The agent will leverage the Claude 4 Sonnet model for nuanced content understanding and generation, integrating with LiveKit for potential voice interaction, Crossmint for micro-payment/royalty processing, and Ludwig for orchestrating complex content workflows and approval processes. The agent system will incorporate best practices from RAI for ensuring responsible and secure AI operation.
Use the challenge page to recover the original task boundaries before you tune the prompt. That keeps your variants grounded in the same evaluation target instead of drifting into a different problem.