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.
Demonstrate how to deploy your Pydantic AI agents on Modal, leveraging its serverless capabilities for efficient inference with Amazon Bedrock. Create a custom 'Enterprise API Connector' tool (represented by a Pydantic model for its schema) that agents can call to fetch simulated real-time market data or legal precedent. Show the Modal setup for deploying agents and how agents would interact with this Pydantic-defined tool.
Adaptation plan
Keep the source stable, then branch your edits in a predictable order so the next prompt run is easier to evaluate.
Preserve the source structure until you know which part of the prompt is actually driving the result quality.
Change domain facts, examples, and tool context first before you rewrite the instruction scaffold.
Validate one failure mode at a time so prompt changes stay attributable instead of getting noisy.
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.
Structured M&A Due Diligence with Pydantic AI, GPT-5, and Claude Sonnet 4
This challenge focuses on building a robust, type-safe multi-agent system using Pydantic AI for conducting financial and legal due diligence in mergers and acquisitions. Developers will design agents that leverage the distinct strengths of GPT-5 for complex financial modeling and market analysis, and Claude Sonnet 4 for detailed legal document review and risk identification. The critical aspect of this system is Pydantic AI, which ensures strict output validation and type safety across all agent interactions and generated reports, vital for accuracy in financial and legal contexts. The solution requires integrating these advanced models via scalable inference platforms like Amazon Bedrock and deploying the agent system efficiently using Modal. Agents will be designed to interact with simulated enterprise data sources, perform structured analysis, identify red flags, and generate a comprehensive, validated M&A due diligence report. This project emphasizes the importance of structured outputs and data integrity in critical business applications of generative AI.
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.