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.
Conduct end-to-end testing using the 'Chatbot Interoperability Test' task. Monitor agent-to-agent communication and data flow. Identify any issues with intent routing, message translation, or MCP integration. Refine the Claude Opus 4.1 prompts for the IntentRouter and adjust agent logic for improved performance and reliability.
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 rubric, target behavior, and pass-fail criteria as the baseline for evaluation.
Adjust fixtures, mocks, and thresholds to the system under test instead of weakening the assertions.
Make sure the prompt catches regressions instead of just mirroring the happy-path examples.
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.
A2A Interoperability Gateway
This challenge addresses the critical need for interoperability between diverse AI chatbot services and messaging platforms, inspired by regulatory demands for open access. Participants will develop an A2A protocol-compliant interoperability gateway, enabling a messaging platform (simulated WhatsApp) to seamlessly integrate and host rival AI chatbots. The system will act as a 'broker,' translating messages and intents between different chatbot APIs and the platform's native interface. The core will utilize Claude Opus 4.5 for its advanced reasoning and language understanding to parse incoming requests and route them appropriately. AutoGen will orchestrate the 'gateway agents,' managing agent-to-agent (A2A) communication with external chatbot agents (simulated). Semantic Kernel will be employed to define a rich set of 'plugins' or 'skills' that represent the functionalities of various rival chatbots, allowing for flexible integration via MCP. Developers will focus on creating a robust, secure, and extensible system that demonstrates how platforms can open up to third-party AI, fostering a competitive and innovative ecosystem. This involves designing dynamic routing, security mechanisms for A2A communication, and efficient protocol translation.
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.