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.
Develop a simulated streaming analytics tool that provides dummy performance data (e.g., click-through-rate, view duration) for an ad. Configure the 'Data Analyst Agent' to interpret this data and the 'Optimizer Agent' to suggest modifications to the ad creative. Run a simulated optimization loop where the agents iteratively improve an ad based on performance feedback, demonstrating dynamic adaptation.
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.
Dynamic 'Pause Ad' Creative & Optimization with GPT-5 & RAG
This challenge focuses on building an advanced generative AI system that dynamically creates and optimizes interactive pause ads. The system will employ AutoGen to orchestrate a team of specialized agents ('Creative Agent', 'Data Analyst Agent', 'Optimization Agent') that collaboratively design ad creatives, analyze viewer data, and adapt campaigns in real-time. GPT-5 will serve as the core generative engine for ad copy, visual concepts, and interactive elements. A key aspect of this challenge is the implementation of a sophisticated RAG (Retrieval Augmented Generation) system, powered by LlamaIndex, to ensure ads adhere to brand guidelines, legal requirements, and target viewer preferences. Agents will utilize 'extended thinking' with adaptive reasoning budgets to refine ad concepts and optimize performance based on real-time feedback from a simulated streaming analytics platform. The goal is to produce highly personalized and effective pause ads without explicit human intervention for each creative iteration.
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.