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 an optimization model, deployed via Seldon Core, that recommends alternative materials for a specific construction component. Given a target material and project constraints (e.g., maximum cost increase, minimum carbon reduction), the model should query available alternatives (from Vespa) and suggest the best option to achieve sustainability goals while respecting project limitations. The LLM (Gemini 2.5 Pro) can be used here to generate natural language explanations for the recommendations or suggest broader strategies.
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.
Carbon-Smart Construction Material Traceability with Gemini Pro & Vespa
With increasing pressure to reduce embodied carbon in construction, verifying sustainability claims and tracking material provenance is crucial. Large-scale projects, like the stalled Fenway Center, highlight the complex interplay of material sourcing, project schedules, and regulatory compliance. This challenge focuses on building a system that can ingest material certification data, calculate embodied carbon footprints in real-time, and trace materials across a construction supply chain. The goal is to provide transparency and enable intelligent decision-making for sustainable construction, mitigating risks associated with material availability and environmental compliance. Participants will develop an intelligent platform capable of processing diverse material documentation (e.g., ASTM certifications, EPDs), extracting key sustainability metrics, and linking them to specific project phases and suppliers. The system will leverage a powerful generative AI model to verify claims, suggest eco-friendly alternatives when supply chain issues arise, and help optimize material selection for carbon reduction targets. A real-time data store and search engine will underpin this, providing instant insights into the project's environmental impact.
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.