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.
Outline a deployment strategy for running your selected code generation LLMs (e.g., a Hugging Face model and OpenAI o3 via proxy) using TensorRT-LLM. Describe the steps for quantization, model compilation, and setting up an inference server that can be accessed by your DSPy program.
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.
DeepCode Architect: Multi-Model Code Generation & Optimization
Inspired by reports of DeepSeek V4 outperforming other leading models in coding benchmarks, this challenge focuses on building an advanced, multi-model system for code generation and optimization. Developers will create an automated workflow that takes natural language requirements, generates code using an ensemble of specialized LLMs, and then rigorously tests and optimizes that code for performance, security, and best practices. This system will showcase modern AI engineering by orchestrating different models, leveraging techniques like programmatic prompting with DSPy, and deploying models efficiently with TensorRT-LLM. The goal is to produce highly functional, optimized code that can rival human-written quality, demonstrating how specialized generative AI can push the boundaries of software development.
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.