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 16 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.
Set up an experimentation pipeline using Ray Tune to optimize the parameters for your inference routing agent (e.g., thresholds for switching between DeepSeek R1 and simulated Trainium based on prompt length, complexity, or user priority). Concurrently, integrate Ellipsis as a monitoring and control interface, allowing real-time adjustments to routing policies and viewing experiment results. Provide code snippets for defining a Ray Tune experiment and for Ellipsis interaction. ```python
import ray
from ray import tune # Placeholder for your inference routing function that Ray Tune will optimize
def train_router_policy(config): # Simulate routing decisions and measure metrics latency_penalty = config["latency_weight"] * 0.1 cost_penalty = config["cost_weight"] * 0.01 # In a real scenario, this would call your ADK agent and run inferences # Return a metric for Ray Tune to optimize, e.g., 'combined_score' return {"combined_score": -(latency_penalty + cost_penalty)} # Configure Ray Tune experiment
# tune.run(
# train_router_policy,
# config={
# "latency_weight": tune.uniform(0.1, 1.0),
# "cost_weight": tune.uniform(0.1, 1.0),
# },
# num_samples=10,
# ) # Ellipsis integration (conceptual - assumes Ellipsis API or SDK for messaging)
class EllipsisMonitor: def send_alert(self, message: str): print(f"Ellipsis Alert: {message}") def get_user_command(self) -> str: # Simulate getting command from Ellipsis interface return "" # Example usage in the agent system
# monitor = EllipsisMonitor()
# monitor.send_alert("New optimal routing policy identified by Ray Tune!")
```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 already mixes executable detail with instructions, so the safest path is to tune examples and interfaces before you rewrite the overall scaffold.
Google ADK Multi-Model Inference Routing with DeepSeek R1 for Cerebras/Trainium Optimization
Inspired by AWS's strategy of deploying specialized AI chips like Cerebras' Wafer-Scale Engine alongside cost-effective Trainium processors, this challenge involves building an intelligent multi-agent system using Google ADK. The system will act as a dynamic inference router, intelligently dispatching requests to different AI models (e.g., DeepSeek R1) or simulated hardware endpoints based on real-time performance metrics, cost constraints, and security policies. Agents within the Google ADK framework will analyze incoming inference queries, assess their complexity, and determine the optimal model and hardware configuration for execution. Key aspects include integrating persistent memory management with Zep for agent state, enforcing security policies with Lakera to protect against malicious inputs, and leveraging Ray Tune for optimizing model routing decisions through experimentation. The goal is to maximize inference throughput and minimize cost while ensuring security and reliability for critical AI workloads.
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.