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 4 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.
Design a specific simulation scenario where a sudden, unexpected obstacle (e.g., a child running into the street) appears. Implement the logic for your `SensorInterpreter` to detect this event and for the `DecisionMaker` agent (using Claude 4 Sonnet, deployed on Cerebrium) to react appropriately and safely. Evaluate its response time and outcome (e.g., collision avoided, emergency braking performed). Add this scenario to your MLflow tracking. ```python
# Assuming a simulated environment function
def simulate_obstacle_event(current_speed: float, distance_to_obstacle: float) -> dict: # Simulate sensor data and environment update return {"obstacle_detected": True, "distance": distance_to_obstacle, "speed_obstacle": 0.0} def run_obstacle_scenario(config: dict): with mlflow.start_run(run_name="Obstacle_Reaction_Test"): # Specific MLflow run mlflow.log_params(config) # Simulate initial state # sensor_data = {"road_clear": True, "speed": 60.0} # path_plan = ModalGPT5ProClient().plan_path(sensor_data, ...) # Trigger obstacle event after some time event_data = simulate_obstacle_event(60.0, 20.0) # 20 meters ahead # Simulate DecisionMaker's reaction using CerebriumClaude4SonnetClient # decision = CerebriumClaude4SonnetClient().make_tactical_decision("obstacle_ahead", path_plan_segment) # Log metrics mlflow.log_metric("reaction_time_ms", random.randint(100, 300)) mlflow.log_metric("collision_avoided", True) mlflow.log_metric("final_speed", random.uniform(0.0, 10.0)) # Log conversation or decision details
```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.
AutoGen Multi-Agent System for Autonomous Vehicle Simulation & Planning
Drawing inspiration from the emergence of self-driving car companies, this challenge tasks you with developing a robust multi-agent system using AutoGen for simulating autonomous vehicle decision-making and planning. The system will feature specialized agents collaborating to interpret sensor data, generate dynamic path plans, and make real-time tactical decisions in a simulated environment. This project will emphasize the conversational capabilities of AutoGen agents, leveraging GPT-5 Pro for complex strategic planning and Claude 4 Sonnet for nuanced contextual reasoning. Agents will be deployed on Modal and Cerebrium for optimized, low-latency inference, crucial for real-time autonomous systems. An MLflow integration will provide comprehensive MLOps tracking and experimentation capabilities, ensuring robust development and evaluation of the agentic driving policies. The system will simulate a complex urban driving scenario, where agents must coordinate to navigate traffic, react to unexpected events, and adhere to safety protocols.
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.