GPT-5 - RoboTaxi Route Optimization
Develop a system using GPT-5 to optimize robotaxi routes in Singapore, leveraging real-time traffic data and integrating with map APIs. The system should utilize RAG capabilities to access and process information from various sources, including traffic updates, road closures, and points of interest. The GPT-5 model will be used to reason about the optimal route based on the retrieved information, considering factors like travel time, passenger preferences, and potential congestion. Few-shot learning techniques will be used to train the model on a limited dataset of route optimization examples. The final product should be a functioning prototype that can suggest optimal routes given specific parameters.
What you are building
The core problem, expected build, and operating context for this challenge.
Develop a system using GPT-5 to optimize robotaxi routes in Singapore, leveraging real-time traffic data and integrating with map APIs. The system should utilize RAG capabilities to access and process information from various sources, including traffic updates, road closures, and points of interest. The GPT-5 model will be used to reason about the optimal route based on the retrieved information, considering factors like travel time, passenger preferences, and potential congestion. Few-shot learning techniques will be used to train the model on a limited dataset of route optimization examples. The final product should be a functioning prototype that can suggest optimal routes given specific parameters.
Shared data for this challenge
Review public datasets and any private uploads tied to your build.
What you should walk away with
Master capabilities for building RAG-based applications
Implement efficient data ingestion and processing pipelines
Design a prompt engineering strategy for GPT-5 to optimize routes
Apply few-shot learning to fine-tune GPT-5 for route optimization
Build a user interface to visualize routes and analyze performance
Integrate map APIs (e.g., Google Maps Platform) for real-time data
Deploy the solution as a cloud-based service using serverless technologies
How this agent runs
Evaluation will be based on the accuracy and efficiency of route optimization, as well as the user-friendliness of the interface.
Challenge input
Start location, end location, time of day, passenger preferences (optional)
Agent execution
The configured agent processes the input under the challenge policy.
Evaluated output
Optimal route with estimated travel time, visualized on a map
- The evaluator checks the declared output contract.
- Route Accuracy target: 90
- Python execution harness
View technical recipe
Configured tools
No tool records are attached.
Evaluation contract
- The evaluation module defines the checks.
Recipe state
This is a preview. The configuration can change before the evaluation recipe is locked.
Run this agent on your dataset and AI stack
Bring your dataset, model providers, and success criteria. We will scope the right managed run for your team.
Scope a managed run[ok] Wrote CHALLENGE.md
[ok] Wrote .versalist.json
[ok] Wrote eval/examples.json
Requires VERSALIST_API_KEY. Works with any MCP-aware editor.
DocsFind another challenge
Jump to a random challenge when you want a fresh benchmark or a different problem space.