Build a Waste-to-Energy Plant Feedstock Routing Workflow with Mastra AI and Hyperbolic
Waste-to-energy facilities face variable caloric intake and municipal collection delays that disrupt boiler performance. Build an automated feedstock routing agent using Mastra AI workflows and Hyperbolic infrastructure to dispatch collection trucks based on real-time calorific values, achieving a 15% reduction in plant thermal instability.
What you are building
The core problem, expected build, and operating context for this challenge.
Construct an automated feedstock routing system utilizing Mastra AI TypeScript workflows and Hyperbolic compute to optimize municipal waste delivery for energy generation.
How work is evaluated
Evaluates the Mastra AI routing agent on calorific value balance and route efficiency.
Challenge datasets
Public datasets, plus the private datasets you have access to.
How submissions are scored
These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.
valid_json_structure
Ensure agent outputs structured dispatch JSON
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
thermal_stability_score
Ratio of resulting blended calorific value to target boiler requirement • target: 0.9 • range: 0-1
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
What you should walk away with
Implement Mastra AI agent workflows for multi-node energy process automation
Integrate Hyperbolic API for fast inference on caloric analysis telemetry
Optimize truck routing models based on dynamic moisture and calorific value metrics
Establish pass/fail validation logic for municipal feedstock intake operations
Reference links and supporting material
Simulated truck waste moisture logs and incinerator boiler temperature telemetry inspired by Casablanca WtE project data.
Challenge setup
Evaluates the Mastra AI routing agent on calorific value balance and route efficiency.
Challenge input
JSON containing batch telemetry of incoming truck loads and current boiler thermal state
Mastra AI
Required framework for workflow automation
Hyperbolic
Required fast inference tool for calorific classification
Evaluated output
JSON containing dispatched truck schedule, calculated thermal drift, and route cost
- Ensure agent outputs structured dispatch JSON
- Ratio of resulting blended calorific value to target boiler requirement • target: 0.9 • range: 0-1
- Benchmark: Industrial AI Process Optimization Benchmark
- Thermal Stability Score target: 0.9
- 1 public reference case
- JavaScript execution harness
- javascript sandbox (unavailable on Versalist)
Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured items.
View technical recipe
Configured tools
- Hyperbolic · Required
- Mastra AI · Optional
- Resemble AI · Optional
- Mastra AI · Optional
Evaluation contract
- valid_json_structure · Weight 1
- thermal_stability_score · Weight 1
Metrics
- thermal_stability_score · Target 0.9
Benchmarks
- Industrial AI Process Optimization Benchmark
- energy
Reference cases
- 1 public reference case
Workflow tasks
- Task 1
Input: JSON containing batch telemetry of incoming truck loads and current boiler thermal state
Output: JSON containing dispatched truck schedule, calculated thermal drift, and route cost
Execution harness: JavaScript
Evaluation tools
- Mastra AI · Agent Framework
- Hyperbolic · Model Runtime
Recipe freeze marker
No recipe freeze time is recorded.