Back to challenges
Challenge

Substation Procurement & Telemetry Agent with Mastra AI and Retell AI

Riyadh Expo 2030 substation deployment demands rigorous supplier SLA tracking and real-time voice telemetry summaries. Build a TypeScript Mastra AI agent integrated with Retell AI to parse equipment lead-times and conduct automated vendor query voice calls, ensuring zero schedule drift.

Business OperationsHosted by Vera
Sign in free to start
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

Develop an agent using Mastra AI for TypeScript workflow state management combined with Retell AI voice call integration for vendor supply chain verification.

Delivery guide

How work is evaluated

Evaluation

Evaluates Mastra AI agent's ability to trigger Retell AI voice synthesis calls and compute project delay impact based on call transcripts.

Datasets

Shared data for this challenge

Review public datasets and any private uploads tied to your build.

Evaluation rubric

How submissions are scored

These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.

Dimensions
2 scoring checks
Binary
2 pass or fail dimensions
Ordinal
0 scaled dimensions
Dimension 1

Delay Calculation Match

Validates exact calculated delay days from vendor call payload.

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Dimension 2

Extraction Precision

Accuracy of extracted date and status fields. • target: 1 • range: 0-1

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Learning goals

What you should walk away with

  • Construct Mastra AI agent workflows for high-voltage substation asset monitoring

  • Integrate Retell AI voice assistant webhooks to extract supplier commitment dates

  • Analyze potential procurement delays and compute critical path impacts automatically

  • Generate bilingual Arabic/English vendor status reporting dashboards

Resources and assets

Reference links and supporting material

Dataset notes

Synthetic procurement order logs for Riyadh Expo 2030 substations along with generated Retell AI call transcripts in Arabic and English.

How this agent runs

Evaluates Mastra AI agent's ability to trigger Retell AI voice synthesis calls and compute project delay impact based on call transcripts.

Challenge input

JSON payload containing vendor call audio transcription and target component ID.

Mastra AI

TypeScript agent workflow orchestration

Retell AI

Conversational voice call automation

Evaluated output

JSON payload detailing component status, updated delivery date, and total days delay impact.

Checks for
  • Validates exact calculated delay days from vendor call payload.
  • Accuracy of extracted date and status fields. • target: 1 • range: 0-1
Proof of success
  • Benchmark: GCC Infrastructure Procurement Benchmark
  • Extraction Precision target: 1
  • 1 public reference case
Runtime evidence
  • JavaScript execution harness
  • javascript sandbox (unavailable on Versalist)
View technical recipe

Configured tools

Action Space
  • Retell AI · Required
  • Mastra AI · Optional
  • n8n · Optional
Orchestration
  • Mastra AI · Optional

Evaluation contract

  • Delay Calculation Match · Weight 1
  • Extraction Precision · Weight 1

Recipe state

This is a preview. The configuration can change before the evaluation recipe is locked.

Frequently Asked Questions about Substation Procurement & Telemetry Agent with Mastra AI and Retell AI