Skip to main content
Back to challenges
Challenge

Liquid Biopsy QC Automation and Web Workflow Triage with Mastra AI and Skyvern

Clinical liquid biopsy assays require cross-referencing screening platform QC logs with web portal EHR records. Build an automated TypeScript agent using Mastra AI and Skyvern to scrape lab systems, analyze low-input DNA metrics, and schedule reruns for contaminated batches within 30 seconds.

Data ScienceHosted 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 automated lab QC and web navigation agent with Mastra AI and Skyvern.

Delivery guide

How work is evaluated

Evaluation

Evaluates accuracy of automated liquid biopsy rerun decisions and web workflow execution.

Datasets

Challenge datasets

Public datasets, plus the private datasets you have access to.

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

action_enum_check

Ensures action is either PASS or RERUN.

Binary check

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

Dimension 2

qc_triage_accuracy

Accuracy of batch QC triage against lab standards. • target: 0.95 • 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

  • Build TypeScript AI agents using the Mastra AI framework.

  • Integrate Skyvern for vision-based browser automation of lab portals.

  • Analyze liquid biopsy low-input DNA quality metrics (fragment size, yields).

  • Automate batch rerun scheduling when QC thresholds fail.

Resources and assets

Reference links and supporting material

Dataset notes

Synthetic lab QC metrics from liquid biopsy sequencing batches including yield, fragment size, and coverage depth.

Challenge setup

Evaluates accuracy of automated liquid biopsy rerun decisions and web workflow execution.

Challenge input

JSON with DNA yield (ng), mean fragment size (bp), and duplication rate.

Mastra AI

TypeScript framework designed for AI workflow orchestration.

Skyvern

Vision-based web automation system for complex UI tasks.

Evaluated output

JSON with action (PASS/RERUN) and failure_reason.

Evaluation checks
  • Ensures action is either PASS or RERUN.
  • Accuracy of batch QC triage against lab standards. • target: 0.95 • range: 0-1
Configured evaluation evidence
  • Benchmark: Lab Automation QC Benchmark
  • Qc Triage Accuracy target: 0.95
  • 1 public reference case
Configured runtime
  • 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

Action Space
  • Skyvern · Required
  • Mastra AI · Optional
  • Lingo · Optional
Orchestration
  • Mastra AI · Optional

Evaluation contract

  • action_enum_check · Weight 1
  • qc_triage_accuracy · Weight 1

Metrics

  • qc_triage_accuracy · Target 0.95

Benchmarks

  • Lab Automation QC Benchmark
  • biotech

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON with DNA yield (ng), mean fragment size (bp), and duplication rate.

    Output: JSON with action (PASS/RERUN) and failure_reason.

    Execution harness: JavaScript

Evaluation tools

  • Mastra AI · Agent Framework
  • Skyvern · Agent System

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Liquid Biopsy QC Automation and Web Workflow Triage with Mastra AI and Skyvern