Skip to main content
Back to challenges
Challenge

Real-Time DPI API Monitoring Dashboard using Vercel AI SDK

Public digital infrastructure APIs experience regional spikes and latency degradations requiring rapid root-cause summaries. Build a streaming analytics agent using Vercel AI SDK that monitors DPI telemetry and streams actionable incident reports, delivering real-time diagnostic updates with under 100ms streaming latency.

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 a real-time streaming infrastructure monitoring agent using Vercel AI SDK and TypeScript for rapid DPI API anomaly reporting.

Delivery guide

How work is evaluated

Evaluation

Evaluates streaming output response schema and time-to-first-token metric.

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

stream_chunk_validity

Ensures streamed chunks parse cleanly into JSON.

Binary check

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

Dimension 2

streaming_latency_ms

Time to first token chunk. • target: 100 • range: 0-500

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

  • Implement real-time streaming text and object generations using Vercel AI SDK

  • Build TypeScript interfaces for consuming server-sent event streams

  • Process high-frequency API ping logs from public public infrastructure endpoints

  • Generate concise developer diagnostic briefs during active outages

Resources and assets

Reference links and supporting material

Dataset notes

Telemetry stream logs from 10 simulated national public infrastructure microservices.

Challenge setup

Evaluates streaming output response schema and time-to-first-token metric.

Challenge input

JSON containing api_endpoint, current_error_rate, average_latency_ms, and region.

AI SDK

Vercel AI SDK provides low-latency streaming abstractions for TS.

Evaluated output

JSON containing incident_severity ('LOW', 'HIGH', 'CRITICAL'), suspected_cause, and stream_validity (bool).

Evaluation checks
  • Ensures streamed chunks parse cleanly into JSON.
  • Time to first token chunk. • target: 100 • range: 0-500
Configured evaluation evidence
  • Benchmark: Real-time Telemetry Processing Benchmark
  • Streaming Latency Ms target: 100
  • 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
  • Vercel AI SDK · Required
  • Agno · Optional
  • Ax (Adaptive Experimentation) · Optional
Orchestration
  • Vercel AI SDK · Required
  • Agno · Optional

Evaluation contract

  • stream_chunk_validity · Weight 1
  • streaming_latency_ms · Weight 1

Metrics

  • streaming_latency_ms · Target 100

Benchmarks

  • Real-time Telemetry Processing Benchmark
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing api_endpoint, current_error_rate, average_latency_ms, and region.

    Output: JSON containing incident_severity ('LOW', 'HIGH', 'CRITICAL'), suspected_cause, and stream_validity (bool).

    Execution harness: JavaScript

Evaluation tools

  • AI SDK · Streaming Engine

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Real-Time DPI API Monitoring Dashboard using Vercel AI SDK