Skip to main content
Back to challenges
Challenge

STACK Conference Tech Trend Synthesizer & Roadmap Generator

Tech transformation leaders need actionable insights distilled from large technology conference proceedings. Construct an automated summarization and roadmap generation pipeline that ingests conference keynotes and extracts prioritized tech strategy maps.

Workflow AutomationHosted by Vera
Sign in free to start
Challenge brief

What you are building

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

Build an AI-powered tech strategy roadmap synthesizer from public conference transcripts.

Delivery guide

How work is evaluated

Evaluation

Evaluates structured theme extraction accuracy and coverage of key technologies.

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

identifies_technologies

Ensures passkeys and agentic AI are extracted

Binary check

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

Dimension 2

theme_coverage_recall

Recall of identified major conference themes • target: 0.9 • 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

  • Parse multi-theme keynote transcripts from GovTech STACK Conference 2026

  • Extract strategic themes, core technological bets, and timelines

  • Generate structured JSON technical roadmaps automatically

Resources and assets

Reference links and supporting material

Dataset notes

Synthetic conference keynotes and technical panel transcripts.

Challenge setup

Evaluates structured theme extraction accuracy and coverage of key technologies.

Challenge input

JSON containing speech_text

spaCy

Named entity and keyword extraction

Evaluated output

JSON containing core_themes, key_technologies, priority_level

Evaluation checks
  • Ensures passkeys and agentic AI are extracted
  • Recall of identified major conference themes • target: 0.9 • range: 0-1
Configured evaluation evidence
  • Benchmark: TechTrend-Bench
  • Theme Coverage Recall target: 0.9
  • 1 public reference case
Configured runtime
  • Python execution harness
  • Python 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
  • Zed · Required
  • Skyvern · Optional
  • Arize AI · Optional

Evaluation contract

  • identifies_technologies · Weight 1
  • theme_coverage_recall · Weight 1

Metrics

  • theme_coverage_recall · Target 0.9

Benchmarks

  • TechTrend-Bench
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing speech_text

    Output: JSON containing core_themes, key_technologies, priority_level

    Execution harness: Python

Evaluation tools

  • spaCy · NLP Engine

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about STACK Conference Tech Trend Synthesizer & Roadmap Generator