Skip to main content
Back to challenges
Challenge

AutoGen Enterprise AI Tech Stack Playbook Code Generator

Engineering leaders at CTO summits require standardized technical architecture playbooks tailored to their cloud footprint and LLM stack. Build a collaborative code and design generation multi-agent system using AutoGen.

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 architectural playbook generation swarm using Microsoft AutoGen multi-agent system.

Delivery guide

How work is evaluated

Evaluation

Evaluates architectural playbook validity and code syntax.

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

blueprint_validated

Checks successful validation of blueprint.

Binary check

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

Dimension 2

syntax_correctness

Percentage of executable generated code • target: 0.98 • 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

  • Configure AutoGen UserProxyAgent and AssistantAgent teams

  • Synthesize enterprise AI production patterns (RAG, evaluation, guardrails)

  • Generate deployable Terraform and Kubernetes manifests for AI workloads

Resources and assets

Reference links and supporting material

Dataset notes

Enterprise AI reference architectures and benchmark configuration files.

Challenge setup

Evaluates architectural playbook validity and code syntax.

Challenge input

JSON architecture requirement

AutoGen

Mandatory framework requirement

Evaluated output

JSON architecture specification

Evaluation checks
  • Checks successful validation of blueprint.
  • Percentage of executable generated code • target: 0.98 • range: 0-1
Configured evaluation evidence
  • Benchmark: Infra-Gen-Bench
  • Syntax Correctness target: 0.98
  • 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
  • AutoGen · Required
  • Zed · Optional
  • Agency (Observability) · Optional

Evaluation contract

  • blueprint_validated · Weight 1
  • syntax_correctness · Weight 1

Metrics

  • syntax_correctness · Target 0.98

Benchmarks

  • Infra-Gen-Bench
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON architecture requirement

    Output: JSON architecture specification

    Execution harness: Python

Evaluation tools

  • AutoGen · Multi-Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about AutoGen Enterprise AI Tech Stack Playbook Code Generator