Skip to main content
Loading navigation
Back to challenges

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

What you are building

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

How work is evaluated

Evaluation

Evaluates architectural playbook validity and code syntax.

Datasets

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

How submissions are scored

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

  • Configure AutoGen UserProxyAgent and AssistantAgent teams

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

  • Generate deployable Terraform and Kubernetes manifests for AI workloads

Resources

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)

Shows the first task, up to three tools, and up to three evidence 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