Search

More Filters

Show More
Add Listing
Go Back

contoso-creative-writer

0
Multi-Agent Platforms & Frameworks
Report

Report Abuse

Basic Information

Contoso Creative Writer is a sample application and developer template that demonstrates how to build and orchestrate multi-agent AI workflows for creative writing using Azure services. The repository shows a working FastAPI backend and a web UI that accept a topic and instructions, then run a set of coordinated agents: a research agent that uses Bing Grounding, a product agent that queries an Azure AI Search vector index, a writer agent that combines findings, and an editor agent that refines the final article. The project is implemented in Python, uses Prompty to define and manage prompts, and includes orchestrator logic, prompty files for each agent, example product data loaded into a contoso-products index, tracing and evaluation utilities, and deployment scripts that use the Azure Developer CLI. The README documents setup options including GitHub Codespaces, VS Code Dev Containers, and azd-based deployment and resource provisioning requirements.

Links

Stars
395
Language
App URL
https://github.com/Azure-Samples/contoso-creative-writer
Github Repository
https://github.com/Azure-Samples/contoso-creative-writer/blob/main/README.md

Categorization

App Details

Features
The repository bundles multiple practical features to build and evaluate multi-agent applications. It integrates Azure OpenAI models to drive agents and Prompty for prompt management and tracing. The Bing Grounding Tool is used for web-backed research, and Azure AI Search provides semantic similarity searches against an uploaded product vector store. The sample includes a FastAPI server, a frontend web app, per-agent prompty definitions and Python code, and an orchestrator to run full workflows. Observability and quality tooling include Prompty tracing, a .runs trace viewer, and an evaluate script that scores Coherence, Fluency, Relevance and Groundedness. It also contains CI/CD pipeline guidance, azd deployment templates, developer environment instructions for Codespaces and Dev Containers, and guidance on region, model availability and security configuration.
Use Cases
This repository is helpful both as a demonstrable end-to-end creative writing assistant and as a teaching template for developers building multi-agent systems. End users can generate product-specific, well-researched articles by providing a topic and instructions while the agents perform web grounding, vector search, drafting and editing. Developers get concrete examples of agent composition, prompt management with Prompty, integration patterns for Bing Grounding and Azure AI Search, and an orchestrator pattern to coordinate tasks. The included tracing and evaluation tools let teams inspect agent calls and measure output quality. Deployment and CI/CD instructions accelerate taking the sample into Azure, and security notes explain managed identity or Key Vault options for credentials.

Categories

Content Creation (5042)
Monetization & Business (2246)
Development Tools (1407)
Marketing & Social Media (1403)
Education & Career (1380)
Multi-Agent Platforms & Frameworks (1230)
Health & Life (957)
AI Resources (920)
Agents & Automation (778)
Data & Analytics (766)
Productivity Tools (679)
Writing & Editing (666)

Similar Listings

listing image

yutu

0 (0 review)
listing image

cyber-doctor

0 (0 review)
listing image

vibevideo-mcp

0 (0 review)
listing image

xpert

0 (0 review)
listing image

Curie

0 (0 review)

Featured Listings

Tags

Please fill the required fields*