Build a bilingual (English, Swahili), AI agent for Savanna Bites restaurant (Nairobi), using the Microsoft Foundry Toolkit in VS Code and Microsoft Foundry.
# Biashara Agent Workshop
Build a bilingual (English, Swahili), AI agent for Savanna Bites restaurant (Nairobi), using the **Microsoft Foundry Toolkit** in VS Code and **Microsoft Foundry**.
## Prerequisites
- Visual Studio Code
- Foundry Toolkit extension in Visual Studio Code
- (Optional) Microsoft Foundry for models
## Getting Started
1. Fork this repository
1. Clone your fork locally:
```bash
git clone
github.com /Safaricom-Decode-Agents-Workshop.git
cd Safaricom-Decode-Agents-Workshop
```
1. Open the folder in VS Code:
```bash
code .
```
Then follow the workshop steps starting at workshop/01-overview.md.
1. **Create Agent** — set up Biashara Agent in Agent Builder with `gpt-5-mini` via Microsoft Foundry
1. **System Prompt** — define the agent's personality, role, and language behaviour
1. **MCP Tools** — connect the local data server for grounded answers
1. **Evaluation** — run manual and AI-assisted evaluations on agent responses
1. **Web App** — deploy a Flask chat interface powered by the agent
1. **Export Code** — export agent code for production with Microsoft Agent Framework
## Additional Resources
1. BRK441: Build and launch AI agents fast with Microsoft Foundry and the Microsoft Foundry Toolkit