← All stories
● Covered by 1 source · 1 reportMedium impact1 neutral

Microsoft Foundry introduces continuous improvement for AI agents

🔄 Updated 2d ago
New to BrevFeed? We gather this story from every outlet covering it into one summary — ranked by real-world impact, not just the latest headline — so you never miss what matters. What is BrevFeed? →

Key points

  • Foundry agents improve with increased usage and user input.
  • The system identifies and tests improvements, balancing quality, speed, and cost.
  • Capabilities range from skill improvements to training model weights with custom data.
  • GitHub Copilot assists in building agents, integrating with Foundry for deployment.

Continuous Improvement for AI Agents

Microsoft Foundry has introduced continuous improvement features for AI agents, announced at Microsoft Ignite. This update allows agents to learn and adapt based on ongoing usage and user interactions. The system is designed to create a feedback loop where agent traces and user input are fed back into the system to enhance performance over time.

Systematic Optimization

Foundry automatically analyzes agent runs to identify potential improvements. It tests these improvements and provides insights into their impact on quality, speed, and cost, allowing users to decide which changes to implement. The platform offers various methods for progressive improvement, from minor skill adjustments and configuration changes to training model weights using proprietary data.

Integration with GitHub and Azure

The new capabilities integrate with GitHub for agent development, where GitHub Copilot assists in code generation and model orchestration. Once built, agents are deployed and managed within Foundry, which operates on Azure. This unified system supports running and supervising agents at scale across different regions.

Building Intelligent Agents with GitHub

Before improvement, agents are built using GitHub. GitHub Copilot helps automate the coding process for agents, such as those for supply chain automation, by translating natural language descriptions into code. GitHub Copilot Fusion routes and orchestrates models during development, selecting appropriate models while balancing performance, latency, and cost.

Running and Scaling Agents with Foundry

Foundry provides the infrastructure to run, govern, and continuously improve agents for multiple teams across various regions. It supports a wide range of models from providers like OpenAI, Anthropic, Meta, Mistral, and Microsoft's own AI, alongside open-source options.

✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →

The daily brief

One email each morning: the day's tech stories, clustered across outlets and summarized. No account needed.

One email a day. Unsubscribe in one click, any time.

Today's brief

Spend a few minutes, get the whole day. Every topic's top stories in one hands-free rundown — listen, watch, or read the transcript.

~4 min · 3 stories · Nov 21

▶ Play today's brief Listen on Spotify

New every morning, and the back catalogue is archived by date.

Reporting from

Microsoft Foundry now includes continuous improvement capabilities for AI agents, allowing them to learn from usage and user feedback. This system integrates with GitHub for agent development and runs on Azure, enabling organizations to refine agent performance over time.