AI agent development just got easier on GenAI Platform

As AI agents become increasingly embedded in business operations, user experiences, and regulated workflows, the need for greater transparency, control, and performance visibility is more important than ever. That’s why we’re introducing a set of major updates to GenAI Platform, now in public preview, including enhanced agent development features and improved data sourcing through knowledge base citations. These new capabilities make it easier than ever to build, deploy, and refine your AI agents.

Enhancing your AI agents

We’re rolling out powerful new features that give teams more control, transparency, and efficiency when working with AI agents.

Knowledge base citations for better transparency

Understanding the source of AI-generated responses is critical for trust and reliability. With the new knowledge base citations feature, AI agents can now provide clear source attribution for retrieved information, helping users trace responses back to their original context.

• Source attribution displays file names, URLs, PDF pages, and table references.
• Improved auditability enables verification for compliance and transparency.
• Enhanced trust reinforces confidence in AI-generated responses.

This feature is especially valuable for business intelligence applications and educational platforms, where accurate and verifiable information is paramount.

Agent insights for performance monitoring

Optimizing an AI agent requires clear visibility into how it processes requests and responds to users. Agent insights provide key performance metrics to help you refine your agents for speed, efficiency, and cost-effectiveness.

• Performance metrics such as time-to-first-token, latency, and token consumption are crucial for optimizing response times in customer-facing applications like chatbots, virtual assistants, or AI-powered customer support tools.
• Cost transparency enables better forecasting and budget control, helping to ensure you can scale AI-powered applications without unexpected expenses.

Agent insights give you the power to proactively monitor and refine your AI agents, leading to a better end-user experience.

Agent versioning for more control

Making updates to an AI agent is essential for improving its capabilities, but even small tweaks can sometimes lead to unexpected outcomes. With agent versioning, teams can confidently make changes while maintaining full control over their AI’s evolution.

• Change history tracking provides an audit trail of all modifications, ensuring you can monitor and review adjustments over time, especially useful for some industries that require compliance tracking.
• Rollback functionality allows you to quickly revert to a previous version if a new configuration negatively impacts performance, decreasing disruptions for applications like automated customer service or AI-driven decision-making.

With agent versioning, you can iterate on your AI agents with confidence, helping to ensure continuous improvements without unexpected setbacks.

Build smarter, more transparent AI agents

These updates make it easier than ever to build AI agents that are transparent, auditable, and optimized for performance. Whether you’re managing customer-facing agents or internal support tools, these new capabilities help you move faster with greater confidence. Explore our GenAI Platform and start refining your AI workflows today ->