Build Agents
Agents are the workloads that call LLMs and tools through the Agentic Data Plane. Start with how agents work, then create an agent, draw charts from it, trigger it from Microsoft Teams or on a schedule, set up an agent you host yourself, and apply architecture and system-prompt best practices.
Learn how Agentic Data Plane agents use a declarative approach backed by a broad library of prebuilt tools and integrations to replace custom agent code.
Understand how declaratively configured agents execute reasoning loops, manage context, invoke tools, and handle errors.
The A2A protocol lets agents discover and call each other across platforms. Learn how agent cards, authentication, and versioning work.
Design maintainable agent systems with single-agent and multi-agent patterns based on domain complexity.
Write system prompts that produce reliable, predictable agent behavior through clear constraints and tool guidance.
Configure a managed Agentic Data Plane agent declaratively on a single create canvas. No Python or JavaScript code required.
Configure an agent to draw inline charts, inspect their data, and troubleshoot invalid chart blocks in the Playground.
Register a self-managed agent, issue it a client credential, and route its LLM and tool calls through the AI Gateway for spend, traces, and transcripts.
Triggers invoke a deployed agent without calling its API directly, from Microsoft Teams or on a schedule.
