Agents work by synthesizing data from different parts of your Amplitude account: , , , as well as . So the more you're already using Amplitude to analyze user behavior, the more context your Agents will have to work with.

Start by defining a goal for your Agent—like improving conversion or boosting feature adoption. The Agent will use your Amplitude data to identify patterns and make recommendations that you can approve for the Agent to act on.

Amplitude Agents are designed to work with a natural language interface, making them accessible to team members across all skill levels. You can interact with Agents, access analysis, approve recommendations, give them feedback, and adjust their autonomy level based on your comfort. We also plan to offer this interface in multiple languages for our customers across the world.

We're using a combination of models from OpenAI and AWS Bedrock. We've also created many specialized tools and sub-Agents that handle different parts of the work. They can focus on analysis, running experiments, creating guides, etc. Most of the orchestration, memory, and session management is supported by Amplitude’s backend. This approach gives us the flexibility to customize how Agents behave, so they’ll work like product analytics specialists rather than AI generalists.

Agents will be part of the core Amplitude platform—we want every customer to benefit from having AI teammates. There will be additional capabilities you can unlock with other products, but we'll share more specifics about packaging as part of our GA release later this summer. Right now, we're focused on making sure the experience is great for our beta customers.

Not yet, but soon. For now, we're focused on getting the core Agent experience right. Once we do that, we can layer in more integrations and open protocols. We imagine a world where Amplitude Agents will work easily alongside tools and Agents from other systems.

We do not train AI Models on any customer’s data for Amplitude AI Agents.

Agents learn from a few different sources. They start with general best practices from the latest foundation models such as interaction patterns, accessibility standards and design practices that might apply across different industries. From that foundation, we layer in Amplitude's expertise using system prompts that we've developed from working with thousands of teams.

Each Agent builds up its own memory from a customer's database about your specific product and what works for your users. This knowledge stays completely separate and secure for each customer. Over time, we expect Agents will get smarter as their underlying models improve, as we refine our approach, and as they learn more about your particular business.