Agents for Amazon Bedrock

Enable generative AI applications to execute multistep tasks across company systems and data sources

Agents for Amazon Bedrock demo

Agents for Bedrock streamline workflows and automate repetitive tasks. Unleash the power of AI automation to boost productivity and reduce cost.

Retrieval augmented generation

Agents for Amazon Bedrock securely connects to your company’s data sources, and augments the user request with the right information to generate an accurate response. For example, if the user asks about claims eligibility, the RAG agent will look up information from the knowledge base and reconcile between the submitted claims and the eligibility policy response: “You need to turn in your driver’s license, pictures of the damaged car, and an accident report.”

agents for amazon bedrock vector database

Orchestrate and execute multistep tasks

Customers can create an agent in Amazon Bedrock in just a few quick steps, accelerating the time it takes to build generative AI applications. Customers first select a model and write a few instructions in natural language for example, “you are an inventory management agent which determines product availability in the inventory system”). Agents orchestrate and analyze the task and break it down into the correct logical sequence using the FM’s reasoning abilities. Agents automatically call the necessary APIs to transact with the company systems and processes to fulfill the request, determining along the way if they can proceed or if they need to gather more information. 

orchestration plan

Code interpretation

Agents for Amazon Bedrock support the ability to dynamically generate and execute code in a secure environment. This automates complex analytical queries that were previously hard to answer solely through model reasoning. Users can leverage this capability to address a wide range of sophisticated use-cases such as data analysis, data visualization, and mathematical problem-solving.

Code interpretation screenshot

Return of control

Agents for Amazon Bedrock allow you to define an action schema and get the control back whenever the agent invokes the action. This helps you implement business logic in the backend service of your choice. Also, with return of control, you get the ability to execute time-consuming actions in the background (asynchronous execution) while continuing the orchestration flow.

user interface screenshot

Memory retention across interactions

Agents for Amazon Bedrock have the ability to retain memory across interactions, offering more personalized and seamless user experiences. This feature allows agents to remember historical interactions, and improving the accuracy of multi-step tasks. Users benefit from improved recommendations and recall of prior context where required, ensuring a more cohesive and efficient interaction with the agent.

Memory Retention screenshot

Trace through the chain-of-thought reasoning

You can step through the agent's reasoning and orchestration plan with the trace capability. With these insights, you can troubleshoot different orchestration issues to steer the model towards the desired behavior for a better user experience. Moreover, you can review the steps and adjust the instructions as you iterate on the application. With complete visibility into the model's reasoning, you can create differentiated applications faster.

agent chain of thought reasoning capability

Prompt engineering

Agents for Amazon Bedrock automatically creates a prompt template from the user instructions, action group, and knowledge bases. You can use this template as a baseline to further refine the automatically generated prompt template to enhance the user experience. You can also update the user input, orchestration plan, and the FM response. Lastly, with the ability to modify the prompt template, you can gain better control over the agent orchestration.

modify base prompt screen