Agents for Amazon Bedrock

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

Agents for Bedrock demo

Agents for Amazon Bedrock enhance operational efficiency, customer service, and decision-making while reducing costs and enabling innovation

agents for amazon bedrock instructions screenshot

Automatic prompt creation

Agents for Amazon Bedrock creates a prompt from the developer-provided instructions (E.g., “You are an insurance agent designed to process open claims”), API details needed to complete the tasks, and company data source details from knowledge bases. The automatic prompt creation saves weeks of experimenting with prompts for different FMs.

agents for amazon bedrock vector database

Retrieval augmented generation

Agents for Amazon Bedrock securely connects to your company’s data sources, automatically converts data into numerical representations, and augments the user request with the right information to generate an accurate and relevant response. For example, if the user asks about documents required for claims, the agent will look up information from an appropriate knowledge base that you choose (such as the vector engine for Amazon OpenSearch Serverless, Pinecone, or Redis Enterprise Cloud) and provide a response: “You need to turn in your driver’s license, pictures of the damaged car, and an accident report.”

orchestration plan

Orchestrate and execute multistep tasks

Customers can create an agent in Amazon Bedrock in just a few clicks, accelerating the time it takes to build generative AI capabilities into applications. Customers first select their desired model and write a few instructions in natural language (e.g., “you are a friendly customer service agent” and “check 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. 

agent chain of thought reasoning capability

Trace through the Chain of Thought (CoT) reasoning

You can step through the agent's reasoning and orchestration plan with the trace capability. With these insights, you can easily 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.

modify base prompt screen

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.