.

Members-Only

Recent Talks & Demos are for members only

Exclusive feed

You must be an AI Tinkerers active member to view these talks and demos.

February 05, 2025 · Dubai

Bedrock Agents and Powertools Actions

This talk demonstrates using Amazon Bedrock and Lambda to enable LLMs to perform real-world tasks by integrating with systems and automating workflows.

Overview
Tech stack
  • Amazon Bedrock
    Amazon Bedrock is the fully managed, serverless service for building and scaling generative AI applications with a choice of high-performing foundation models via a single API.
    Bedrock is the AWS fully managed service for enterprise-grade generative AI: it delivers a single, consistent API to access a wide selection of top Foundation Models (FMs). This includes models like Anthropic's Claude 3, Meta's Llama 2, and Amazon's Titan family . Developers can privately customize these FMs using their own data via techniques like fine-tuning and Retrieval Augmented Generation (RAG) . Bedrock also provides essential builder tools, including Agents for complex task orchestration and Guardrails for implementing application-specific safety policies . The serverless experience removes infrastructure management, letting teams focus entirely on application logic and deployment .
  • Bedrock Agents
    Build autonomous AI agents to automate complex, multi-step tasks: orchestrating Foundation Models (FMs), company data, and APIs.
    Bedrock Agents is the fully managed service for deploying autonomous, generative AI applications. It leverages a Foundation Model's (FM's) reasoning to break down complex, multi-step user requests into logical sequences. The agent then orchestrates the entire workflow: retrieving proprietary data from your Knowledge Bases, executing specific business functions via your existing APIs (Action Groups), and generating a final, accurate response. This capability accelerates time-to-production for AI-driven automation while maintaining enterprise-grade security and providing full trace visibility for every decision.
  • AWS Lambda
    AWS Lambda is the premier serverless, event-driven compute service: Run code in response to triggers without provisioning or managing any infrastructure.
    Lambda delivers a true serverless experience, executing your code only when needed and scaling automatically from zero to thousands of requests per second (RPS). You pay only for the compute time consumed, measured in millisecond increments, making it highly cost-efficient. The service is event-driven; functions (code blocks) are invoked by triggers from over 200 AWS services, including Amazon S3 for file uploads, Amazon DynamoDB for database changes, and Amazon API Gateway for web backends. Lambda supports multiple runtimes (e.g., Node.js, Python, Java, Go) and manages all underlying resources: OS patching, capacity provisioning, and logging. This allows developers to focus exclusively on application logic, accelerating deployment cycles and reducing operational overhead.
  • AWS Lambda Powertools
    A multi-language developer toolkit to implement Serverless best practices, increasing developer velocity across AWS Lambda functions.
    AWS Lambda Powertools is an official AWS open-source toolkit, available for Python, TypeScript, Java, and .NET, designed to cut boilerplate code and accelerate production-readiness. It provides utility functions for core operational excellence: structured logging via **Logger**, distributed tracing with **Tracer** (integrating with AWS X-Ray), and custom metrics collection using **Metrics** (CloudWatch Embedded Metric Format). Beyond observability, it includes high-value utilities for reliability and resilience, such as **Idempotency** to prevent duplicate function execution and **Batch Processing** to handle partial failures in SQS or Kinesis streams, letting your team focus on business logic.
  • OpenAPI
    OpenAPI Specification (OAS) provides a vendor-neutral, language-agnostic interface description format for modern REST APIs, using JSON or YAML.
    OpenAPI defines a standard, machine-readable format for describing HTTP APIs: this is the core value proposition. The specification, currently at version 3.1.0, allows both humans and computers to understand a service's capabilities without source code access. An OpenAPI Description (OAD) drives critical tooling: it enables automated documentation generation, facilitates client and server code creation (SDKs), and streamlines testing workflows. Governed by the OpenAPI Initiative (OAI) under the Linux Foundation, it ensures a robust, open standard, maximizing interoperability and minimizing guesswork in API consumption.

Related projects