https://makit.net/tags/generative-ai/Recent content in Generative-Ai on Software Engineering, Architecture and AWS Serverless Technology from makitHugo -- gohugo.ioenSun, 26 Oct 2025 00:00:00 +0000https://makit.net/blog/running-a-tiny-strands-agent-on-lambda/Sun, 26 Oct 2025 00:00:00 +0000https://makit.net/blog/running-a-tiny-strands-agent-on-lambda/What is Strands Agents Strands Agents is an open source SDK from AWS for building AI agents with a model-first approach. You define a model, a system prompt, and optional tools. The agent loop handles planning and tool use. It supports multiple providers such as Amazon Bedrock and integrates with the Model Context Protocol for tool discovery and composition. This lets you wire in external capabilities without changing your core agent logic.https://makit.net/blog/bedrock-agents-and-knowledge-bases-part-2/Tue, 16 Jan 2024 00:00:00 +0000https://makit.net/blog/bedrock-agents-and-knowledge-bases-part-2/Building an Amazon Bedrock JIRA Agent with Source Code Knowledge Base - Part 2 Write Access In part 1 of this series, I touched on the definitions of Agents, Knowledge base, RAG, and Amazon Bedrock. I showed a few examples of using Bedrock Agents to use natural language for searching and summarising tasks in JIRA, a task tracker. I also went into how to add Retrieval-Augmented Generation (RAG) to allow the LLM to search the full code base and get an English summary of certain behaviours or explain bugs.https://makit.net/blog/bedrock-agents-and-knowledge-bases-part-1/Thu, 28 Dec 2023 00:00:00 +0000https://makit.net/blog/bedrock-agents-and-knowledge-bases-part-1/Building an Amazon Bedrock JIRA Agent with Source Code Knowledge Base - Part 1 Amazon Bedrock Amazon Bedrock is AWS’s offering of a fully managed service for foundational models. It makes different foundation models from Amazon and third-parties easily accessible. Think of it as a unified API where you can pick and choose from a variety of foundation models to match your project’s needs. Agents In the generative AI world, an agent is built on the premise of using large-language models (LLM) to make decisions on sequences of actions, tasks and with reasoning to create a resource that is capable of taking user input and being able to respond to the input using different tools, external data and more.https://makit.net/blog/digging-into-how-aws-partyrock-works/Sun, 19 Nov 2023 00:00:00 +0000https://makit.net/blog/digging-into-how-aws-partyrock-works/PartyRock PartyRock is a generative playground from AWS. It’s a code-free application builder that integrates quickly and easily with Amazon Bedrock. This allows users to pipe outputs to inputs and play with prompt engineering and other values to create generative AI applications with no previous experience required. Application Generation On the homepage of PartyRock is a simple App builder. This allows users to describe what they want the app to do and then it will generate the GenAI application, using GenAI.https://makit.net/blog/llm-in-a-lambda-function/Sat, 14 Oct 2023 00:00:00 +0000https://makit.net/blog/llm-in-a-lambda-function/Large Language Models and Generative AI Generative AI is a branch of machine learning that deals with models that create entirely new outputs based on being trained on a lot of different examples. They can generate images, videos, music, and text. A Large Language Model is a type of model that can generate text; at a basic level, they predict the next word in a sequence of words. The best-known examples are through products like OpenAI’s ChatGPT or Google’s Bard.