Flowing to agentic

Source: Dev.to

The website I created is boring.
It uses Foundation models for generating content.
It sits behind an API gateway, uses Cognito for authentication, and Amplify serves up the front‑end.

Boring… when there are agents to be built.
The spice of life is doing something you never thought you’d do. This moment of “Ooo let me try it and see what happens” wasn’t expected at this point in the site‑build process. While I intend to keep the site fundamentally the same, I’ll also be deploying a Bedrock agent to have conversations with parents who log in and want to discuss, plan, and create activities in a learning path. This changes the application architecturally, which is why it’s getting its own series of posts. I’ll break up writing about whether the juice is worth the squeeze on this sprinkle of razzle‑dazzle in this boring web app.

Creating the Bedrock agent

Deploy a Bedrock agent that can engage with logged‑in parents, answering questions, helping them plan learning activities, and guiding them through personalized learning paths.

Explore (and maybe set up) prompt routing

Investigate how to route user prompts to the appropriate Bedrock model or custom prompt templates, ensuring relevant and context‑aware responses.

Redesigning the Front end for conversational interactions

Update the Amplify‑served front end to include a chat interface, allowing seamless conversational experiences between parents and the Bedrock agent.

MCP‑fying my lambdas where it makes sense

Refactor Lambda functions into micro‑service components (MCP) where appropriate, improving modularity, scalability, and maintainability.