10 posts
Orchestrating LLMs with AWS Step Functions
AWS Step Functions can transform isolated LLM calls into reliable, observable AI workflows. Learn how to implement prompt chaining, model routing, parallel processing, RAG, automated evaluation, retries, and human approval.
July 19, 2026
How to Use Amazon Bedrock with AWS Step Functions
Learn how to use Amazon Bedrock in AWS Step Functions for AI workflows, prompt chaining, orchestration, automation, parallel processing, and local testing with Thrubit.
May 10, 2026
What Are Amazon Bedrock Inference Profiles & How to Set Them Up
Learn what Amazon Bedrock inference profiles are, how to configure and use them, how to resolve Anthropic model access errors, and how to test Bedrock Step Functions workflows locally with Thrubit.
May 9, 2026
Amazon Bedrock Models for AWS Step Functions
Explore all Amazon Bedrock models available for AWS Step Functions, including Claude, Titan, Llama, Cohere, and more. Learn how to choose the right model for your workflows and how to test Bedrock integrations locally with Thrubit to reduce costs and speed up development.
May 3, 2026 Full AWS Bedrock Integration for Local Step Functions Development
Thrubit 1.3.2 is a major step forward for developers building AI-powered workflows with AWS Step Functions. This release expands Bedrock support beyond simple model invocation and brings the full range of Bedrock service integrations into local execution.
May 1, 2026
What is Amazon Bedrock and How to Use It in Your Step Functions
Amazon Bedrock is AWS’s fully managed service for building and scaling generative AI applications using foundation models from providers like Anthropic, AI21 Labs, Cohere, Meta, and Amazon itself. Instead of managing infrastructure or training models from scratch, Bedrock gives you API access to powerful models so you can generate text, summarize content, classify data, and […]
April 30, 2026
What Are Amazon Bedrock Inference Profiles and How to Set Them Up
Amazon Bedrock simplifies working with foundation models, but once you move into real applications, you run into challenges around cost, consistency, and control. That is where inference profiles become essential. They allow you to standardize how models are invoked across your systems, making it easier to manage behavior, swap models, and control costs without rewriting […]
March 12, 2026
Speeding Up AI Workflows with Parallelization and Batch Inference
As artificial intelligence continues to expand across industries, developers face a growing challenge: how to make complex workflows faster, more efficient, and easier to debug. From language models to computer vision systems, AI pipelines often consist of many moving parts. Each step introduces opportunities for optimization, and two of the most powerful strategies are parallelization […]
November 13, 2025
How to Build and Debug for AI Workflows Without the Cloud
Learn how to build, test, and debug AI workflows locally without cloud dependencies. Explore how tools like Thrubit make AWS Step Functions, Bedrock, and Lambda development faster, cheaper, and more reliable for AI systems.
November 10, 2025
Building Scalable AI Agents with AWS Step Functions and Amazon Bedrock
Learn how to automate and scale AI agent workflows using AWS Step Functions, Amazon Bedrock, and local emulation with Thrubit. Discover how orchestration, model invocation, and offline development come together with a real-world ASL example and workflow diagram.
November 7, 2025