153. LLM Inference with Bedrock
If you’re curious about building with LLMs, but you want to skip the hype and learn what it takes to ship something reliable in production, this episode is for you. We share our real-world experience building AI-powered apps and the gotchas you hit after the demo: tokens and cost, quotas and throttling, IAM and access friction, marketplace subscriptions, and structured outputs that do not break your JSON parser. We focus on Amazon Bedrock as AWS’s managed inference layer: how to get started with the current access model, how to choose models, how pricing works, and what to watch for in production. We also go deep on structured outputs: constrained decoding, schema design that improves output quality, and how to avoid “grammar compilation timed out”. 🧠 Sponsor Thanks to fourTheorem for powering AWS Bites. We help teams build cloud systems that are simple, scalable, and cost effective. Visit https://fourtheorem.com 🧭 Chapters 00:00 Intro 02:06 Definitions: LLM, inference, tokens 05:02 Real-world use cases 11:32 AI vs GenAI, Agents and workflows 16:51 Bedrock overview 23:26 Getting started with Bedrock 30:51 Pricing and cost control 35:13 Gotchas: quotas and access 39:24 Structured outputs and JSON 41:50 Wrap up 🔗 Resources fourTheorem: Bedrock structured outputs guide https://fourtheorem.com/amazon-bedroc... Amazon Bedrock https://aws.amazon.com/bedrock/ Bedrock docs https://docs.aws.amazon.com/bedrock/l... Bedrock pricing https://aws.amazon.com/bedrock/pricing/ Structured outputs https://docs.aws.amazon.com/bedrock/l... Cross-region inference https://docs.aws.amazon.com/bedrock/l... Quotas https://docs.aws.amazon.com/bedrock/l... Throttling help https://repost.aws/knowledge-center/b... Prompt caching https://docs.aws.amazon.com/bedrock/l... Troubleshooting error codes https://docs.aws.amazon.com/bedrock/l... 🎧 Listen Apple Podcasts https://podcasts.apple.com/us/podcast... Spotify https://open.spotify.com/show/3Lh7Pzq... RSS https://anchor.fm/s/6a3312a0/podcast/rss 💬 Questions or feedback? Comment here or reach us Eoin https://bsky.app/profile/eoin.sh | / eoins Luciano https://bsky.app/profile/loige.co | / lucianomammino #AWS #AmazonBedrock #LLM #GenAI #StructuredOutputs #AWSBites

Open Source AI Is Getting Too Big to Run

Build Agents on AWS - Step By Step with Demo

145. We Tried Amazon DSQL So You Don’t Have To (But You Might Want To)
![Yann LeCun's $1B Bet Against LLMs [Part 1]](https://i.ytimg.com/vi/kYkIdXwW2AE/hqdefault.jpg?sqp=-oaymwEjCNACELwBSFryq4qpAxUIARUAAAAAGAElAADIQj0AgKJDeAE=&rs=AOn4CLDbV4izF3i-wxevCVIn7FJjoy1vlA)
Yann LeCun's $1B Bet Against LLMs [Part 1]

18 Years in IT: Tech Leadership & Architecture Lessons with Bjorn Ali Goransson

Deep Agents Explained

Is RAG Still Needed? Choosing the Best Approach for LLMs

152. Exploring Lambda Durable Functions

OWASP's Top 10 Ways to Attack LLMs: AI Vulnerabilities Exposed

138. How Do You Become A Cloud Architect?

MCP vs API Explained: Do You Really Need MCP?

Keynote: After the AI Hype – What’s Real, and What’s Next - Richard Campbell - 2026

The Riskiest Moment of the AI Bubble

Andrej Karpathy: From Vibe Coding to Agentic Engineering w/ Stephanie Zhan

L8 Principal's Agentic Engineering Setup (just copy him)

AI Models Think in Shapes. That Changes Everything w/ Eric Ho of Goodfire

Why is This the Scariest Chart in Electrical Engineering?

The horrible truth about Zen 6

143. Is App Runner better than Fargate?

