LAI #134: Your First LLM App on AWS for Under a Dollar

Towards AI launched a new enterprise division, Towards AI Deployment, that places AI engineers—many of whom started as community members—inside client organizations to deploy production AI. The newsletter also shares practical advice on agent evaluation, highlighting the need to intentionally break tools in staging to test recovery logic.

Good morning, AI enthusiasts This week is a mix of practical builds and a milestone for us. We also have a big announcement from Towards AI; more on that below. Inside the issue: Let’s get into it This week, I don’t have a video for you, but something even bigger. It’s a big week for me at Towards AI: we just launched Towards AI Deployment, a dedicated enterprise division. Here’s the part I’m proudest of: several of the AI engineers in those pods started right here, as community members and students. They trained with us, and now they’re deploying production AI inside client organizations. And everything they learn doing that work flows back here: the failure cases become AI Tips of the Day, the evaluation methods become course lessons. The context engineering patterns we shared at our World’s Fair workshop came from exactly this kind of work. Two of our co-founders dive deeper into how we went from teaching machine learning to half a million practitioners to deploying AI directly inside businesses, and why we’ve made PE-backed companies and investors our focus. Watch the full video here. https://www.linkedin.com/posts/denis-p-72588a44 louie-and-i-sat-down-with-our-advisor-zeena-ugcPost-7483166744618967040-vWGV/ And, if you’ve been building in public here, keep going. This community is the first place we look when the pods hire. Agent evals should intentionally break the tools. A clean staging run shows how an agent behaves when all dependencies cooperate. Production is where a tool times out after completing an action, or sends back a payload the agent cannot parse. That is when agents repeat work, invent a successful result, or continue without the information they need. Put these failures into the eval harness. Force a 429 response at a known step. In another test, make a required dependency unavailable. Record each tool call and assert what the agent should do next. A read may be safe to retry automatically. A write should first check whether the original action already happened. If the task cannot continue safely, the correct result is a clear stop or escalation. Measure recovery success separately from normal task completion. Otherwise, a high pass rate on easy paths can hide weak recovery logic. To learn more about agent evaluation, tool use, and guardrails, check out our Agent Engineering: Building Multi-Agent Systems Course https://academy.towardsai.net/courses/agent-engineering?utm source=Newsletter&utm medium=email&utm id=AItips . — Louis-François Bouchard, Towards AI Co-founder & Head of Community Vivek m4 https://discord.com/channels/702624558536065165/983037843532308500/1524439240396505220 has built his first open-source project, Spider Canvas, an AI-powered rendering runtime that lets developers build, preview, and iterate on React, HTML, CSS, JavaScript, WebGL, and three.js applications instantly in the browser. It supports real-time streaming, live code preview, sandboxing, and session persistence. Check it out on GitHub https://github.com/M4SPIDER/spider-canvas and support a fellow community member. If you have any questions or suggestions on how to improve it further, share them in the thread https://discord.com/channels/702624558536065165/983037843532308500/1524439240396505220 . We’re writing the second edition of our book, and I asked the community to help pick the title. If you haven’t voted yet, there’s still time. But honestly, the title matters less than what’s inside. So what I really want to know is: what topics do you want us to go deeper into in the second edition? More on agents? Evaluation? Deployment? Cost optimization? Something we didn’t cover at all in the first one? Let us know in the thread https://discord.com/channels/702624558536065165/833660976196354079/1526256618763976926 , this is your chance to shape what goes in. The Learn AI Together Discord community is flooding with collaboration opportunities. If you are excited to dive into applied AI, want a study partner, or even want to find a partner for your passion project, join the collaboration channel https://discord.gg/rj6m9AF7eC Keep an eye on this section, too — we share cool opportunities every week 1. Keatwonobe https://discord.com/channels/702624558536065165/998978160605540454/1525017668086923327 is a researcher exploring a new functional architecture for small model learning. The current model is between 1.2 and 1.8 million parameters in size, but can reduce CE loss on text to sub-0.1 levels in under 2k steps and run multiple continuous tasks simultaneously as a multimodal package. He wants to make it more capable, and if you think you can help, talk to him in the thread https://discord.com/channels/702624558536065165/998978160605540454/1525017668086923327 2. Yasssooo. https://discord.com/channels/702624558536065165/784477688551178240/1525984786881974312 wants to dive deeper into AI Engineering by taking on more projects and collaborating with others doing the same. So if this is your goal too, connect with him in the thread https://discord.com/channels/702624558536065165/784477688551178240/1525984786881974312 3. Mxropriv https://discord.com/channels/702624558536065165/998978160605540454/1524581914001014794 is working on an AI/app competition project and looking for teammates interested in software, AI, design, or business. If you are a high school student who wants to do something similar, reach out to him in the thread https://discord.com/channels/702624558536065165/998978160605540454/1524581914001014794 Meme shared by bin4ry d3struct0r https://discord.com/channels/702624558536065165/830572933197201459/1526343271197048922 Stop Prompting And Start Looping. A Claude Code Engineer’s Guide to /goal and /loop https://pub.towardsai.net/stop-prompting-and-start-looping-a-claude-code-engineers-guide-to-goal-and-loop-e7662aaaafd6?sharedUserId=tai-tech By Pravin Borate https://1pravin-borate.medium.com/?source=---byline--e7662aaaafd6--------------------------------------- Claude Code’s /goal and /loop commands turn one-shot prompting into loop engineering, in which agents work autonomously until the task is complete. /goal wraps a Stop hook with a second evaluator model that verifies completion from conversation evidence, while /loop reruns prompts on a schedule for recurring tasks like CI monitoring. The article demonstrates both techniques by building a self-healing test suite: six planted bugs, a hook that blocks test-file edits, a fully autonomous fix cycle, and guidance on writing verifiable goal conditions. 1. A Beginner’s Guide to Amazon Bedrock: Your First LLM App Without the Overwhelm https://pub.towardsai.net/a-beginners-guide-to-amazon-bedrock-your-first-llm-app-without-the-overwhelm-51fcddef6a1e?sk=8b2ca6b60631d0af2df2f4c24686ac4f By Harish Ramkumar https://medium.com/@ramkumar.harish?source=---byline--51fcddef6a1e--------------------------------------- Amazon Bedrock lets developers call Claude and other foundation models via a single AWS API without managing infrastructure. This beginner guide walks through IAM users, model access, and a first working Python call with the Anthropic SDK, and explains inference parameters such as temperature and max tokens. It progresses to building RAG pipelines with Knowledge Bases and adding Guardrails for content filtering and PII redaction, finishing with production tips covering prompt caching, batch inference, and security hardening, all runnable for under one dollar. 2. Context Window Management Is the New Memory Management https://pub.towardsai.net/context-window-management-is-the-new-memory-management-3a2b8ad7768e?sk=03073390fb40181b18ac28cdceee4d2b By Satyam Sahu https://satyamsahu671.medium.com/?source=---byline--3a2b8ad7768e--------------------------------------- Context windows function like RAM in LLM applications, and most teams manage them carelessly until cost and quality issues surface. The article explains tokens, why huge context limits breed complacency, and three failure modes: runaway API bills, the lost-in-the-middle attention problem, and undebuggable responses. It also covers three practical tips: setting token budgets, pruning stale history, and compressing old turns into summaries, backed by a simple Python context manager. 3. The vLLM Optimization Playbook for L40S https://pub.towardsai.net/the-vllm-optimization-playbook-for-l40s-backed-by-83-experiments-ae5da228f514?sharedUserId=tai-tech By Vedanti https://medium.com/@vedanti220201?source=---byline--ae5da228f514--------------------------------------- In this article, the author shares their findings after measuring vLLM’s optimizations on an NVIDIA L40S, running Llama 3.1 8B Instruct across 83 configurations and 4 production-style workloads. The result is vllm-optimization-bench, an open-source benchmark harness that produces concrete numbers on how vLLM optimizations behave in practice. If you are interested in publishing with Towards AI, check our guidelines and sign up https://contribute.towardsai.net/ . We will publish your work to our network if it meets our editorial policies and standards. LAI 134: Your First LLM App on AWS for Under a Dollar https://pub.towardsai.net/lai-134-your-first-llm-app-on-aws-for-under-a-dollar-465728838d6e was originally published in Towards AI https://pub.towardsai.net on Medium, where people are continuing the conversation by highlighting and responding to this story.