Andy Kroll

11x AWS Certified (AI/ML/Data) | Generative AI + AWS Enablement @awscloud | Enabling YOU to harness cloud & machine learning tech 🚀

[Andy Kroll @AndyKrollTX]

https://t.co/hicje0455z

[Andy Kroll @AndyKrollTX]

Waco will always have a piece of my heart after 15 years, but I’m excited to share that we’ve officially relocated to the north Austin area (Liberty Hill)!

It’s a big change leaving such a tight-knit community, but the timing felt right for a new adventure.

I’m still at AWS doing AI enablement and exited to connect with the Austin tech scene!

It’s been a fun week of volunteering and exploring the area but if you’re in the area I’d love to hear your food and kid activity recommendations 🤤

[Andy Kroll @AndyKrollTX]

View my verified achievement from @awscloud. https://t.co/uOActhuGoC via @credly

[Andy Kroll @AndyKrollTX]

This is nice because now I can pull in this power to validate templates only when I need to do that action which frees up my context window!

[Kiro @kirodotdev]

New Kiro powers just dropped⚡️

Build AWS infrastructure with CDK and CloudFormation or transform your database development with Amazon Aurora with a single click.

Learn more 👉 https://t.co/M6LO0Mw5Ol

[Andy Kroll @AndyKrollTX]

Having post #AWSreInvent blues, so I decided to reminisce about my visit to the AWS Certified Lounge.

Generated this video using @grok Imagine. The opening image is a real photo I took, then had Grok generate the video from it. It looks remarkably like my desk when I'm studying for certs with all the notes I take!

Here’s the prompt I used: Late night study session aftermath, MacBook Pro screen glowing with AWS Solutions Architect practice exam results, camera crane movement rising from keyboard level upward and backward, revealing scattered study materials, celebratory CERTIFIED AWESOME coffee cup still steaming, half-eaten victory brownie on plate, disposable coffee cup knocked over empty, purple-blue neon lighting from off-screen monitor creating dramatic rim light, exhausted but triumphant atmosphere, desk cluttered with handwritten flashcards and crumpled notes, golden hour window light mixing with cool LED glow, emotional payoff moment after months of preparation, shallow focus pulling from laptop screen to celebration spread, 8 seconds, documentary-style authenticity

[Andy Kroll @AndyKrollTX]

@brooke_jamieson @AWSEvents Great work!

[Andy Kroll @AndyKrollTX]

Success! Now I can hold an AMA about the latest announcements here at the airport haha. Stop by gate D9 if you want to get up to speed 😂

First pass, Kiro implemented the AWS Knowledge MCP server for the agent, but I asked it to use the new AWS-MCP server. Kiro researched and implemented it. I also noticed the agent wasn’t always retrieving the most recent announcements. I asked Kiro to prioritize the latest ones; it updated the agent’s system prompt, and the agent started working perfectly. It even grouped them into re:Invent announcements and November ones.

With just a couple of prompts to Kiro and a few minutes while waiting to board, I have a working agent that fetches the latest AWS announcements and summarizes each in a sentence or two.

It actually took longer to take the pictures and write this post than to build the agent!! 👻

[Andy Kroll @AndyKrollTX]

While we wait for the airplane to leave #AWSreInvent (😭), let’s see if we can fire up @kirodotdev and create an agent that will go find the latest AWS announcements to help me catch up on everything I missed this week! 👻

[Andy Kroll @AndyKrollTX]

A great concise way to see the big announcements at #AWSreInvent 👇

[Amazon Web Services @awscloud]

https://t.co/RXr1UjzzQY

[Andy Kroll @AndyKrollTX]

Love seeing all the Kiro updates!

#AWSreInvent

[Darek Gusto @darekgusto]

The new 0.7 release of @kirodotdev came out public yesterday, so here are some of my thoughts on the latest features:

- Kiro Powers
- Autonomous Agent
- Context usage meter (finally!!!)
- Context summarization
- Slash commands

Open the thread to read more.

[Andy Kroll @AndyKrollTX]

@DigitalColmer @Werner Woah! I must have missed something. Why is it his last RIV talk?

[Andy Kroll @AndyKrollTX]

That’s a wrap for #AWSreInvent day 3!

Ended the night at the AAI party and had a great time catching up with everyone. Had the pleasure of running into @DigitalColmer again!

Took some selfies at the party but after reviewing them they were very blurry so enjoy this Wizard of Oz pic 😂

[Andy Kroll @AndyKrollTX]

@maishsk @jameshoodcodes Wow that’s quick!!

[Andy Kroll @AndyKrollTX]

Learning how to migrate the well-architected way in our workshop this morning!

#AWSreInvent

[Andy Kroll @AndyKrollTX]

Love the analogy of Kiro powers being like Neo instantly downloaded martial arts expertise in The Matrix!

#AWSreInvent

[Kiro @kirodotdev]

⚡ Empower AI agents with curated expertise from partners!

Kiro powers can turn AI agents into experts instantly by dynamically loading powers from partners - @figma, @supabase, @stripe, @getpostman, @neondatabase, @Netlify, @datadoghq, and @Dynatrace.

Support a range of use cases spanning UI, backend, full-stack, API, and agent development, and databases, application deployment, and observability.

Download a power with one click or create and share your own. 👉 https://t.co/nZ7eSUj2k0

#KiroPowers #AICoding #AWSreinvent #StrandsAgents #BedrockAgentCore

[Andy Kroll @AndyKrollTX]

Had a great discussion in today’s workshop about agent memory in AI systems, and thought I’d share what makes short-term vs. long-term memory in AgentCore Memory different and when to use each.

Short-term memory captures turn-by-turn interactions within a single session, letting agents maintain immediate context so users don’t repeat themselves.

Think of it like working memory—when you ask “What’s the weather in Seattle?” and follow up with “What about tomorrow?”, the agent remembers you’re still talking about Seattle.

Long-term memory automatically extracts and stores key insights across multiple sessions—things like user preferences, important facts, and session summaries. This is persistent knowledge that creates personalized experiences over time.

For example, if you mention preferring window seats during a flight booking, that preference gets stored and the agent can proactively offer window seats in future conversations.

This ties directly into context engineering—the practice of designing systems that provide the right information, in the right format, at the right time to help AI models accomplish tasks.

While prompt engineering focuses on crafting individual instructions, context engineering is about building dynamic systems that manage information flow across multiple interactions.

Memory systems are a core component of context engineering, determining what information gets included when the model generates responses.

By combining short-term and long-term memory strategically, you’re engineering the context that makes AI agents feel less like stateless question-answerers and more like intelligent assistants that actually know you.

#AWSreInvent

[Andy Kroll @AndyKrollTX]

The second day of #AWSreInvent has been off to an exciting start. We started off with a workshop on Bedrock AgentCore.

Next up is a workshop on generative AI security testing and protection strategies, where we’ll explore red teaming techniques to assess the security of AI stacks.

Let’s go!

[Andy Kroll @AndyKrollTX]

@SwamiSivasubram @kirodotdev Spooky!

[Andy Kroll @AndyKrollTX]

An amazing first day of #AWSreInvent comes to an end. Supported a couple workshops today and will be back at it again tomorrow.

Was busy most of the day and trying to catch up with announcements. What are some of the ones that stood out to you?

[Andy Kroll @AndyKrollTX]

The first of many selfies this week starting with the one and only @DigitalColmer #AWSreInvent