Danilo Poccia
banner
danilop.bsky.social
Danilo Poccia
@danilop.bsky.social
Chief Evangelist (EMEA) @ AWSCloud. Serverless, IoT, AI/ML. Few pics, some music. My opinions. Complexity is a science. He/him.
Reposted by Danilo Poccia
📰🚨 AWS Weekly Roundup: Kiro CLI latest features, AWS European Sovereign Cloud, EC2 X8i instances, and more (January 19, 2026)

#AWSNewsBlog #AWSCommunityDay #reInvent #AWSBuilderCenter #SSACommunity
AWS Weekly Roundup: Kiro CLI latest features, AWS European Sovereign Cloud, EC2 X8i instances, and more (January 19, 2026) | Amazon Web Services
At the end of 2025 I was happy to take a long break to enjoy the incredible summers that the southern hemisphere provides. I’m back and writing my first post in 2026 which also happens to be my last...
ift.tt
January 20, 2026 at 9:43 AM
Here's my AWS Weekly Roundup 👉 AWS Lambda for .NET 10, AWS Client VPN quickstart, Best of AWS re:Invent, and more (January 12, 2026)

ift.tt/iwO2SgI

#AWS #News #Serverless #VPN
AWS Weekly Roundup: AWS Lambda for .NET 10, AWS Client VPN quickstart, Best of AWS re:Invent, and more (January 12, 2026) | Amazon Web Services
At the beginning of January, I tend to set my top resolutions for the year, a way to focus on what I want to achieve. If AI and cloud computing are on your resolution list, consider creating an AWS…
ift.tt
January 13, 2026 at 8:48 AM
I had a problem. I had accumulated too many MCP servers over time. So I asked Kiro to improve its own configuration and group tools into Powers that are loaded in context only when needed. Self-optimization is a new pattern.

dev.to/aws/how-i-us...

#AWS #Kiro #DevEx #AI
How I Used Kiro to Optimize Its Own MCP Configuration
I had a problem. My Kiro setup had accumulated 14 MCP servers over time: AWS tools, web automation,...
dev.to
January 12, 2026 at 1:32 PM
Hey, Amazon Science is on Bluesky! Welcome :)

@amazon-science.bsky.social
January 8, 2026 at 8:45 AM
Chain-of-Draft (CoD) prompting is a technique that compresses reasoning steps to 5 words or less while maintaining accuracy.

#AWS #AI
January 5, 2026 at 6:14 PM
More details on Mantle, our next-generation inference engine for Amazon Bedrock. Designed with zero operator access (ZOA) from the ground up—no SSH, no Session Manager, no serial consoles. There's no mechanism for any AWS operator to access customer prompts or completions.

#AWS #AI #Security
January 5, 2026 at 4:41 PM
Happy 2026! If learning AI and cloud computing is on your list of resolutions this year, what about starting with an AWS Free Tier account?

#CloudComputing #AI #AWS #LearnToCode #TechEducation #DevCommunity #2026Goals
January 5, 2026 at 12:35 PM
Just got my first (smart) telescope and got these – 20’ each 🤩
January 3, 2026 at 7:30 PM
Happy holidays from #Rome 🚶🏻‍♂️📷
December 29, 2025 at 9:33 AM
Reposted by Danilo Poccia
dev.to/aws/explorin...

The OpenAI API format is what most are used to. If you're wondering what switching to Amazon Bedrock would actually look like, the barrier is lower than you might expect. Project Mantle provides OpenAI-compatible endpoints and the same SDK, just a different base URL. (1️⃣/3️⃣)

🧵
Exploring the OpenAI-Compatible APIs in Amazon Bedrock: A CLI Journey Through Project Mantle
After Amazon Bedrock introduced OpenAI-compatible application programming interfaces (APIs) through...
dev.to
December 28, 2025 at 6:33 PM
Amazon Bedrock now has OpenAI-compatible APIs through Project Mantle. I built a CLI to explore them and learned some interesting things about the two different approaches. 🧵

dev.to/aws/explorin...

#AWS #AI #OpenAI #Python
Exploring the OpenAI-Compatible APIs in Amazon Bedrock: A CLI Journey Through Project Mantle
After Amazon Bedrock introduced OpenAI-compatible application programming interfaces (APIs) through...
dev.to
December 16, 2025 at 1:15 PM
Reposted by Danilo Poccia
Heavy downside at CloudWatch: Managing logs at scale usually sucks.
With Unified Data Management, this may be solved!
December 16, 2025 at 12:03 PM
Reposted by Danilo Poccia
RUM is a heavily overlooked feature of CloudWatch, even though it's great.
Now it finally supports mobile apps too! 🕵️‍♂️
December 14, 2025 at 7:57 AM
Reposted by Danilo Poccia
Inspired by the general availability of Amazon S3 Vectors, I used it with Nova Multimodal Embeddings to build "SemStash", a semantic storage for humans and AI agents:

dev.to/aws/building...

#AWS #AI #Storage #Python #MCP
Building a Semantic Storage for Humans and AI Agents
This week at AWS re:Invent 2025, Amazon S3 Vectors reached general availability, bringing...
dev.to
December 5, 2025 at 3:32 PM
Inspired by the general availability of Amazon S3 Vectors, I used it with Nova Multimodal Embeddings to build "SemStash", a semantic storage for humans and AI agents:

dev.to/aws/building...

#AWS #AI #Storage #Python #MCP
Building a Semantic Storage for Humans and AI Agents
This week at AWS re:Invent 2025, Amazon S3 Vectors reached general availability, bringing...
dev.to
December 5, 2025 at 3:32 PM
Amazon Bedrock now supports Responses API on new OpenAI API-compatible service endpoints 👉 Responses API support is available today starting with OpenAI's GPT OSS 20B/120B models, with support for other models coming soon

go.aws/447OY2F

#AWS #AI #OpenAI #reInvent #AWSreInvent #DevEx #SDK
Amazon Bedrock now supports Responses API from OpenAI - AWS
Discover more about what's new at AWS with Amazon Bedrock now supports Responses API from OpenAI
go.aws
December 5, 2025 at 9:34 AM
Strands Agents now speaks TypeScript: A Side-by-Side Guide 👉 This article compares the Python and TypeScript implementations side by side, building a practical example along the way

dev.to/aws/strands-...

#OpenSource #AI #Python #TypeScript
Strands Agents now speaks TypeScript: A side-by-side guide
The Strands Agents SDK, which was released as open source in May 2025, recently added TypeScript...
dev.to
December 4, 2025 at 3:18 PM
Amazon Bedrock adds 18 fully managed open weight models 👉 Including the new Mistral Large 3 and Ministral 3 models

go.aws/3XuL5kE

#AWS #AI #reInvent #AWSreInvent
Amazon Bedrock adds 18 fully managed open weight models, including the new Mistral Large 3 and Ministral 3 models | Amazon Web Services
Access fully managed foundation models from leading providers like Google, Kimi AI, MiniMax AI, Mistral AI, NVIDIA, OpenAI, and Qwen, including the new Mistral Large 3 and Ministral 3 3B, 8B, and 14B…
go.aws
December 2, 2025 at 5:08 PM
Amazon S3 Vectors now generally available with increased scale and performance 👉 Reduce the total cost of storing and querying vectors by up to 90% when compared to specialized vector database solutions

go.aws/3XuL2oY

#AWS #Storage #AI
Amazon S3 Vectors now generally available with increased scale and performance | Amazon Web Services
Scale vector storage and querying to new heights with S3 Vectors' general availability—now supporting up to 1 billion vectors per index, 100ms query latencies, and expanded regional availability,…
go.aws
December 2, 2025 at 5:06 PM
Introducing Amazon Nova 2 Sonic 👉 Our new speech-to-speech model for conversational AI

New languages, improved speech understanding, asynchronous tool calling , and more.

buff.ly/Dg3RMpr

#AWS #AI #reInvent #AWSreInvent
Introducing Amazon Nova 2 Sonic: Our new speech-to-speech model for conversational AI | Amazon Web Services
Build more natural voice interactions with enhanced speech-to-speech AI—now featuring multilingual conversations, dynamic speech control, crossmodal inputs, and improved telephony integration while…
buff.ly
December 2, 2025 at 5:00 PM
Amazon Bedrock AgentCore adds quality evaluations and policy controls for deploying trusted AI agents – Plus episodic functionality in AgentCore Memory and bidirectional streaming in AgentCore Runtime

buff.ly/t84SD0Z

#AWS #AI #reInvent #AWSreInvent
Amazon Bedrock AgentCore adds quality evaluations and policy controls for deploying trusted AI agents | Amazon Web Services
Deploy AI agents with confidence using new quality evaluations and policy controls—enabling precise boundaries on agent actions, continuous quality monitoring, and experience-based learning while…
buff.ly
December 2, 2025 at 4:58 PM
Introducing Amazon Nova Forge: Build your own frontier models using Nova 👉 Start development from early model checkpoints, blend your datasets with Amazon Nova-curated training data, and host custom models securely on AWS.

buff.ly/8b5Z3lJ

#AWS #AI #reInvent #AWSreInvent
Introducing Amazon Nova Forge: Build your own frontier models using Nova | Amazon Web Services
New program gives organizations unprecedented access to Nova model training, enabling them to build custom frontier models that deeply embed domain expertise without the traditional barriers of cost,…
aws.amazon.com
December 2, 2025 at 4:45 PM
Build reliable AI agents for UI workflow automation with Amazon Nova Act, now generally available

buff.ly/Jb6ApsO

#AWS #AI
Build reliable AI agents for UI workflow automation with Amazon Nova Act, now generally available | Amazon Web Services
New AWS service helps developers build AI agents that automate browser-based tasks like form filling, search & extract, shopping & booking, and QA testing—with over 90% reliability for enterprise…
aws.amazon.com
December 2, 2025 at 4:42 PM