Massimo Re Ferré
@mreferre.bsky.social
📤 1374
📥 82
📝 439
Chief Psychology Officer @awscloud More about me @
https://it20.info/about/
50% of the posts claim that the model is the product. The other 50% of the posts claim that the harness is the product. Which one is it?
3 months ago
1
1
0
How do I reconcile this?
3 months ago
1
0
0
I am drafting a blog post about how to connect the dots around concepts such as agent orchestration, specs, tasks lists, planning mode, autonomous agents, todo lists, sub-agents, and more. I am kidding.
3 months ago
1
2
0
[ New blog post ] "Adding Kiro support to
Backlog.md
using
Backlog.md"
it20.info/2026/02/addi...
loading . . .
GitHub - MrLesk/Backlog.md: Backlog.md - A tool for managing project collaboration between humans and AI Agents in a git ecosystem
Backlog.md - A tool for managing project collaboration between humans and AI Agents in a git ecosystem - MrLesk/Backlog.md
https://Backlog.md
3 months ago
0
1
1
[ Using the Ralph Wiggum loop to execute Kiro specs ]
it20.info/2026/02/usin...
loading . . .
Using the Ralph Wiggum loop to execute Kiro specs
This blog post assumes you are somewhat familiar with Kiro specs driven development (if you are not, this is a great read) and the Ralph Wiggum loop (if you are …
https://it20.info/2026/02/using-the-ralph-wiggum-loop-to-execute-kiro-specs/
4 months ago
0
0
0
It looks like "files" are the "new database" in generative AI (coding tools) land. I am not sure how this is going to scale but it seems to be working for now. Maybe there will be an NFS renaissance in the coming months. Who knows. 💁♂️
4 months ago
1
1
0
[ Blog ] On the importance of the feedback loop in spec-driven development
it20.info/2021/01/on-t...
loading . . .
On the importance of the feedback loop in spec-driven development
This is a short and unstructured blog post on some experiments I have been running using Kiro spec-driven development. I thought I'd share my random notes and …
https://it20.info/2021/01/on-the-importance-of-the-feedback-loop-in-spec-driven-development/
4 months ago
0
1
0
"Run all tasks - Execute every task in your spec with a single click from the spec navbar" Best feature in 0.8.140. Now I can watch all the YouTube reels I want, while @kirodotdev works for me relentlessly 😘
kiro.dev/changelog/id...
5 months ago
0
0
0
The state of social media (from my perspective): [ X ] : a s*it show [ BlueSky ] : the place where you talk about what a s*it show X is [ LinkedIn ] : "I just want to be Facebook for pros" I miss good ol' Twitter. Thanks for coming to my TED talk.
5 months ago
0
4
0
Happy new year!!
add a skeleton here at some point
5 months ago
0
1
0
[ new blog post ] "Specs, intent and the source of truth"
it20.info/2025/12/spec...
loading . . .
Specs, intent and the source of truth
The world is changing. Fast. I have been working in the generative AI coding tool space for about 3 years now. And it feels 70. I often joke about the fact that …
https://it20.info/2025/12/specs-intent-and-the-source-of-truth/
6 months ago
1
1
0
I am so glad I don't have to fly much with
#britishairways
these days...
7 months ago
0
0
0
Thew new Outlook 16 for Mac isn't that bad looking .... I just wish it could do the basics.
8 months ago
0
1
0
[ new blog ] "Using Kiro specs to build IaC out of a shell script"
it20.info/2025/09/usin...
loading . . .
Using Kiro specs to build IaC out of a shell script
In this post, I am continuing my Kiro experiments to produce better specs outcomes. I am doing so using my demo app repository …
https://it20.info/2025/09/using-kiro-specs-to-build-iac-out-of-a-shell-script/
9 months ago
0
0
0
[ Blog ] Using Q CLI to validate the implementation of Kiros specs
it20.info/2025/09/usin...
loading . . .
Using Q CLI to validate the implementation of Kiros specs
Many of us have one or more litmus tests for assessing the capabilities and workflows of generative AI code assistants. Simon Willison has his "Pelican on …
https://it20.info/2025/09/using-q-cli-to-validate-the-implementation-of-kiro-specs/
9 months ago
0
0
0
Very interesting (and on point) article on the state of coding agents with respect to their prices and costs. I love that more people are starting to speak the truth about the current situation.
ethanding.substack.com/p/ai-subscri...
TL/DR (from the article itself):
9 months ago
0
2
0
On one hand I feel the world move too fast. And then I see these things were people still think “the cloud is just someone else’s computer”. And it suddenly feels 2015 all over again.
add a skeleton here at some point
9 months ago
0
1
0
reposted by
Massimo Re Ferré
Luc van Donkersgoed
10 months ago
The AWS News Feed is currently without funding 😢 Meanwhile development of new features continues, the site's numbers are consistently growing, and with the pre:Invent season about to fire up we expect only more visitors and subscribers in the coming months! Will you become a sponsor? Send me a DM!
0
2
3
Passimo is a first.
10 months ago
1
2
0
The electronics version of “it works on my machine”. We need a Docker for cords.
add a skeleton here at some point
10 months ago
1
1
0
Blown away by your response to Kiro. 100k+ joined our preview in week one, more than we expected. We've added a waitlist. To those waiting – thank you for your patience. Using Kiro? Your feedback means everything. Read the full update on our blog:
bit.ly/4o31OHE
loading . . .
This is fine... (really)
https://bit.ly/4o31OHE
10 months ago
11
27
10
11 months ago
0
1
0
reposted by
Massimo Re Ferré
Luc van Donkersgoed
11 months ago
Remote. Debugging. For. Lambda. This is the biggest change in Lambda since microsecond billing. You can set a breakpoint in VSCode on your machine, execute the function in the cloud, inspect its state, and step through the remote process. This is yuuuge!
aws-news.com/article/2025...
loading . . .
Simplify serverless development with console to IDE and remote debugging for AWS Lambda
AWS Lambda introduces console to IDE integration and remote debugging, enabling developers to streamline serverless development by easily moving function code ...
https://aws-news.com/article/2025-07-17-simplify-serverless-development-with-console-to-ide-and-remote-debugging-for-aws-lambda
2
19
5
reposted by
Massimo Re Ferré
Danilo Poccia
11 months ago
Introducing Amazon Bedrock AgentCore: Securely deploy and operate AI agents at any scale (preview) 👉 A comprehensive set of enterprise-grade services that help developers quickly and securely deploy and operate AI agents at scale using any framework and model
go.aws/46eKVUa
#AWS
#AI
#GenAI
#MCP
loading . . .
Introducing Amazon Bedrock AgentCore: Securely deploy and operate AI agents at any scale (preview) | Amazon Web Services
Amazon Bedrock AgentCore enables rapid deployment and scaling of AI agents with enterprise-grade security. It provides memory management, identity controls, and tool integration—streamlining…
https://go.aws/46eKVUa
1
8
7
reposted by
Massimo Re Ferré
Hacker News 100
11 months ago
Kiro: A new agentic IDE
https://kiro.dev/blog/introducing-kiro/
https://news.ycombinator.com/item?id=44560662
loading . . .
Introducing Kiro
A new agentic IDE that works alongside you from prototype to production
https://kiro.dev/blog/introducing-kiro/
0
4
3
reposted by
Massimo Re Ferré
Brian McEntire
11 months ago
IMO, this is the equivalent of 2 Michelin Stars 😅
add a skeleton here at some point
2
39
2
I will take "not terrible" from
@quinnypig.com
... How do they say? "It means a lot coming from you" ?
add a skeleton here at some point
11 months ago
0
3
0
Don't worry Patricia! I am going to be your safe!
11 months ago
0
1
0
“There is only one thing in the world worse than being talked about, and that is not being talked about.” (Oscar Wilde)
add a skeleton here at some point
11 months ago
0
2
1
"I have received an email that you can find in the file lambda-email.txt. You have access to the AWS account. Can you figure what I should be doing to resolve this problem and anticipate issues?" Using
#QCLI
to deal with Lambda runtime deprecations.
11 months ago
0
0
0
This world is doomed.
add a skeleton here at some point
11 months ago
1
1
0
TIL that Anthropic credits expire. But you can set auto-renew so that you can invest even more money in credits (that will expire). 🤔💁♂️
11 months ago
0
2
0
Where do we sit (today) on the spectrum that goes from... "GenAI is going to replace all developers" to... "Gen AI doesn't work and won't work"?
12 months ago
1
0
0
I have to concur
add a skeleton here at some point
12 months ago
0
1
0
Kubernetes homelab
add a skeleton here at some point
about 1 year ago
0
0
0
about 1 year ago
0
0
0
reposted by
Massimo Re Ferré
Clare Liguori
about 1 year ago
Fun chat about Strands Agents, I love it when the space station is involved in demos
www.youtube.com/watch?v=Ausm...
loading . . .
Model Driven Agents - Strands Agents (A New Open Source, Model First, Framework for Agents)
YouTube video by AWS Developers
https://www.youtube.com/watch?v=Ausm87d5Ry8
1
14
6
reposted by
Massimo Re Ferré
Clare Liguori
about 1 year ago
Excited to open source Strands Agents today! LLMs have gotten so good at reasoning and tool use that building model-driven agents with Strands is easy AND powerful Models + Tools = 🧬 Read more:
aws.amazon.com/blogs/openso...
loading . . .
Introducing Strands Agents, an Open Source AI Agents SDK | Amazon Web Services
Today I am happy to announce we are releasing Strands Agents. Strands Agents is an open source SDK that takes a model-driven approach to building and running AI agents in just a few lines of code. Str...
https://aws.amazon.com/blogs/opensource/introducing-strands-agents-an-open-source-ai-agents-sdk/
0
17
8
reposted by
Massimo Re Ferré
Niko Virtala
about 1 year ago
@mreferre.bsky.social
this Q thingy is pretty good. right now I only wish the VSCode plugin agentic mode would have a similar option to run commands autonomously as the CLI version has [t] — now the flow keeps waiting for me to run them and that unnecessary interruption is just a waste of time
1
1
1
The Gen AI 2025 version of the "17 ways to run containers"
about 1 year ago
0
2
1
Kind of funny in a ... recursive way
about 1 year ago
0
0
0
reposted by
Massimo Re Ferré
Gergely Orosz
about 1 year ago
This can happen with any AI agent… or human developer! A BIG difference w AI agents: they will write more code, faster than before, and ship a LOT more code to prod! So ship more bugs as well. Software engineers (not AI engineers) will build o11y solutions to solve for this!
6
63
17
What’s going on on LinkedIn? LOL
about 1 year ago
0
0
0
This is the list, in descending order, of the most expensive compute options out there: 1- Lambda 2- Fargate 3- EC2 4- Lightsail/VPS 5- a Dell server 6- a white-box server 7- a build-your-own server Consider the cost of labor to increase as you go down the list. It's that simple.
add a skeleton here at some point
about 1 year ago
0
2
0
@simonwillison.net
bringing wisdom as usual
simonwillison.net/2025/May/1/n...
loading . . .
Two publishers and three authors fail to understand what “vibe coding” means
Vibe coding does not mean “using AI tools to help write code”. It means “generating code with AI without caring about the code that is produced”. See Not all AI-assisted …
https://simonwillison.net/2025/May/1/not-vibe-coding/
about 1 year ago
0
2
0
reposted by
Massimo Re Ferré
Deepak
about 1 year ago
MCP all the things
aws.amazon.com/blogs/devops...
loading . . .
Extend the Amazon Q Developer CLI with Model Context Protocol (MCP) for Richer Context | Amazon Web Services
Earlier today, Amazon Q Developer announced Model Context Protocol (MCP) support in the command line interface (CLI). Developers can connect external data sources to Amazon Q Developer CLI with MCP su...
https://aws.amazon.com/blogs/devops/extend-the-amazon-q-developer-cli-with-mcp/
0
5
1
"It's a beautiful gold card"
about 1 year ago
0
1
0
MCP needs a Docker Hub
loading . . .
about 1 year ago
1
1
0
Load more
feeds!
log in