AWS Hero 🚀 / Cloud Expert 🪄 / Engineering Innovator 🤖

Brno, Česká republika
Joined October 2010
Filip Pyrek retweeted
We have partnered with @AnthropicAI to launch the Claude connector for Fusion. With the Fusion MCP, you can now tap into Claude’s desktop capabilities—speech, vision, web search, and cross-service workflows—right inside your design flow. Combined with #AutodeskAssistant, this opens up more flexible, customizable agentic workflows for how you build with Fusion + Claude. Learn more here: autode.sk/4mXFaQN
Claude
@claudeaiApr 28
Replying to @claudeai
With the Autodesk Fusion connector, designers and engineers can create and modify 3D models through conversation.
31
163
42
1,717
177,248
Filip Pyrek retweeted
Today, we’re evolving @StitchbyGoogle from @GoogleLabs into an AI design canvas transforms natural language prompts into production-ready front-end code. Some highlights from what’s new: 1. A complete redesign of the Stitch UI, which can now ingest multimodal references (text prompts, images, or code) as creative seeds for your design ideas 2. A brand new, context-aware design agent that can share feedback on builds, generate PRDs, and ask questions to better understand your vision. You can even talk to the agent if you prefer a verbal sounding board 3. A new agent-friendly markdown file, DESIGN.md, which you can use to export or import your design rules to or from other design and coding tools Whether you’ve been designing for decades or you’re whiteboarding your first software idea, Stitch can help you turn concepts into prototypes in minutes rather than days ➡️ stitch.withgoogle.com
216
434
81
5,510
20,124,806
Filip Pyrek retweeted
Today, we’re releasing a significant upgrade to our specialized reasoning mode, Gemini 3 Deep Think. Deep Think is built to drive practical applications, enabling researchers to interpret complex data and engineers to model physical systems through code. With the updated Deep Think, you can turn a sketch into a 3D-printable reality. Deep Think analyzes the drawing, builds the complex shape, and generates a file so you can create the physical object with 3D printing. This is rolling out now to Google AI Ultra subscribers. Select the "Deep Think" option in the tools menu to get started. Learn more here: goo.gle/3MoiifF
599
1,857
690
16,549
5,060,870
Filip Pyrek retweeted
Comparing Opus 4.6 to Opus 4.5
23
22
1
310
56,012
I really think there's a huge advantage to vibe coding golang over typescript. Obviously, you wouldn't use golang for frontend. But if your in services land, forgo nodejs and do golang. It's a simple language that has a very consistent ecosystem and AI does well.
12
2
34
4,134
Filip Pyrek retweeted
I missed CDK Aspects when I moved to SST. Being able to modify all resources at once is a superpower. Turns out, you don't have to give that up. You can auto-add alerts to every Lambda function in your stack with a simple transform. Here is how to auto-monitor your entire stack:
1
4
568
Filip Pyrek retweeted
OpenCode 400K monthly active users 40K GitHub stars 400 contributors 2.5M downloads It took us 5 months But it’s based on everything we’ve learnt over 5 years Building consumer apps, open source products, designing SDKs, TUIs, positioning, marketing
77
34
9
1,201
128,821
POLYGLOBE JUST GOT ANOTHER MASSIVE UPGRADE 🌐 DeepStateLive’s Ukraine war map is now draped directly onto the globe, live and synced with @Polymarket . Shaded control zones, shifting frontlines, Russian/Belarusian unit icons and direction of attack arrows all sitting under your markets and OSINT in near real time. These Ukraine geo markets confuse people constantly. is it the city limits, the oblast, “enter” vs “capture all of”? Now, when you hover a market, we draw the exact area of operation it resolves on and spell out the rule in plain English. No more rule debates, no more guessing what actually settles. The only way to monitor the situation.
561
587
1,727
6,990
6,624,560
AWS finally made centralized logging simple 🎉 Everybody says "you need a central logging account" but creating it was quite a hassle. Your options before: 🔹 Observability Access Manager (OAM) Works, but complicated setup. Requires understanding sinks, sources, and links. Not exactly plug-and-play. 🔹 Custom Solutions Log Subscription filters + Kinesis Data Streams + Lambda. You're now maintaining infrastructure instead of building features. 🔹 Third-Party Tools Works great! Costs more. Another vendor dependency. AWS just launched CloudWatch log centralization. Built into Organizations 🔥 What it does: Creates rules that automatically copy logs from source accounts to your central logging account. Cross-account. Cross-region. No Kinesis needed. Setup is three steps: 1️⃣ Delegate your logging account as administrator 2️⃣ Create centralization rules (by account ID, OU, or entire org) 3️⃣ Logs start copying over You can create up to 50 rules. Logs include @aws.account and @aws.region fields for filtering. If you run multiple AWS accounts, this is the simplest path to centralized observability. --- Hey, I’m Sandro — a full-stack engineer who’s built dozens of production-grade apps on AWS. I share what I learn with 11,000+ devs at awsfundamentals.com/newslett….
1
2
19
1,324
Filip Pyrek retweeted
Charly Wargnier ♨️
@DataChaz13 Nov 2025
If you’re still sending raw JSON into your LLMs, you’re burning tokens, latency, and budget! Try TOON (Token-Oriented Object Notation). Clear like YAML, compact like CSV: • 30–60% fewer tokens • Up to 50% lower costs • Shines for tabular data. Free and Open source 🧵↓
508
1,115
468
8,335
2,540,752
Microsoft did it again! Building with AI agents almost never works on the first try. You spend days tweaking prompts, adding examples, hoping it gets better. Nothing systematic, just guesswork. This is exactly what Microsoft's Agent Lightning solves. It's an open-source framework that trains ANY AI agent with reinforcement learning. Works with LangChain, AutoGen, CrewAI, OpenAI SDK, or plain Python. Here's how it works: > Your agent runs normally with whatever framework you're using. Just add a lightweight agl.emit() helper or let the tracer auto-collect everything. > Agent Lightning captures every prompt, tool call, and reward. Stores them as structured events. > You pick an algorithm (RL, prompt optimization, fine-tuning). It reads the events, learns patterns, and generates improved prompts or policy weights. > The Trainer pushes updates back to your agent. Your agent gets better without you rewriting anything. The best part: you can also optimize individual agents in a multi-agent system. I have shared the link to the GitHub repo in the replies! Let me know if I should cover this in a video demo!
57
371
17
2,468
201,558
AWS launched "Automatic quota management" While it is currently only a notification. It seems they are working already on an auto-adjust mode. And I would love to have some default settings in either IAC or an Account Factory available. With that it could be much easier to ensure that devs don't need to handle quotas in new accounts. Since this is typically something you don't know until you debug a weird error for quite some time. Nice step AWS 👍🏽
1
2
1
7
1,409
I got married at 21, started having kids at 23. Obviously that's early for a lot of people. But my focus was always family first, work second. I still worked tons, like really a lot. Now 20 years later can I say that was the best decision. Work is nothing compared to my family.
- fall in love - get married - have kids - work hard - be faithful - stay together - find meaning - be happy
3
3
129
18,010
Holy shit... Stanford just published research that destroys every prompt engineering guru. Turns out most "advanced techniques" are just survivorship bias and confirmation bias. Here's what the data actually shows:
63
166
23
1,173
146,787
At BottleCapAI, we believe AI shouldn’t cost tens of millions to train. We are now opening challenge for those who want to help with that! 🏆 $3K / $2K / $1K prizes ⏰ Deadline: 11/11/2025 🖥️ 1 GPU. Your ideas. 👉 Join the NoCap Test: github.com/BottleCapAI/NoCap…
1
8
3
41
11,037
Google just changed note taking forever. NotebookLM got massive upgrades. 7 Powerful features you can't afford to miss:
31
114
6
1,292
176,188
Three unforgettable days with our #AWSHeroes comes to a bittersweet end. ✨ To our AWS Heroes - your passion and willingness to share knowledge never ceases to inspire us, thank you! 🦸 🦸‍♂️ #AWSHeroesSummit
3
38
13
105
20,179