Sign in to view Nhat Cuong’s full profile
or
Already on LinkedIn? Sign in
By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy.
Sign in to view Nhat Cuong’s full profile
or
Already on LinkedIn? Sign in
By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy.
United Kingdom
Sign in to view Nhat Cuong’s full profile
Nhat Cuong can introduce you to 10+ people at Meta
Join with email
or
Already on LinkedIn? Sign in
By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy.
552 followers
500+ connections
Sign in to view Nhat Cuong’s full profile
or
Already on LinkedIn? Sign in
By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy.
View mutual connections with Nhat Cuong
Nhat Cuong can introduce you to 10+ people at Meta
Join with email
or
Already on LinkedIn? Sign in
By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy.
View mutual connections with Nhat Cuong
or
Already on LinkedIn? Sign in
By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy.
Sign in to view Nhat Cuong’s full profile
or
Already on LinkedIn? Sign in
By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy.
About
Welcome back
By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy.
New to LinkedIn? Join now
Activity
552 followers
-
Nhat Cuong Nguyen shared thisQwant recrute un data engineer pour travailler sur ses problématiques NLP! Opportunité de travailler sur un moteur de recherche et un projet européen :) Poste basé sur Neuilly. #nlp #data #deeplearningNhat Cuong Nguyen shared thisData processing for NLP Qwant recrute ! Vous pouvez nous aider en diffusant largement cette annonce. Je répond avec plaisir à vos questions. https://lnkd.in/e9q7Eq9
-
Nhat Cuong Nguyen shared thisActable AI, a no-code deep learning data analytics made by ex-Googler, just released a first video about their service and it looks exciting!Nhat Cuong Nguyen shared thisCheck out our new video. Actable AI's automated, no-code Deep Learning platform empowers domain experts to get deep data insights in minutes instead of waiting weeks, months or years to see their needs met by tech people. https://lnkd.in/dA2sQTC #AI #deeplearning #datascience #dataanalytics #nocode #businessanalytics #ActableAIActable AI - No-code, Powerful Data Analytics with Deep Learning AIActable AI - No-code, Powerful Data Analytics with Deep Learning AI
-
Nhat Cuong Nguyen shared thisHi everyone, All along my career in Tech, I find that to communicate clearly is a valuable skill in any team or project. In this article, I try to make clarity easier to achieve. I introduce 2 simple rules. They are no secrets, but knowing them is not enough. I dig in and analyse why these rules are hard to follow, and give some suggestions to make them easier. Hope this helps some of you or maybe your colleagues who struggle to communicate clearly.
-
Nhat Cuong Nguyen shared thisDear all, I used my spare time recently to write an article. Since my field is not Public Health or Virology, my article is about Software Engineering. While I am socially distanced to all of you, I hope I can still be useful to some. It is my take to answer a very simple question: What is the first thing to do to start a Software Engineering task? #softwareengineering Stay safe, stay calm. I hope we will soon shake hands and "faire la bise" again.
-
Nhat Cuong Nguyen shared thisAlizée Gau et Hugo Venturini produisent un projet documentaire sur le rôle de l'art dans un temps de transition. Je trouve leur travail sublime. Il faut beaucoup de courage et de coeur pour s'ouvrir et pour comprendre l'autre comme ils font. Je ne peux que vous le partager humblement et vivement. Puis, Il y a grande chance que désormais nous serons toujours dans un temps de transition...Nhat Cuong Nguyen shared this[PUBLICATION] 4ème épisode de Katharsis pour Usbek & Rica, cette fois-ci sur la France ! Après le Rwanda, puis le Québec, l'Hexagone n'est pas en reste : à Nantes puis à Paris, nous avons rencontré les artistes qui transforment nos agoras, un projet à la fois... Et réinventent la ville de demain. Avec Hugo Venturini à l'audio, et moi-même à la plume ainsi qu'à la photographie. Un grand merci à Blaise Rosnay, Fanny Broyelle, Malte Martin, Jean Blaise, François Delarozière et Stéphanie Aubin pour leurs témoignages, ainsi qu'à Usbek&Rica pour cette belle collaboration. https://lnkd.in/g6c87xj
-
Nhat Cuong Nguyen shared thisFrom Software Engineers to CTO - How not to fail your communication Are you a software engineers or do you work in technology? Have you ever had troubles trying to understand others or having yourself understood? I’m having a little talk about this subject at the Officience hq in HCM city on Friday July 12th. Being an insider, I thought quite a while about this, and the talk will combine my personal experience, thoughts as well as some knowledge from the books I read. We will of course discuss openly. As the event will be in HCM city, the talk and discussion will be in Vietnamese. The event is free and all of you will be very welcome if interested! Here is the link to claim your free place:Từ lập trình viên đến CTO: Diễn đạt rõ ràng và hiệu quảTừ lập trình viên đến CTO: Diễn đạt rõ ràng và hiệu quả
-
Nhat Cuong Nguyen shared thisCher réseau, comment vous ORGANISEZ vos NOTES? Notes de travail? Notes d'étude? Notes numériques? Si oui lequel? (Evernote?) Notes sur papier? Si oui combien de carnets en parallèle? C'est honnêtement une question que je me pose. Et vu le nombre de gens qui achètent soit Evernote soit des Moleskine, la réponse devrait se trouver quelque part! Merci d'avance de vos réponses.
-
Nhat Cuong Nguyen shared thisGuys, I wish you all a very inefficient day. And remember, trying to be perfect is a waste of time! It is to be taken with a grain of salt, obviously, but reading this is so relieving :D
-
Nhat Cuong Nguyen shared thisNhat Cuong Nguyen shared thisInterested in #ArtificiaIIntelligence? Have a look at these great cheatsheets created by our engineering students and twin brothers Afshine Amidi and Shervine Amidi! #IA Now available on Github Suite At At&T Field: http://bit.ly/2xB1I1C See: >> Deep Learning: http://stanford.io/2BsQ91Q >> Supervised Learning: http://stanford.io/2nRlxxp >> Unsupervised Learning: http://stanford.io/2MmP6FN >> Tips and tricks: http://stanford.io/2MEHwFM ---- Aussi en version française : >> Apprentissage profond : http://stanford.io/2NLrRVv >> Apprentissage supervisé : http://stanford.io/2NKScTI >> Apprentissage non-supervisé : http://stanford.io/2pc0q9t >> Petites astuces : http://stanford.io/2xmhGO3
-
Nhat Cuong Nguyen liked thisNhat Cuong Nguyen liked thisJ’en suis seulement à la page 9 sur 18 et j’hésite entre un bon shot de rhum ou un anxiolytique… Besoin urgent d’aller faire un câlin à un 🌳.
-
Nhat Cuong Nguyen liked thisNhat Cuong Nguyen liked thisIt was a pleasure to meet CFOs in both Phoenix and San Francisco last week. Two cities benefiting from the AI boom: SF in the application layer and Phoenix in chips and infrastructure. The Zalos (YC F25) team and I spent time with finance leaders across the two cities. Despite the different roles of both cities in the ecosystem, the priorities for CFOs are identical. CFOs are excited to use agents to start reducing inaccuracies and compliance risks in their accounting processes. The shared goal is to start saving on the significant time currently invested in manual processes. These conversations highlight that the desire for more reliable, automated accounting is universal. Loved hosting this one and hearing such honest perspectives. DM me if you are a CFO or finance leader, we would love to see you at the next one!
-
Nhat Cuong Nguyen reacted on thisNhat Cuong Nguyen reacted on thisI am very honoured to be part of Citywire’s selection of fund managers under 40 managing over $1bn in assets. In the current market environment, the message I shared feels even more relevant. I feel fortunate to be surrounded by experienced and talented colleagues, and I’m sincerely thankful for the trust and support of my managers Hervé Boiral, CFA, Jean-Marie DUMAS, Amaury d'Orsay. A special thank you as well to the credit team (alias the “DreamTeam”) for their continued support throughout this journey Laure Canivet Donsimoni, Alban de Faÿ, Raphaël Chemla, Daniela Montezuma, Maeva Ramadier, CFA, Lucie Dronneau, Arnaud Sliman
-
Nhat Cuong Nguyen liked thisNhat Cuong Nguyen liked thisNo API? No problem. Zalos (YC F25) just raised $3.6M. The startup trains AI agents from screen recordings of real finance workflows. It requires no custom connectors and no changes to existing systems. It runs inside the exact tools finance teams already use. The founders come from Agicap, Apple Pay, and Y Combinator's Fall 2025 batch. Read more: https://lnkd.in/d6j8FKfu
-
Nhat Cuong Nguyen reacted on thisNhat Cuong Nguyen reacted on thisZalos (YC F25), a Y Combinator-backed startup founded in 2025 by CEO William Fairbairn and CTO Hung Hoang, has raised $3.6 million in a seed funding round led by 14Peaks Capital. The company builds AI “Computer Use Agents” that automate repetitive corporate finance tasks such as reconciliations, transaction categorization, and form-filling by logging directly into existing enterprise platforms like Oracle, NetSuite, SAP, and Quickbooks. Operating out of London and San Francisco, Zalos aims to serve CFOs and finance teams at large enterprises, positioning its technology as an “invisible Finance Manager” that reduces millions of hours spent on routine operations while improving over time through reinforcement learning. FOUNDERS: William Fairbairn & Hung Hoang INVESTOR: 14Peaks Capital ROUND: Seed AMOUNT: $3,600,000 HQ: London, United Kingdom #VentureCapital #Zalos #WilliamFairbairn #HungHoang #TradedVC
-
Nhat Cuong Nguyen reacted on thisNhat Cuong Nguyen reacted on thisI am excited to be speaking at Iceberg Summit 2026 on April 8 2026. Hope to see you there! https://lnkd.in/gKjTXDMv
-
Nhat Cuong Nguyen reacted on thisMost of my time will not be on stage at GenAI Zürich ;-) Swing by SkipLabs booth and say hi !Nhat Cuong Nguyen reacted on this🎤 Dr Hugo Venturini, Software Engineer at SkipLabs, takes the stage at GenAI Zürich 2026! 🎙️ Talk title: "Constraining AI Until It Works" The compiler changed everything. Before it, programmers worked in assembly – painstaking, error-prone, impossible to scale. The compiler introduced a contract: if it finishes, the output works. You don't read the assembly. You trust it. That contract unlocked decades of software progress. Today, AI is writing more code than ever. But that contract is gone. Agents say "done" when the code is broken. Engineers spend more time debugging AI output than shipping. What if we could bring that contract back? In this talk, we'll explore how combining opinionated execution, reactive computation, and sound static analysis can restore deterministic confidence to AI-generated code – and what it takes to make "done" mean done again. ⏳🎫 Less than one month left until GenAI Zürich 2026! Secure your conference pass via this link: https://lnkd.in/eE5ceX6X 🧑💻 « From Prompt to Product » – Join the GenAI Zürich Hackathon 2026 and turn your GenAI ideas into real solutions: https://lnkd.in/e8j2AkMY 📅 1–2 April 2026 · Volkshaus Zürich #GenAIZurich #GenAIZurich2026 #GenAIZurich2026Speaker
-
Nhat Cuong Nguyen reacted on thisNhat Cuong Nguyen reacted on thisPROUD : 6 mois après son passage sur Clef de voûte, Alex LeBrun est CEO de AMI Labs, qui a levé hier un des + gros Seed ever ($1,03B). Storytime 👇 Alex est un profil comme on en croise peu. En 25 ans dans la tech, il a notamment : - fondé VirtuOz, une startup d’IA revendue après 10 ans - lancé wit.ai, rachetée par Meta 2 ans plus tard - travaillé directement avec Yann LeCun sur l’IA chez Meta. Mais Alex reste avant tout un entrepreneur. En 2021, il cofonde Nabla, une startup qui utilise l’IA pour aider les médecins à documenter leurs consultations. 85 000 médecins l'utilisent et la startup lève $120M. Mais Alex va prendre une décision peu commune : Quitter son rôle de CEO de Nabla pour rejoindre AMI Labs. La raison ? Il est convaincu que la prochaine génération d’IA ne se contentera pas de générer du texte. Elle devra comprendre le monde. C’est exactement l’ambition de Yann LeCun, qui a quitté Meta pour lancer AMI Labs : un laboratoire qui conçoit des “world models”. Venant de Nabla, Alex voit immédiatement où appliquer ces avancées : la médecine. En janvier dernier, il rejoint donc AMI Labs comme CEO. Et hier, la startup a annoncé une levée record de $1,03 milliards. Un des plus gros Seed jamais levés. J’ai eu la chance de recevoir Alex sur mon podcast Clef de voûte il y a 6 mois. Ce qui m’avait marqué pendant l’épisode : son humilité et sa capacité à naviguer entre recherche IA de pointe et obsession produit. Une combinaison rarement vue parmi mes 150 invités. Un grand bravo à Alex et toute l’équipe d’AMI Labs. — PS : si vous voulez comprendre comment Alex pense l’IA et le produit, je remets ici l’épisode de Clef de voûte 👇
-
Nhat Cuong Nguyen reacted on thisNhat Cuong Nguyen reacted on thisTypes aren't annotations. They're logic in disguise. Most programmers think of types as labels: "this is an int, that's a string." The typechecker watches for mismatches, the compiler uses them for optimizations, and that's about it. In type theory, types are something else entirely. A type is defined by exactly two things: how you construct its values (introduction rules) and how you use them (elimination rules). There's no memory, no bytes, no machine. The type is its rules. Take pairs. A programmer thinks: "(int, string) is two values packed together." A type theorist says: "If you have an A and a B, you can introduce a pair. If you have a pair, you can project out either element." That's the whole definition. Here's where it gets strange. Those introduction and elimination rules follow the exact same patterns as the rules of formal logic. Constructing a pair looks like proving "A and B." Choosing between two types looks like proving "A or B." A function from A to B looks like proving "if A, then B." This isn't a metaphor. It's a formal correspondence called the Curry-Howard isomorphism. Why should a working programmer care? Because as AI agents write more of our code, we're increasingly alienated from it. Fuzzy natural language prompts aren't precise enough to specify what we actually want, let alone verify what the agent built. The UK's Safeguarded AI project (£59 million, 60 researchers, heavy on category theorists) [1] is building exactly this: software where you formally specify requirements, have AI design the system, then verify it meets your spec. The specification language isn't English. It's math. The ability to think formally about the problem you're solving will be the defining skill of this era of software engineering. Are you seeing formal methods or type-theoretic thinking show up in how your team works with AI agents? #TypeTheory #Programming #SoftwareEngineering #AI #FormalMethods
Experience & Education
-
Meta
******** ********
-
*********
***
-
**********
**** ***** ******** ********
-
***************
******** ******* ****** ****** *********** *** ******** ******* undefined
-
-
***** **************
******** ** **** **** ************ ******** ******** *******
-
View Nhat Cuong’s full experience
See their title, tenure and more.
Already on LinkedIn? Sign in
By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy.
Licenses & Certifications
Volunteer Experience
-
President, Lead of Content
CAFE SACH - ROBOOKSTA
- Present 10 years 1 month
Education
We explore and implement new ways for people to share and to connect around their books and reading experience.
This takes form as monthly offline events in Paris with 25-40 attendants. We are expanding and experimenting the model in different cities.
I am mainly in charge of the Content strategy and implementation.
Our team are 8 and we rock!
Projects
-
Booklender - Side project
- Present
See projectBooklender is a tool to manage to whom you have lent your books. The project has the ambition to be as simple and easy to use as possible.
Languages
-
English
Full professional proficiency
-
French
Native or bilingual proficiency
-
Vietnamese
Native or bilingual proficiency
View Nhat Cuong’s full profile
-
See who you know in common
-
Get introduced
-
Contact Nhat Cuong directly
Explore more posts
-
Katherine Perron
SheerForce Solutions - AI… • 811 followers
You know what nobody's talking about? The orchestration tax. OpenAI just shipped multi-agent routing directly into their API. No SDK. No wrapper. Just native request delegation across specialized models. That's not a feature update — it's them admitting that the hardest part of building with AI isn't the model quality anymore. Every team I know has someone spending 40% of their time writing routing logic. Which agent handles what. How to pass context. What fails over where. It's invisible, unglamorous, and it's the reason most AI projects ship 6 months late. Most people think this makes developers lazy. I think it makes them dangerous. When you stop solving plumbing problems, you start solving real ones. The teams that move fast this year won't be the ones with the best ML engineers — they'll be the ones who deleted the most code. What's the ugliest orchestration workaround currently running in your stack? #AI #APIs #Automation https://lnkd.in/eYfSendB
-
Sam Barker
IBM • 827 followers
The Kroxylicious project is very pleased to announce the release of Kroxylicious 0.16.0 [1]. See the Changelog [2] for a list of changes and summary of Deprecations, Changes and Removals. Apache Kafka 4.1.0 compatibility - The main change in this release is Apache Kafka 4.1.0 compatibility. The proxy will now relay Kafka 4.1 specific versions of the Kafka RPC and your filters can intercept them. Observability improvements - Thanks to the work of hrishabhg[3], the proxy now sports connection count gauges, allowing you to monitor downstream and upstream connection counts in realtime. [1] https://lnkd.in/gRw5a_SU [2] https://lnkd.in/gRUJ9h2J [3] https://lnkd.in/gxaPwviu
26
-
Justin Reidy
Product and engineering… • 2K followers
Claude Code and Claude Agent SDK are two great tastes that taste great together. The same "primitives" for working with Claude Code – Skills, Commands, Subagents – are you what employ when configuring your own agentic harness with the Agent SDK. So the lessons and best practices you learn while coding contributes DIRECTLY to the agentic system(s) you're architecting, and vice versa. You should probably be experimenting with multiple harnesses (for both coding and implementation). But if you can choose only one, it's hard to argue with Claude.
12
3 Comments -
Louhab Ali
Zone01 Oujda • 604 followers
𝗜𝗻𝘁𝗿𝗼𝗱𝘂𝗰𝗶𝗻𝗴 𝟬-𝗦𝗵𝗲𝗹𝗹 — a 𝗨𝗻𝗶𝘅-𝗹𝗶𝗸𝗲 𝘀𝗵𝗲𝗹𝗹 𝗯𝘂𝗶𝗹𝘁 𝗳𝗿𝗼𝗺 𝘀𝗰𝗿𝗮𝘁𝗰𝗵 𝗶𝗻 𝗥𝘂𝘀𝘁. We created a lightweight, 𝗺𝗼𝗱𝗲𝗿𝗻 𝘀𝗵𝗲𝗹𝗹 𝗳𝗼𝗿 𝗟𝗶𝗻𝘂𝘅 𝗲𝗻𝘃𝗶𝗿𝗼𝗻𝗺𝗲𝗻𝘁𝘀—𝗻𝗼 𝗕𝗮𝘀𝗵, 𝗻𝗼 𝗲𝘅𝘁𝗲𝗿𝗻𝗮𝗹 𝘁𝗼𝗼𝗹𝘀—just pure system-level programming. 𝗪𝗵𝗮𝘁 𝗶𝘁 𝗱𝗼𝗲𝘀: Smart prompt with 𝗚𝗶𝘁 𝗯𝗿𝗮𝗻𝗰𝗵 + 𝗽𝗮𝘁𝗵 𝗖𝗼𝗹𝗼𝗿𝗳𝘂𝗹 𝗼𝘂𝘁𝗽𝘂𝘁 like Zsh (syntax highlighting, error hints) 𝗕𝘂𝗶𝗹𝘁-𝗶𝗻 𝗰𝗼𝗺𝗺𝗮𝗻𝗱𝘀 like cd, ls, cat, rm, echo, mkdir, etc. Handles signals (𝗖𝘁𝗿𝗹+𝗗), errors, and user input like a real shell 𝗪𝗵𝘆 𝗶𝘁'𝘀 𝗰𝗼𝗼𝗹: Written 𝟭𝟬𝟬% in Rust Re-implements 𝗰𝗼𝗿𝗲 𝘀𝗵𝗲𝗹𝗹 𝘁𝗼𝗼𝗹𝘀 Deep dive into terminal control, ANSI colors, input parsing, and more ... I worked on cat, rm, cd and some parsing tasks —focusing on file operations and graceful error handling while Amine Habchi made the project structure and worked on ls command in addition to cp , mv and parsing cmdline. Handling these features wouldn’t have been possible without abdelouahab khir who made a powerful parsing system as well as echo , mkdir , pwd tracking and other features. Check it out : https://lnkd.in/ev5fU4_b #Rust #Linux #Shell #SystemProgramming #OpenSource #CLI #TerminalTools
34
4 Comments -
Nikolay Kopylov
Kranus Health • 3K followers
That's a wonderful way to promote it in the, probably, most conservative and pushback community. And I get the pushback - the wave of PRs lacking context made it increasingly hard to be a maintainer of any popular open source product. Well, let's see if the problem gets solved when AI is employed on the other side as well. Wonderful times we are living in!
1
1 Comment -
Aymeric C.
Mercari, Inc. • 548 followers
I wrote an article on how we translate user-generated content at scale at Mercari. It summarizes two years of work with various models, LLMs but not only, and how cost evolved, reducing it 100x over the period. I also go over non-AI features and user experience. https://lnkd.in/gbpQAQmX
39
2 Comments -
Mateusz Stepniak
Allegro • 385 followers
What do we do at Allegro when we find promising technology? We battle-test it. 🛠️ More than six years ago, we built MBox, our in-house Server-Driven UI solution. Over time, as our ecosystem evolved, so did our expectations. We began exploring alternatives to our internal technology stack, looking for solutions that could offer the best of both worlds: the speed and flexibility of server-driven UI, combined with truly native performance and a modern developer experience. That search led us to Lynx, a recently released, open-source cross-platform framework designed around native rendering. On paper, it looked too good to ignore. Read the full story of why we’re exploring Lynx and how it integrates with our ecosystem on #AllegroTechBlog ➡️ https://shr.bi/wKWPKn5s
6
-
Daniel Westall
Freelance • 418 followers
Been hands-on work with Amazon Q Developer recently, good base models and some interesting ideas, enjoying my time with it. 🎯 Always Plan Before You Act The best results come from plans, planing first, then execute. Tools like Cline nail this with explicit "plan" and "act" buttons - you can even push the planning phase to a cheaper model while reserving expensive compute for execution, Amazon Q doesnt have this, but !always ask your AI to create a plan before taking action. Recent research papers back this up - agentic workflows with explicit planning phases significantly outperform back and forth conversation approaches. Also dont forget to ask it for questions! 👑 Context Is for Kings ( win if you know the quote ) Amazon Q really shines here with its profiles system, which I think beats tools like Gemini CLI hands down. Its secret sauce? Scope your context strategically: • Keep general contexts global across all profiles • Create focused, profile-specific contexts for specialized work • Always include business language in project contexts - your AI should speak your domain, not just code Pro tip: Got an internal library? Have your LLM generate context and bake it directly into projects that use it. This creates self-documenting, AI-friendly codebases. ⚡ MCP: Great Power, Great Responsibility Model Context Protocol integration is a game-changer, but use it wisely. Atlassian's MCP implementation is my go-to - it transforms how you work with tickets, documentation, and project context, it also enables some awesome workflows. But be selective about which external systems you connect. More isn't always better and there's is a vast quality cliff and thats not touching on the deep hole of MCP security. 🛠️ Command Line Precision Instruct your LLM to use command-line tools for anything requiring precision. Don't let your AI wing it on: • Code formatting and style enforcement • Package version management When your AI can directly invoke linters, package managers, and build tools, you get consistent, reliable results instead of "close enough" approximations. 💡And Finally ........ The Reality Check AI-assisted development isn't plug-and-play magic. There's a real learning curve, and success comes from combining thoughtful tooling with solid engineering practices. The tools can bootstrap your workflow and handle routine tasks brilliantly, but they can't replace intentional implementation and good foundations like documentation, because guess what LLM needs to really shine documentation. But the engineer using the tool correctly remains the critical factor and theres a interesting conversation about a engineers who truly leverage these tools vs those that dont. I've been learning this tools, because as i've said before they are changing our industry, knowing what these tools will do to your engineering team is critical for the coming years or maybe .. tomorrow. Any Amazon Q tricks your want to share? #amazon #amazonq #llm #engineeringtooling
18
3 Comments -
Mauricio Pérez Romero
Winston Artory Group • 3K followers
3 days ago I shared AgentLint — 10 rules to stop AI agents from drifting during long sessions. Since then I've shipped 4 major releases. Here's what changed: 10 rules → 42 rules across 7 packs AgentLint now auto-detects your stack and activates the right guardrails: 🐍 Python — bare excepts, unsafe shell, SQL injection, dangerous migrations 🎨 Frontend — accessibility checks (alt text, form labels, focus states, touch targets) ⚛️ React — loading states, empty states, lazy loading 🔍 SEO — metadata, Open Graph, semantic HTML, structured data 🔐 Security (opt-in) — blocks Bash file writes that bypass guardrails, catches data exfiltration attempts Full lifecycle coverage AgentLint went from 3 hook events to all 17 that Claude Code supports. New always-active quality rules: - Validates commit messages - Catches dead imports - Warns when error handling gets removed - Injects a self-review prompt at session end - Tracks session length and warns before things drift AGENTS.md support If your project uses AGENTS.md, AgentLint reads it and generates matching config automatically. Installation that just works I dogfooded a fresh install and hit the same PATH issues many developers face with pip on macOS. Fixed it — the resolver now probes 5 locations to find the binary. No more manual PATH hacking. The numbers 42 rules. 741 tests. 96% coverage. All running locally in milliseconds. pip install agentlint agentlint setup If you're running AI agents on production codebases, the question isn't whether they'll drift — it's whether you'll catch it before or after it ships. 👉 https://lnkd.in/eRMqpDHd #AI #ClaudeCode #DevTools #OpenSource #CodingAgents #DeveloperExperience #Python #AgentSafety
7
-
Hemant Rathore
Teikametrics • 2K followers
We moved from RabbitMQ to AWS SQS. Reliability, not throughput, forced the decision. At our traffic levels, failures were silent. Backlogs growing quietly during peak traffic. On-call pain became our strongest signal. We asked a hard question internally. Can this system degrade gracefully at scale? RabbitMQ required constant operational tuning. Disk pressure. Broker health. Backpressure management. Too many sharp edges for our growth curve. SQS offered fewer operational failure modes. Managed durability with a simpler surface area. But reliability did not come for free. We redesigned consumers around idempotency. Visibility timeouts were treated as strict contracts. Lag became a first-class reliability metric. Retries were explicit, observable, and bounded. The result was a calmer system overall. Fewer incidents during traffic spikes. Monitoring became actionable. On-call was mostly uneventful. Engineering focus shifted back to delivery. At our scale, operational simplicity became reliability. What early reliability signal did you ignore and regret? #EngineeringLeadership #ScalableSystems #ReliabilityEngineering
42
6 Comments -
Bharat Meda
Syren • 4K followers
AI-assisted solutioning makes me 𝕟𝕠𝕤𝕥𝕒𝕝𝕘𝕚𝕔. As part of Syren’s solutions team, I work with multiple models* to build scalable, feature-rich, service-oriented, and agentic supply-chain solutions. [* I often find myself returning to Claude Opus 4.5; read about Opus 4.6 this morning, will check it out] I am genuinely enjoying building closer to the speed of thought. But also pausing to observe and appreciate, between each session, the importance of context and intent. As much as I am training the models, I am also getting better at the art of planning, utilizing the tokens, multi-modal, and context refinement. And of course, validation of the solutions with functional experts and business leaders is imperative. That said, it’s hard not to feel a bit nostalgic about the "classic" days of software engineering. ▪️ PRs that encouraged deep review and healthy debate around standards and consistency (sometimes also abused by overly zealous engineers) ▪️ UX discussions that reflected just how seriously teams took user experience (sometimes at every level of leadership) ▪️ Thoughtful (and sometimes lengthy) conversations about dependency upgrades, technical debt, and long-term maintainability ▪️ Estimation and planning exercises designed to bring predictability and alignment to delivery. Agreed, sometimes they were futile ▪️ Strong architectural opinions formed through years of hard-earned experience Many forward-looking organizations are thoughtfully navigating this transition. They are embracing AI to accelerate delivery while still preserving the rigor, discipline, and institutional knowledge that made engineering teams effective in the first place. However, as things continue to evolve rapidly, the challenge (and opportunity) ahead is to continuously find the right balance. What parts of traditional engineering culture are worth preserving as AI reshapes how we build, and which should we finally let go? 🤔 #Syren #AIEngineering #SoftwareEngineering #EngineeringLeadership #GenAI #Claude #ClaudeOpus #AIAgent #Coding
36
3 Comments -
Marc Brooker
Amazon Web Services (AWS) • 19K followers
Most verification folks won't agree with me, but the thing I find most exciting about efforts like this is the bug finding. Standard libraries are extremely highly leveraged places to find and fix bugs: you can fix millions of programs at the same time! Great to see ongoing progress on the Rust standard library verification effort.
165
6 Comments -
Linearloop
12K followers
Your CI/CD bill is not exploding because of “expensive runners,” it is bleeding out through flaky tests, over-parallelized jobs, and slow feedback loops that quietly tax every deploy This piece shows you how to redesign pipelines so you cut compute waste, shrink queues, and speed up developer flow without adding yet another approval gate or YAML religion Full breakdown in the comments. #DevOps #CICD #PlatformEngineering
8
1 Comment
Explore top content on LinkedIn
Find curated posts and insights for relevant topics all in one place.
View top contentOthers named Nhat Cuong Nguyen
-
Nhat Cuong Nguyen
Ho Chi Minh City, Vietnam -
Nhat Cuong Nguyen
Vietnam -
nhat cuong nguyen
Greater Sydney Area -
Nhat Cuong Nguyen
Quận Ninh Kiều
6 others named Nhat Cuong Nguyen are on LinkedIn
See others named Nhat Cuong Nguyen