AI Applications In Engineering

Roadmap to Learn Agentic AI This roadmap breaks down the journey into 12 focused stages: – Grasp the core differences between traditional AI and autonomous agents – Build a solid foundation in ML, LLMs, and frameworks like LangGraph, CrewAI, and AutoGen – Understand how agents use memory, plan actions, and collaborate – Learn to implement retrieval-augmented generation (RAG) and adaptive reinforcement learning – Deploy agents in real-world scenarios with performance monitoring and continuous improvement If you're building AI that goes beyond chat interfaces, this roadmap will help you architect systems that are capable, contextual, and action-oriented. Feel free to save or share if you find it valuable.

"Vancouver, Vancouver! This is it!". Those were the chilling final words of volcanologist David A. Johnston on May 18, 1980, right before the lateral blast of Mount St. Helens removed the top 1,300 feet of the mountain in seconds. Do you remember? In 1980, monitoring required physical proximity, manual seismic readings, and real-time visual observations over radio frequencies. Tragically, traditional models struggled to predict the unprecedented side-slope failure that triggered the catastrophic eruption. Fast forward to today, and Artificial Intelligence is fundamentally changing how we forecast the unpredictable: 🌋 Multi-Modal Data Fusion: Instead of relying on isolated seismographs, AI systems ingest streams of satellite radar, thermal imaging, gas emission data, and micro-seismic activity simultaneously. 🛰️ Pattern Recognition Across History: Machine learning models are trained on eruption patterns globally. A seismic signature in an unmonitored region can now be matched instantly against decades of historical data from thousands of miles away. ⚡ Real-Time Anomaly Detection: Deep learning algorithms (like isolation forests) scan continuous satellite streams in near-real-time to detect subtle thermal spikes or ground deformation weeks before a physical event occurs. 🎯 Bridging the Data Gap: Through transfer learning, AI allows scientists to extend accurate forecasting models to remote, under-monitored regions where millions of lives are at risk. Technology isn't just giving us faster notifications; it’s shifting disaster management from reactive survival to predictive mitigation. Whether in geology, supply chains, or enterprise risk management, the core lesson of Mount St. Helens remains: The signals are almost always there—it’s our ability to process and interpret them in time that saves lives. #Technology #ArtificialIntelligence #DataScience #RiskManagement #AI #Geology #PredictiveAnalytics #FutureOfTech

How do materials fail, and how can we design stronger, tougher, and more resilient ones? Published in #PNAS, our physics-aware AI model integrates advanced reasoning, rational thinking, and strategic planning capabilities models with the ability to write and execute code, perform atomistic simulations to solicit new physics data from “first principles”, and conduct visual analysis of graphed results and molecular mechanisms. By employing a multiagent strategy, these capabilities are combined into an intelligent system designed to solve complex scientific analysis and design tasks, as applied here to alloy design and discovery. This is significant because our model overcomes the limitations of traditional data-driven approaches by integrating diverse AI capabilities—reasoning, simulations, and multimodal analysis—into a collaborative system, enabling autonomous, adaptive, and efficient solutions to complex, multiobjective materials design problems that were previously slow, expert-dependent, and domain-specific. Wonderful work by my postdoc Alireza Ghafarollahi! Background: The design of new alloys is a multiscale problem that requires a holistic approach that involves retrieving relevant knowledge, applying advanced computational methods, conducting experimental validations, and analyzing the results, a process that is typically slow and reserved for human experts. Machine learning can help accelerate this process, for instance, through the use of deep surrogate models that connect structural and chemical features to material properties, or vice versa. However, existing data-driven models often target specific material objectives, offering limited flexibility to integrate out-of-domain knowledge and cannot adapt to new, unforeseen challenges. Our model overcomes these limitations by leveraging the distinct capabilities of multiple AI agents that collaborate autonomously within a dynamic environment to solve complex materials design tasks. The proposed physics-aware generative AI platform, AtomAgents, synergizes the intelligence of LLMs and the dynamic collaboration among AI agents with expertise in various domains, incl. knowledge retrieval, multimodal data integration, physics-based simulations, and comprehensive results analysis across modalities. The concerted effort of the multiagent system allows for addressing complex materials design problems, as demonstrated by examples that include autonomously designing metallic alloys with enhanced properties compared to their pure counterparts. We demonstrate accurate prediction of key characteristics across alloys and highlight the crucial role of solid solution alloying to steer the development of alloys. Paper: https://lnkd.in/enusweMf Code: https://lnkd.in/eWv2eKwS MIT Schwarzman College of Computing MIT Civil and Environmental Engineering MIT Department of Mechanical Engineering (MechE) MIT Industrial Liaison Program MIT School of Engineering

Most AI portfolios look the same. RAG chatbot. Sentiment analysis. Maybe a fine-tuned model. Recruiters have seen it 500 times this week. You need to show off "Multi-Agent Systems" to get you noticed in 2026. The global agentic AI market is projected to grow from $5.1B in 2024 to over $47B by 2030. Every major tech company, from Google to Microsoft, is racing to hire engineers who can build systems where multiple AI agents coordinate, communicate, and act autonomously. The problem? Most people don't know where to start. So here are 10 project ideas that show you can build what the industry actually needs: 🥦 Smart Traffic Control System Fixed signal timings cost urban economies billions annually. Build agents that dynamically adjust signals using real-time traffic data. 🥦 Disaster Response System Poor coordination in emergencies costs lives. Build agents for rescue teams, drones, and medical units that allocate tasks dynamically. 🥦 Autonomous Warehouse System Amazon alone operates 750,000+ robots. Build a system where inventory agents and robot agents collaborate on storage and delivery. 🥦 Multi-Agent Stock Trading Simulator Algorithmic trading accounts for 60-73% of US equity volume. Build competing trading agents, a market maker, trend follower, and arbitrage agent, in a simulated environment. 🥦 Smart Energy Grid System Up to 8% of electricity generated globally is lost due to distribution inefficiency. Build agents that balance demand across homes, grids, and solar sources. 🥦 Delivery Drone System Last-mile delivery accounts for 53% of total shipping costs. Build drone agents that coordinate routes and avoid collisions. 🥦 Medical Diagnosis System Diagnostic errors affect approximately 12 million Americans annually. Build specialist agents (cardiology, radiology, pathology) that collaborate on patient data. 🥦 Multi-Agent Game AI System The global gaming market is worth $200B+. Build RL-based agents that compete and cooperate in a simulated game environment. 🥦 Environmental Monitoring System India has 14 of the world's 20 most polluted cities. Build distributed sensor agents that detect anomalies in air and water quality in real time. 🥦 Personal Assistant System Build a planner agent, research agent, and executor agent that collaborate to handle complex, multi-step tasks, the architecture behind every serious AI product being built today. Each of these maps to a real-world problem, a real industry, and a real hiring need. You don't need to build all 10. You need to build one, document it well, and explain the architecture clearly. That alone puts you ahead of 90% of applicants. Which one are you building?

If you’re an aspiring AI engineer trying to understand how the industry is moving beyond LLMs, here’s a quick eagle’s-eye view of one of the most fascinating frontiers in AI today: 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗔𝗜 𝗦𝘆𝘀𝘁𝗲𝗺𝘀. We’ve reached a point where large language models can generate text, summarize papers, write code, and even reason, but that’s not enough anymore. The next leap isn’t about bigger models. It’s about autonomy, with systems that can not only generate but also decide, act, and adapt in the real world. That’s where Agentic AI Systems come in. These are goal-driven, adaptive platforms capable of orchestrating complex workflows, making independent decisions, and using memory to 𝗥𝗲𝗮𝘀𝗼𝗻 → 𝗔𝗰𝘁 → 𝗔𝗱𝗮𝗽𝘁. Instead of just prompting a model for a single response, you’re designing a network of intelligent components that: → Understand goals and constraints → Plan actions through orchestration frameworks → Execute via tools, APIs, or other agents → Observe results, learn, and improve over time This shift, from intelligence to autonomous intelligence, is why agentic systems have become one of the most important topics for modern AI engineers. 𝗪𝗵𝘆 𝗧𝗵𝗶𝘀 𝗠𝗮𝘁𝘁𝗲𝗿𝘀 → For AI Engineers: Agentic architectures are redefining how applications are built- from RAG pipelines and copilots to autonomous research or data systems. Understanding gateways, planners, orchestrators, memory layers, and evaluation loops will become a must-have skill set. → For Tech Leaders: If you’re leading teams or evaluating where AI fits into your business, this is your blueprint for understanding how next-gen systems will operate- safely, scalably, and with clear policy and observability layers. Happy learning & Happy Building 🚀

Engineers love details. But for Digital Twins, Maximum Detail is a trap. The biggest mistake I see? They try to model everything before they’ve defined the problem. They build a DT that is heavy, expensive, and slow - because they focused on graphical perfection instead of data relevance. Here is the engineering reality: The Purpose dictates the Level of Detail (LoD). If you don't define why you are building the DT, you cannot define what needs to be modeled. Here is how the top players strip away the noise: ❇️ The Automotive Approach (Tesla) They don't just scan the car. They simulate specific data sets: aerodynamics, motor performance, suspension, and body design materials. Goal: Predict performance before design. LoD: Functional data > Visual data. ❇️ The Manufacturing Approach (Siemens) Here, precision matters. The DT is linked to an inspection database including geometry interpretation and kinematic relations. Goal: Eliminate processing errors and improve throughput. LoD: High geometric fidelity to handle tolerances in the assembly line. ❇️ The Energy Approach (General Electric) This is the gold standard for ROI. GE created a "digital twin farm" for wind turbines. Did they model every bolt? No. They focused on the motor temperature and wind strength. The Result: Energy production increased by 20%. Generated $100 million in extra value over the farm's lifespan. The Engineering Takeaway? 🖐️ To implement a DT, you need a process to identify the appropriate complexity. Step 1: Imagine the opportunity (the problem). Step 2: Identify the configuration with the highest value. Step 3: Only then do you determine the LoD. If you are building a DT for facilities management, you don't need the same LoD as an aerospace engineer predicting fatigue failure. Start only modeling what matters! -------- Follow me for #digitaltwins Links in my profile Florian Huemer

I stopped using Claude as a chatbot. I started using it as my Product Design team. 🚀 Most designers use AI for generating copy, rewriting text, or creating random UI ideas. That's only scratching the surface. While working on an AI Interview Engine project, I realized Claude can contribute to almost every stage of product design from problem discovery to developer handoff. Today, my workflow looks very different. How I use Claude to ship AI-powered products 🌱1. Discover & Research - User pain points - Competitor analysis - Market research - Interview questions - Research synthesis Instead of spending hours organizing notes, Claude helps me identify patterns and opportunities faster. 💡 2. Product Thinking & Strategy - PRDs - Feature prioritization - User journeys - Edge cases - Success metrics This is where Claude becomes powerful. Not because it gives answers. Because it helps me ask better questions. 🎯 3. UX Flows & Information Architecture - User flows - Task flows - Journey maps - States and scenarios - Error handling Many UX problems appear before a single screen is designed. 🎨 4. Claude Design + UI Creation - Screen concepts - UX critiques - Design system recommendations - Interaction ideas - Accessibility checks Claude helps me explore more possibilities before committing to a direction. ⚡ 5. Claude Code: This changed my workflow completely. I use it for: - Frontend prototypes - Design system implementation - UX validation - Product simulations - Documentation generation Seeing ideas come alive in code helps uncover issues much earlier. 🌻6. Validation & Iteration - Heuristic reviews - UX audits - Edge case testing - Scenario generation - Accessibility review The goal is not to validate designs. The goal is to validate decisions. 🚀 7. Handoff & Delivery - Functional requirements - Developer documentation - Acceptance criteria - Component behavior - Interaction specifications Developers get more clarity and fewer assumptions. The biggest lesson? AI didn't replace my design process. It amplified it. The more product thinking, judgment, and decision-making I bring, the better the output becomes. That's why I believe the future belongs to designers who can combine: 🧠 Product Thinking 🤖 AI Leverage 🎨 Design Craft 📈 Business Understanding Not just screen design. What part of your design process are you currently using Claude for? 👇 I'd love to learn from your workflow too. #uxdesign #productdesign #uidesign #claudeai #claudecode #artificialintelligence #designsystems #uxresearch #figma #designleadership #aidesign #productdesigner #userexperience #designthinking #aitools #aiindesign #ai #aidesigntools #designercommunity # #juniordesigners #learning #linkedin #creator #uiux

How do we evaluate AGI for Engineering? Designing physical systems — such as drones, electric vehicles, or energy infrastructure — requires more than solving equations. It demands interdisciplinary reasoning, tool fluency, creativity, and sound judgment under constraints. A new paper from P-1 AI offers a robust answer to a pressing question: How can we evaluate Engineering Artificial General Intelligence (eAGI)? The proposed framework: Adapts Bloom’s Taxonomy to map cognitive levels in engineering tasks — from recalling formulas to reflecting on design decisions. Integrates physics-based metadata (domain, system type, standards) to generate realistic and scalable benchmarks. Goes beyond text: it enables evaluation of structured artifacts, like CAD and SysML models. Demonstrates application on a classic problem: motor-propeller matching for eVTOL drones. This marks an essential step toward AI systems that actively collaborate with engineers — not just as copilots, but as creative and critical partners. Highly recommended for those working in: - AGI applied to physical systems - Evaluation of LLMs and autonomous agents - AI-assisted engineering design Link: https://lnkd.in/dQTZyKU6 Title: On the Evaluation of Engineering Artificial General Intelligence Authors: Sandeep Neema, Susmit Jha, Adam Nagel, Ethan Lew, Chandrasekar Sureshkumar, Aleksa Gordić, Chase Shimmin, Hieu Nguyen and Paul Eremenko Great Work!

The AI that saves the planet vs. the AI that eats the grid. Guardian Australia has dropped a bombshell: Australian data centre demand is projected to double by 2030, consuming as much as 11% of NSW's grid. As we head into a hot summer, with AEMO warning of grid reliability risks, this isn't just a future problem. It's an immediate resilience crisis. We are in a paradox. We need AI to optimise the grid, map biodiversity and predict floods. But the 𝘵𝘳𝘢𝘪𝘯𝘪𝘯𝘨 of that AI is threatening the very energy security we're trying to protect. This is why 60 industry leaders gathered at Greenhouse last week to launch the 'Better Data Centres' initiative. They know this isn't a software problem; it's a systems engineering challenge. This is Post 9 in my #ClimateCatalysts series. After mapping 850+ members of Climate Crew's Sydney chapter (CC.SYD), I’ve identified the 16 'Intelligence Architects' who are resolving this paradox. They are building the physical and digital infrastructure to ensure our intelligence doesn't cost the earth. 🏗️ The 𝗜𝗻𝗳𝗿𝗮𝘀𝘁𝗿𝘂𝗰𝘁𝘂𝗿𝗲 𝗔𝗿𝗰𝗵𝗶𝘁𝗲𝗰𝘁 (a.k.a. the 'Builder'): We start with the hardware. Antonia Collings (CEO, Enaxiom) isn't writing code; she's building the physical cooling infrastructure. Her firm's 'HydroCool' tech solves the massive heat and water problem of data centres, turning a liability into a water-positive asset. (Also read about David Soutar, Abdullah kazim & Martin Hamilton in the carousel). 📉 The 𝗠𝗶𝘁𝗶𝗴𝗮𝘁𝗶𝗼𝗻 𝗔𝗿𝗰𝗵𝗶𝘁𝗲𝗰𝘁 (a.k.a. the 'Optimiser'): Next, we need efficiency. Afonso Firmo (Co-CEO, NetNada) uses AI to automate carbon accounting, giving companies the visibility they need to squeeze emissions out of their supply chains and operations. (Also read about Simon R., James Crowley & Hayder Fernando Rocha in the carousel). 🛡️ The 𝗔𝗱𝗮𝗽𝘁𝗮𝘁𝗶𝗼𝗻 𝗔𝗿𝗰𝗵𝗶𝘁𝗲𝗰𝘁 (a.k.a. the 'Protector'): Then, we apply the intelligence. Alex Shapilsky (Cicada Innovations) connects the deep tech and satellite imagery streams that serve as the eyes of our climate AI models, providing the raw data we need to predict and adapt. (Also read about Stephen Catchpole, Yashada Kulkarni & Nikki Epema in the carousel). ⚖️The 𝗚𝗼𝘃𝗲𝗿𝗻𝗮𝗻𝗰𝗲 𝗔𝗿𝗰𝗵𝗶𝘁𝗲𝗰𝘁 (a.k.a. the 'Guardian'): Finally, we need trust. Michael Savanis (MLTG Corp) operationalises 'ethical AI', ensuring that as we deploy these powerful models, we have the rigorous oversight and governance frameworks to do so safely. (Also read about Chetan Dwivedi, Alexiane Richard-Bole & Meredith Caldwell in the carousel). The Green Digital Revolution promised at COP30 Brazil is possible. But it won't be delivered by market forces alone. It's being engineered by these 16 leaders. Who's an 'Intelligence Architect' in your network? Tag a catalyst building the smart grid, green IT or adaptation tech. #ClimateTech #DataCenters #GreenIT #AI #ClimateCrew #GreenerTogether Cover photo: Antonia Collings. Image © Robin Wyatt.