Real-Time AI Task Analysis

I recorded myself testing Shortcut, an AI Excel agent, in real-time—no preparation, no second takes. The demonstration reveals something profound about where analytical work is heading. Watch the AI agent process my request for a retirement planning spreadsheet: it immediately asks clarifying questions about organization structure, income streams, and inflation assumptions. Then you see the magic happen. Task by task, it builds multiple worksheet tabs, creates complex formulas for cash flow analysis, and generates visual dashboards with conditional formatting. The AI even creates dynamic key findings that change based on the data: "If cash flow analysis is greater than zero, then display this message, if not, display this warning." What struck me most was watching it troubleshoot merge cell conflicts in real-time while explaining its logic. The final product includes client information sheets, income stream analysis, expense breakdowns, investment calculators, and automated insights—all from conversational prompts. This isn't about replacing Excel skills. It's about making sophisticated financial modeling accessible to every advisor through natural language. The quality of our questions, not our technical abilities, now determines the analytical value we can deliver. Watch the entire video below.

Very promising! A new open-source platform for research on Human-AI teaming from Duke University uses real-time human physiological and behavioral data such as eye gaze, EEG, ECG, across a wide range of test situations to identify how to improve Human-AI collaboration. Selected insights from the CREW project paper (link in comments): 💡 Comprehensive Design for Collaborative Research. CREW is built to unify multidisciplinary research across machine learning, neuroscience, and cognitive science by offering extensible environments, multimodal feedback, and seamless human-agent interactions. Its modular design allows researchers to quickly modify tasks, integrate diverse AI algorithms, and analyze human behavior through physiological data. 🔄 Real-Time Interaction for Dynamic Decision-Making. CREW’s real-time feedback channels enables researchers to study dynamic decision-making and adaptive AI responses. Unlike traditional offline feedback systems, CREW supports continuous and instantaneous human guidance, crucial for simulating real-world scenarios, and making it easier to study how AI can best align with human intentions in rapidly changing environments. 📊 Benchmarking Across Tasks and Populations. CREW enables large-scale benchmarking of human-guided reinforcement learning (RL) algorithms. By conducting 50 parallel experiments across multiple tasks, researchers could test the scalability of state-of-the-art frameworks like Deep TAMER. This ability to scale the study of the interaction of human cognitive traits with AI training outcomes is a first. 🌟 Cognitive Traits Driving AI Success. The study highlighted key human cognitive traits—spatial reasoning, reflexes, and predictive abilities—as critical factors in enhancing AI performance. Overall, individuals with superior cognitive test scores consistently trained better-performing agents, underscoring the value of understanding and leveraging human strengths in collaborative AI development. Given that Humans + AI should be at the heart of progress, this platform promises to be a massive enabler of better Human-AI collaboration. In particular, it can help in designing human-AI interfaces that apply specific human cognitive capabilities to improve AI learning and adaptability. Love it!

MIT and Harvard Medical School researchers just unlocked interactive 3D medical image analysis with language! Medical imaging AI has long been limited to rigid, single-task models that require extensive fine-tuning for each clinical application. 𝗩𝗼𝘅𝗲𝗹𝗣𝗿𝗼𝗺𝗽𝘁 𝗶𝘀 𝘁𝗵𝗲 𝗳𝗶𝗿𝘀𝘁 𝘃𝗶𝘀𝗶𝗼𝗻-𝗹𝗮𝗻𝗴𝘂𝗮𝗴𝗲 𝗮𝗴𝗲𝗻𝘁 𝘁𝗵𝗮𝘁 𝗲𝗻𝗮𝗯𝗹𝗲𝘀 𝗿𝗲𝗮𝗹-𝘁𝗶𝗺𝗲, 𝗶𝗻𝘁𝗲𝗿𝗮𝗰𝘁𝗶𝘃𝗲 𝗮𝗻𝗮𝗹𝘆𝘀𝗶𝘀 𝗼𝗳 𝟯𝗗 𝗺𝗲𝗱𝗶𝗰𝗮𝗹 𝘀𝗰𝗮𝗻𝘀 𝘁𝗵𝗿𝗼𝘂𝗴𝗵 𝗻𝗮𝘁𝘂𝗿𝗮𝗹 𝗹𝗮𝗻𝗴𝘂𝗮𝗴𝗲 𝗰𝗼𝗺𝗺𝗮𝗻𝗱𝘀. 1. Unified multiple radiology tasks (segmentation, volume measurement, lesion characterization) within a single, multimodal AI model. 2. Executed complex imaging commands like “compute tumor growth across visits” or “segment infarcts in MCA territory” without additional training. 3. Matched or exceeded specialized models in anatomical segmentation and visual question answering for neuroimaging tasks. 4. Enabled real-time, interactive workflows, allowing clinicians to refine analysis through language inputs instead of manual annotations. Notably, I like that the design includes native-space convolutions that preserve the original acquisition resolution. This addresses a common limitation in medical imaging where resampling can degrade important details. Excited to see agents being introduced more directly into clinician workflows. Here's the awesome work: https://lnkd.in/ggQ4YGeX Congrats to Andrew Hoopes, Victor Ion Butoi, John Guttag, and Adrian V. Dalca! I post my takes on the latest developments in health AI – 𝗰𝗼𝗻𝗻𝗲𝗰𝘁 𝘄𝗶𝘁𝗵 𝗺𝗲 𝘁𝗼 𝘀𝘁𝗮𝘆 𝘂𝗽𝗱𝗮𝘁𝗲𝗱! Also, check out my health AI blog here: https://lnkd.in/g3nrQFxW

Agentic AI Doesn’t Just React – It Learns & Adapts in Real-Time! AI is advancing at a pace that’s hard to keep up with—what seemed like science fiction a few years ago is now becoming reality. We’re moving beyond pre-programmed automation and into the era of Agentic AI—systems that don’t just execute tasks but learn, adapt, and make decisions in real-time. This shift isn’t magic—it’s the result of cutting-edge engineering and real-time learning. If you love the tech behind it, here’s what makes it work: How Agentic AI Works Under the Hood: ⚡️ Event-Driven AI – Instant Reactions Without the Lag Traditional systems constantly check for updates—wasteful and slow. Agentic AI flips the script: ✅ Uses event-driven architecture to react immediately to changes. ✅ Leverages message queues & event streams for real-time responsiveness. ✅ Processes only what matters—no wasted cycles, no delays. 🧠 Reinforcement Learning – Learning on the Fly Most RL models are trained in labs, but Agentic AI learns while operating: ✅ Continuously refines decisions based on live feedback. ✅ Algorithms like SARSA, Q-Learning, and Policy Gradients adapt in real-time. ✅ Every action shapes the next move—no rigid playbook. 🧩 Complex Event Processing (CEP) – Finding Meaning in the Chaos AI isn’t just reacting to single events—it’s detecting patterns: ✅ Analyzes event sequences in real time. ✅ Recognizes key trends in massive data streams. ✅ Crucial for fraud detection, predictive analytics, and automated risk assessment. 🕸️ Knowledge Graphs – AI That Understands Context AI needs more than just data—it needs connections: ✅ Links information like a human brain—context matters. ✅ Powers better reasoning, recommendations, and predictions. ✅ Used in search engines, personal assistants, and enterprise analytics. This isn’t just AI getting faster—it’s AI becoming truly intelligent, adapting on the fly to changing environments. 💡 Where do you see Agentic AI having the biggest impact? Cybersecurity? AI Ops? Finance? Supply Chain? Drop your thoughts below—let’s geek out over the real-world applications! 👇 #AgenticAI #RealTimeAI #TechDeepDive #ReinforcementLearning #EventDrivenArchitecture #ComplexEventProcessing #KnowledgeGraphs #ContextualAI #AdaptiveIntelligence

🚀 Big AI updates from Current Bengaluru today! Apache Flink is getting some major upgrades in Confluent Cloud that make real-time AI way easier: 🔹 Run AI models directly in Flink –Bring your model and start making predictions in real time. No need to host externally. 🔹 Search across vector databases – Easily pull in data from places like Pinecone, Weaviate, and Elasticsearch as well as your real-time streams. 🔹 Built-in AI functions – Flink now has built-in tools for forecasting and anomaly detection, so you can spot trends and outliers as the data flows in. Additionally, Tableflow for Iceberg is now GA, and Delta Lake is in early access, making it easier to connect real-time data streams to your AI workflows without managing ETL pipelines. 💡 Why this matters – AI needs fresh, fast data. These updates make it way easier to run models, retrieve data, and build real-time AI apps without stitching together a dozen different tools. Exciting times for AI + streaming! #Current2025 #Confluent #ApacheFlink #AI #RealTimeData #StreamingAI