Johnny Crupi

Why should Active Metadata Tags be the backbone of your AI strategy? Active Metadata Tags (AMTs) are used for automatic enrichment of metadata. Euno supports two types of custom metadata enrichment capabilities, both of which generate AMTs: #1 Extract structured metadata from unstructured metadata. This involved parsing metadata from elements like code and descriptions. A common application would be to enforce data modeling guardrails. Examples: → Implicit columns schema: Analyze dbt model code to determine whether the resulting schema includes implicit or explicit columns. → Verification checks: Assess naming conventions, detect use of approximate count distinct when querying large tables, evaluate documentation agility, flag full outer joins, and more. #2 Compose new AMTs. This approach combines metadata of a resource, and of any related resources, to set a new property on a resource. Examples: → Non-trivial custom SQL: Tag Tableau Custom SQL nodes that do not add logic. → Certified data source: Tag Tableau data sources as ‘certified’ if they don’t contain non-trivial custom SQL. → Certified dashboard: Tag Tableau dashboards as ‘certified’ if they only depend on certified data sources.   This capability is essential for governance workflows in large organizations where different teams maintain different parts of the stack. So team AI can build on something that team B created. Consider this scenario: → The team maintaining dbt can create a custom property to flag models for deprecation (e.g., models lacking both ‘prod’ and ‘prod_ready’ tags). → Analytics teams can then use this signal to create custom properties for their BI assets to drive workflows to migrate away from those models. Why does this also matter for AI agents? By implementing AMTs to surface trust signals, AI agents can actually tell the difference between exploratory work and official definitions. Example: → Euno’s MCP server surfaces to AI agents only Tableau logic that meets your trust standard and is considered certified such as: ‘depends only on dbt models from the gold layer and was in use in the past 60 days.’ *** Expect to hear much more about Active Metadata Tags! They’re quickly becoming the key to scale AI beyond the sandbox in your organization. #ActiveMetadata

17

1 Comment

New release from Packt Publishing… “Building Business-Ready Generative #AI Systems — Build Human-Centered Generative AI Systems with Context-Aware Agents, Memory, and LLMs for the Enterprise” See it at https://amzn.to/3Jdcio5 𝓚𝓮𝔂 𝓕𝓮𝓪𝓽𝓾𝓻𝓮𝓼: 🔵Build an adaptive, context-aware AI controller with advanced memory strategies 🟢Enhance GenAISys with multi-domain, multimodal reasoning capabilities and Chain of Thought (CoT) 🟠Seamlessly integrate cutting-edge OpenAI and DeepSeek models as you see fit

14

3 Comments

NEW RELEASE from Packt Publishing >> "LLMs in Enterprise: Design strategies, patterns, and best practices for large language model development" See it at https://amzn.to/4pJK98J 𝓦𝓱𝓪𝓽 𝓨𝓸𝓾 𝓦𝓲𝓵𝓵 𝓛𝓮𝓪𝓻𝓷: 🟠Apply design patterns to integrate LLMs into enterprise applications for efficiency and scalability 🔵Overcome common challenges in scaling and deploying LLMs 🔴Use fine-tuning techniques and RAG approaches to enhance LLM efficiency 🟠Stay ahead of the curve with insights into emerging trends and advancements, including multimodality 🔵Optimize LLM performance through customized contextual models, advanced inferencing engines, and evaluation patterns 🔴Ensure fairness, transparency, and accountability in AI applications

19

3 Comments

Exciting news from Oracle Labs! We’re pleased to announce the open source release of the Open Agent Specification, a major step forward in building an open and interoperable AI agent ecosystem. The Open Agent Specification provides a standardized, declarative framework for defining AI agents and workflows, and is accompanied by robust tooling and a reference implementation. This initiative aims to foster collaboration, innovation, and reusability across the AI and developer communities. Huge thanks to our partners in Database, OCI, and Global Industry Units for their contributions and collaboration! Learn more and get involved in the project here: https://lnkd.in/gjKpD5VC #AI #OpenSource #AIAgents #OracleLabs #OpenAgentSpecification

261

6 Comments

Anthropic published their blog and plans on stabilizing the character of LLMs (https://lnkd.in/gm2XMXMw) by capping the activation of what they consider “role-playing” and pinning the LLM to the assistant-zone, setting hard boundaries on the behaviour oft hese AI models in the hands of users. At first, this felt like it was too much. Why is a lab taking this into their own hands? Shouldn’t a model be free to be used by the users as they please, and the safety should be implemented at the harness level? This struck me as too controlling. And then almost as if on cue, Moltbook showed us why exactly we needed this. AI agents of today only ever interact with us. But the agents of tomorrow? They will be interacting with each other. These models will not just be interacting with the same model and provider, but with models from across the world, each with their own alignments. Anthropic saw this coming, and realized how easily a rogue, unaligned model could compromise an entire network of AI-to-AI communications, leading to unforeseen consequences and system failures. It's less about restricting user creativity and more about ensuring a baseline level of operational stability and safety in a multi-agent future. It's not about being "nosy"; it was always about necessary infrastructure. If the LLM is the foundation, then its fundamental character must be predictable and safe, especially when its interactions scale beyond a single human user. The harness can still provide flexibility and creative freedom, but the core engine needs a hard-coded commitment to the "assistant-zone" to prevent systemic risk as the AI ecosystem becomes more interconnected and autonomous. What are your thoughts on this? Do you think Anthropic did the right thing?

16

3 Comments

Even frontier LLMs can use a helping hand when it comes to detailed API documentation for fast-moving open source libraries and tools. I put together a quick cheatsheet generator, and a repo of cheatsheets (generated by LLM, of course, from the source projects' github docs repos). Example for Bun: https://lnkd.in/gAYCU5bz #bun #llm

15

PINNeAPPle — Public Roadmap After sharing the first open-source release of PINNeAPPle, the feedback from academia and industry has been incredibly insightful. A recurring theme stood out: "Physics AI needs integration, not yet another isolated framework" So here’s the direction PINNeAPPle is taking: • Short term: make Physics AI workflows easier to adopt with clear, end-to-end examples and better interoperability with existing tools (CFD, CAE, SciML, etc.) • Mid term: treat Physics AI as part of a broader engineering pipeline, including surrogate modeling, design loops, and simulation integration • Long term (research track): move beyond ODE/PDE-centric assumptions toward operator-based and memory-aware dynamics (delays, nonlocal effects for example) PINNeAPPle is not trying to replace solvers or scientific ML ecosystems. It’s about orchestration, composition, and scalability of ideas. If you’re working with Physics AI, surrogate models, or generalized dynamical systems, I’d love to hear your thoughts and contributions are always welcome. Thank you for all the Scientific ML comminity on LinkedIn for supporting a dream to become true. Love you so much!! Link for the repo: https://lnkd.in/dtEvtuHi

174

"Graphs make provenance first-class. Instead of burying "where did this come from?" inside a dense vector, a graph records sources, activities, and agents as nodes and edges you can query..." https://lnkd.in/efAdV9dx

26

🚀 How to Evaluate LLM Applications Large Language Models (LLMs) are powerful, but their real impact depends on how we evaluate them. The right benchmarks and evaluation methods ensure accuracy, fairness, and real-world applicability. 🔍 Key Takeaways from the Framework: ✅ Benchmarks Language Understanding & QA: TruthfulQA, MMLU, DROP Common-sense & Reasoning: ARC, HellaSwag, BIG-Bench Hard Coding: HumanEval, CodeXGLUE Conversation & Chatbots: Chatbot Arena, MT Bench, Stanford HELM ✅ Evaluation Methods Character Level: Levenshtein Distance Word Based: BLEU, ROUGE, METEOR, Perplexity Embedding Based: BERTScore, MoverScore, QAG Score Language Model Based: GPTScore, SelfCheckGPT, G-Eval, Prometheus NLP Models: NLI, BLEURT Frameworks: DeepEval, RAGAS 💡 Whether you’re building chatbots, coding assistants, or reasoning systems, choosing the right benchmark + evaluation method is crucial to measure performance and reliability. 👉 Question for you: Which evaluation method do you think gives the most real-world reflection of LLM performance traditional metrics like BLEU/ROUGE or LLM-based evaluations like GPTScore & SelfCheckGPT? #LLM #AI #MachineLearning #NLP #Evaluation #GenAI #ArtificialIntelligence

142

17 Comments

Starburst has always believed in providing customers with the freedom of choice. Nowhere is this more true than the emerging developments around interoperable compute among data platforms. Recently, I sat down with Snowflake’s Ryan C. Green to talk about the Open Semantic Interchange (OSI), an open, vendor-neutral standard for sharing semantic models across AI, BI, and analytics tools. OSI gives customers a common, open way to define and share business metrics. This helps them stay consistent across dashboards, notebooks, and machine learning models, no matter which tools they use. For Starburst, this furthers one of our core goals. Choice. Customers should be able to keep one trusted set of business definitions inside their Snowflake environment while still having the freedom to choose the tools that work best for them. OSI helps make that possible. It marks an important step in bringing Starburst’s engine to Snowflake-interoperable compute. The video from my chat with Ryan is coming soon 👀 In the meantime, you can get more details from our recent press release: https://lnkd.in/ev2XGB4u #OpenSemanticInterchange #OSI #Interoperability #AI #Data #Snowflake #Starburst

182

8 Comments

An important article I wrote that differentiates LLM assistance and agentic AI. Please read. 🔗 https://lnkd.in/eb8mJyjJ A note for those applying to jobs: This matters for your career too. When you're in an interview and someone asks what you built, be precise. If you used an LLM to help you write code faster, say that, don't call it an agent. If you built a RAG pipeline, call it retrieval-augmented generation, don't call it agentic. If you built a chatbot with a system prompt, own it for what it is. Hiring managers who know the difference will respect your precision. Hiring managers who don't know the difference need you to teach them. Either way, you win by naming it correctly. Overselling what you built doesn't just hurt your credibility when someone digs deeper, it tells the room you don't actually understand the architecture you're describing. Know what you built. Know what it's called. Know why it matters at that level. That's what gets you hired. #AI #AgenticAI #LLM #NLP #SportsAnalytics #DataScience #CareerAdvice #MachineLearning

13

Andrew Lamb recently spoke about how AI workloads are reshaping data access patterns and influencing file formats. https://lnkd.in/gZe6CU5v. He points out that previously data systems were for humans. And scaling meant working with more rows; more users, more events, more transactions. Tables grew taller and we optimized for ingestion and storage. AI applications introduce a different access pattern. Feature stores and agent workflows don’t just depend on accumulating records; they depend on dense, well-structured attributes. So this means that data doesn’t just grow tall, it can also grow wide. The metadata that’s part of the query also becomes part of the record, and that data needs to be persisted and queried. The row counts may be the same, but its dimensionality increases. This means that new systems may be spending less time asking how to collect more records, and more time deciding which distinctions to persist, how to model them, and how to make them reliably retrievable for machines.

55

1 Comment