The Hedgineer Podcast

Anthropic and Google both had massive dev days recently. And they couldn't be more different. In this episode, Jhanvi and Michael break down what each announcement signals about the frontier model race and where it's headed. Anthropic is doubling down on enterprise agents, memory stores, and "dreaming," while Google is going wide with consumer AI, a multimodal Omni model, and Spark embedded across its entire product suite.They also get into a question that comes up with clients and candidates alike: how worried should companies actually be about vendor lock-in? Plus: what happens when you run the same agentic harness with different frontier models, why tokens per second is becoming a more important metric, and why you shouldn't switch back and forth between Cowork and ChatGPT. Key TakeawaysDecouple Architecture via Open Standards: To prevent long-term vendor lock-in, firms should deploy custom skill libraries and organizational knowledge layers as open, text-based formats stored in client-owned GitHub repositories rather than within proprietary model environments.Implement OpenTelemetry Early: The highest hurdle to switching model providers is the loss of historical session data; setting up an independent OpenTelemetry system up front ensures your firm owns its telemetry and interaction data, permitting smooth cross-provider migration.Isolate Compute with Managed Sandboxes: Utilizing self-hosted agent tool containers allows institutional firms to keep localized data execution and tools within their secure cloud environments while securely executing the core inference loop via external APIs.Focus on Immediate ROI Over Early Optimization: Many firms stall their AI adoption by over-engineering cross-cloud or cross-vendor compatibility too early. Successful deployment requires mastering one ecosystem to capture immediate time-to-value before optimizing for compute spend arbitrage.About HedgineerHedgineer is building the AI platform for institutional investing — deploying agents, skills, and data connectors directly inside hedge funds and asset managers to transform investment and operational workflows. The Hedgineer Podcast follows CEO Michael Watson and COO Jhanvi Virani as they navigate the frontier of AI adoption in finance, sharing unfiltered perspectives from the teams, guests, and problems they work with every day. Subscribe for weekly analysis on AI infrastructure and institutional finance.Watch the full episode on Spotify or YouTube at youtube.com/@hedgineer.Connect with us on LinkedIn at linkedin.com/company/hedgineer-io or reach out at podcast@hedgineer.io.Hedgineer.io

The transition from AI as a chatbot to AI as an autonomous agent requires more than just better models; it requires agents capable of regulating their own state and context at scale.In this episode of The Hedgineer Podcast, co-hosts Michael Watson and Jhanvi Virani sit down with Mitch Troyanovsky, co-founder of Basis, an agent platform specifically designed for the accounting industry. The conversation moves beyond the hype of generative AI to address the engineering realities of building "agent-native" enterprises. Mitch explains why the next frontier of applied machine learning involves closing the loop on self-improving agents—systems that can optimize their own trajectories, contexts, and tools without constant human intervention.We explore the "single pane of glass" debate: whether specialized platforms like Basis will remain the system of record or if frontier model interfaces will eventually consolidate all enterprise workflows. The discussion delves into the technical nuances of Recursive Language Models (RLMs) and the "Better Intelligence" approach, where models are leveraged to programmatically curate their own context windows to maintain performance over long-duration tasks.The episode also tackles the cultural shift required for AI adoption. From implementing "Do You Stand By This" (DYSB) protocols to ensure accountability, to the "lexical taxonomy" required to write documentation specifically for LLM consumption rather than human readers, we provide a blueprint for firms looking to move from experimental AI to production-grade agentic systems.Key Takeaways:Closing the Applied ML Loop: Why the next generation of agents will focus on self-regulation and autonomous state management to handle production workloads.The "Database-ification" of SaaS: How AI agents interacting via API threaten the value proposition of traditional software UIs, potentially reducing many SaaS tools to mere structured data stores.Recursive Language Models (RLMs): A technical look at using model intelligence to dynamically curate context at every forward pass, moving beyond simple "append-only" context windows.Writing for Machines: Why traditional human writing styles are inefficient for LLMs and how "information density" is becoming a critical engineering discipline.About the Guest:Mitchell Troyanovsky is the co-founder of Basis, a New York-based platform building AI agents for the accounting industry. He is a leading voice on the future of agentic systems at scale and the implementation of Recursive Language Models in production.About HedgineerHedgineer is building the AI platform for institutional investing — deploying agents, skills, and data connectors directly inside hedge funds and asset managers to transform investment and operational workflows. The Hedgineer Podcast follows CEO Michael Watson and COO Jhanvi Virani as they navigate the frontier of AI adoption in finance, sharing unfiltered perspectives from the teams, guests, and problems they work with every day. Subscribe for weekly analysis on AI infrastructure and institutional finance.Watch the full episode on Spotify or YouTube at youtube.com/@hedgineer.Connect with us on LinkedIn at linkedin.com/company/hedgineer-io or reach out at podcast@hedgineer.io.Hedgineer.io

Anthropic just announced an enterprise services venture backed by Goldman, Hellman & Friedman, and Blackstone. OpenAI is raising $4B for something similar. So why are frontier model providers suddenly trying to become consultants?In Season 3 Episode 3 of The Hedgineer Podcast, Michael and Jhanvi break down what's driving the move: why handing a company a Claude license rarely translates into real automation, and why building domain-specific is critical to successful deployments. The real unlock behind all of this is agent harnesses, which have expanded what AI can do far beyond a chat interface. They dig into how providers are approaching harnesses differently and why state management and organizational memory are the differentiators that not enough people are talking about.Plus: GPT 4.5 vs. 5.5 cost dynamics, why understanding model caching could save your company thousands of dollars, and whether Apple is sitting on the consumer unlock that could shift public skepticism on AI.  About HedgineerHedgineer is building the AI platform for institutional investing — deploying agents, skills, and data connectors directly inside hedge funds and asset managers to transform investment and operational workflows. The Hedgineer Podcast follows CEO Michael Watson and COO Jhanvi Virani as they navigate the frontier of AI adoption in finance, sharing unfiltered perspectives from the teams, guests, and problems they work with every day. Subscribe for weekly analysis on AI infrastructure and institutional finance.Watch the full episode on Spotify or YouTube at youtube.com/@hedgineer.Connect with us on LinkedIn at linkedin.com/company/hedgineer-io or reach out at podcast@hedgineer.io.Hedgineer.io

Neel Somani is a quant engineer turned content creator covering power markets, AI infrastructure, and crypto. In this episode of The Hedgineer Podcast, we dig into how the AI boom is reshaping energy markets, how rising compute costs are forcing companies to measure AI ROI, and whether open source models are changing the build vs. buy decision.About the GuestNeel Somani is a technologist and researcher focused on the intersection of machine learning, commodities, and formal methods. Formerly a quantitative researcher in the power and commodities space, he has recently gained prominence for his work in mechanistic interpretability and his contributions to solving Erdős problems using large language models.Follow Neel on X at @neelsomani, TikTok at @neelsalami, and Instagram at @neelsalamiAbout HedgineerHedgineer is building the AI platform for institutional investing — deploying agents, skills, and data connectors directly inside hedge funds and asset managers to transform investment and operational workflows. The Hedgineer Podcast follows CEO Michael Watson and COO Jhanvi Virani as they navigate the frontier of AI adoption in finance, sharing unfiltered perspectives from the teams, guests, and problems they work with every day. Subscribe for weekly analysis on AI infrastructure and institutional finance.Watch the full episode on Spotify or YouTube at youtube.com/@hedgineer.Listen wherever you get your podcasts. Connect with us on LinkedIn at linkedin.com/company/hedgineer-io or reach out at podcast@hedgineer.io.Hedgineer.io

SaaS companies are pivoting: less investment in the dashboard, more in the API. Salesforce's headless MCP suite, Ramp's CLI, Linear's AI connectors — the pattern is the same. Products are being rebuilt for agents, not humans.In this episode, Jhanvi and Michael dig into what's driving the shift and what it means for funds evaluating their stack. They also get into the architecture question that's coming up with every data vendor they talk to: how do you actually design a good MCP server? They break down the difference between open-source and closed-source skills, where intelligence belongs in the stack, and why the firms that win this next wave won't look like tech companies in the traditional sense.About Our Hosts: Michael Watson is the co-host of The Hedgineer Podcast, CEO of Hedgineer, and a technologist focused on deploying AI within the institutional investment space. Jhanvi Virani is the COO of Hedgineer and co-host, specializing in scaling operations and technology platforms for hedge funds.Subscribe for weekly analysis and trends within AI, Finance, and TechnologyAvailable wherever you get your podcasts!Video available on YouTube and Spotifyyoutube.com/@hedgineerQuestions? Topics you’d like for us to discuss? Email us at podcast@hedgineer.ioHedgineer.io#AIEngineering #InstitutionalInvesting #AssetManagement

Season 2 Finale: Open-Sourcing the Investor Library with Daloopa CEO Thomas LiThe Season 2 finale of The Hedgineer Podcast features the return of Thomas Li, Co-founder and CEO of Daloopa, for his third appearance on the show. This episode marks a significant milestone as we transition into a new chapter for the podcast.Special Announcement: Season 3 and New FormatBefore diving into the discussion, host Michael Watson announces a major shift for the upcoming season. Starting next week, The Hedgineer Podcast will move to a weekly release schedule to provide more frequent insights into the rapidly evolving world of technology, data, and AI. Joining the show as a permanent co-host is Jhanvi Virani, Hedgineer’s COO, who will help anchor our weekly updates and industry analysis.Episode OverviewIn this finale, Michael and Thomas explore the decision to open-source Daloopa’s "investor library" of skills and agents—a move that challenges the historically closed-off nature of the financial data ecosystem. They discuss the philosophy behind treating AI agents as "text files" that can be refined by a community of sophisticated investors, effectively turning what was once proprietary alpha into the new industry beta.The conversation delves into the technical obsession required to serve institutional clients, particularly regarding latency. Thomas explains why Daloopa prioritizes parsing unstructured press wires over waiting for structured SEC filings: in high-stakes markets, saving a few minutes of "server lag" is the difference between a successful trade and a missed opportunity.We also cover the strategic landscape of building on frontier models. Thomas shares his experience partnering with Anthropic to build their Excel plugin and discusses whether evolving LLMs are a "wind behind the sail" or an existential risk for specialized fintech companies.Key TakeawaysThe Open-Source Investor Library: Why Daloopa is providing its corpus of fundamental investing skills to the community and how 100+ hedge funds are already contributing back.Latency as a Moat: The engineering challenge of bypassing SEC server lag by parsing raw press wires to deliver verified data in seconds.Agents vs. Chat: Why the future of finance lies in agentic workflows (like "Scout" and "Claude Code") rather than simple prompt-and-response interfaces.Internal AI Adoption: How Daloopa uses AI internally—from analyzing customer feedback to helping sales teams prep for meetings—without hiring "AI Engineers," but by making everyone an AI user.Timestamps00:00 – Season 3 Announcement: Weekly episodes and new co-host Jhanvi Virani04:15 – The decision to open-source the investor library of skills11:30 – Why an "Agent" is just a text file and the power of community iteration18:45 – Monetizing the "Engine": Ferrari’s philosophy applied to financial data26:20 – The transition from Alpha to Beta in AI-driven research35:10 – Partnering with Anthropic and the future of Excel-based agents42:00 – Obsessing over seconds: Parsing press wires vs. SEC filingsAbout the Guest: Thomas Li is the Co-founder and CEO of Daloopa, a provider of high-fidelity data for company financials and KPIs.About the Host: Michael Watson is the founder of Hedgineer, building data and AI platforms for institutional asset managers.Subscribe for weekly analysis starting next season.youtube.com/@hedgineerHedgineer.io Hosted on Acast. See acast.com/privacy for more information.

AI Orchestration: From Custom Skills to Autonomous Hedge Fund OperationsMost asset managers treat AI as just a chatbot, failing to bridge the gap between an LLM's general reasoning and the specific, high-stakes workflows of their actual day-to-day.In this episode of The Hedgineer Podcast, Michael Watson sits down with Jhanvi Virani, COO of Hedgineer, to discuss the practical mechanics of deploying AI within hedge funds and asset managers. Jhanvi details her experience shadowing a CIO to translate their cognitive investment process into a digital skill—a structured framework that allows Claude to synthesize fragmented data from order management systems, SharePoint research, and consensus estimates into polished, institutional-grade outputs in a one-day turnaround. We move beyond simple prompting to explore the "Agentic Loop," discussing how local schedulers and the Claude Agent SDK are enabling systems to run autonomously 24/7.The conversation also covers the technical nuances of the Claude Ecosystem, comparing developer-centric Claude Code with user-friendly Claude Cowork. Jhanvi shares her on-the-ground findings regarding the limitations of local vs. remote execution and why building a secure, server-side environment is the ultimate bottleneck for scaling AI intelligence across a firm.Key TakeawaysThe Skill-Based Unlock: How shadowing investment professionals allows engineers to map complex and manual research workflows into automated skills that produce consistent, high-polish one-pagers.Claude Code vs. Cowork: A breakdown of why developers prefer terminal-based workflows for multitasking, while non-technical users leverage Cowork for scheduled tasks and visual connector management.Building "AI Native" Infrastructure: The 0-to-1 process of auditing fund workflows, building custom MCP (Model Context Protocol) connectors for legacy data vendors, and establishing organizational agent management frameworks.The Self-Healing Feedback Loop: Using usage analytics and "meta-agents" to observe behavior, evaluate performance, and automatically suggest system improvements, creating a self-sufficient AI framework.Timestamps00:00 - Introduction and the role of skills in unlocking automation 04:15 - Evolving daily workflows with Claude Code and Cowork 08:42 - UI vs. Terminal: Optimizing screen real estate and parallel sessions 14:30 - Testing the bounds: Automating expense reports and attachment limitations 17:45 - Windows vs. Linux runtimes and the "Local Scheduler" in Cowork 22:10 - The Agentic Loop: From Claude Agent SDK to OpenClaw deployments 29:40 - CIO Shadowing: Translating a day of research into a custom AI skill 36:50 - The future of autonomous analytics and observation agents 43:15 - Deliverables for becoming AI Native: Audits, MCP servers, and data warehouses 51:00 - AI Personification: Authenticity in communication and the risk of "AI slop." 64:20 - Team expansion in Bangalore and the tech-focus of South IndiaGuest Bio: Jhanvi Virani is the COO of Hedgineer, where she oversees the deployment of AI infrastructure and automation for institutional asset managers. She specializes in bridging the gap between technical LLM capabilities and high-level investment workflows.Host Bio: Michael Watson is the founder of Hedgineer and host of the podcast, focusing on the intersection of data science, AI, and hedge fund technology.Links & SubscribeSubscribe for weekly analysis on AI and Asset Management.youtube.com/@hedgineerHedgineer.io Hosted on Acast. See acast.com/privacy for more information.

Data Liquidity and the Agentic Marketplace: Moving Beyond Bulk SaaS ContractsThe traditional model of purchasing financial data is structurally misaligned with the requirements of modern AI development. While hedge funds have historically navigated opaque pricing and rigid, six-figure bulk contracts, the rise of Frontier Labs and agentic workflows demands a shift toward data liquidity and consumption-based procurement.In this episode, Michael Watson is joined by Dan Entrup (Founder of Agnowledge) and Freeman Lewin (Founder of BrickRoad) to bridge the gap between institutional data strategy and the emerging ML data marketplace. The conversation explores why the "data-centric AI" movement is forcing a reimagining of the supply pipeline, moving away from "buying data to cover your tracks" toward a world where agents autonomously discover, score, and purchase granular datasets for real-time inference.We analyze the friction within current procurement cycles—often involving over 80 emails for a single deal—and contrast this with the "vibe coding" revolution and the Anthropic "skills" ecosystem. By treating expertise as a distributable text-based asset, firms can bypass traditional SaaS moats and build opinionated, autonomous systems that scale far beyond the capacity of human analyst teams.Key TakeawaysThe Shift to Consumption-Based Data: Moving away from bulk annual minimums to consumption models allows firms to trial, backtest, and identify ROI within minutes rather than months, effectively creating a "spot market" for information.Agents as the New Data Buyers: Unlike humans, agents require high-frequency access to small data subsets for accuracy. This creates a need for automated marketplaces where data "sells itself" to machines to maintain trust in agentic outputs.Skills as Monetizable Data: Anthropic’s Model Context Protocol (MCP) and "skills" framework represent a shift where organizational knowledge—such as specific financial modeling styles—becomes a portable, executable asset that can be distributed via marketplaces.The Decline of Legacy SaaS Moats: Software companies that rely on workflow inefficiencies or "proprietary" data that is actually generally available are facing significant valuation pressure as "vibe coding" allows firms to build custom, internal alternatives like CRMs overnight.Timestamps00:00 - Introduction to Dan Entrup and Freeman Lewin. 08:45 - The bifurcation of the data industry: Hedge funds vs. Frontier AI Labs. 15:20 - Friction in data procurement: Why it takes 80+ emails to close a deal. 23:10 - Data-centric AI: Why better data now moves the needle more than algorithmic tweaks. 32:45 - Token optimization vs. Weight fine-tuning for enterprise value. 42:15 - Building the Agentic Marketplace: Why data doesn't sell itself to humans. 54:30 - The "SaaS is Dead" debate and the transition to consumption-based revenue. 79:00 - Anthropic Skills: Structuring and distributing expert knowledge at runtime. 98:30 - Vibe coding and the future of the autonomous, multi-billion dollar "small" firm.About the GuestsDan Entrup is the Founder of Agnowledge and a veteran data strategist who previously served as Head of Data Strategy for a Fortune 500 company. He specializes in expert network curation and helping firms navigate the complexities of data commerce.Freeman Lewin is the Founder of BrickRoad, a frontier data lab building an agentic marketplace for data procurement and liquidity. His work focuses on establishing data liquidity through on-chain transaction histories and utility scoring mechanisms.Michael Watson is the host of The Hedgineer Podcast and founder of Hedgineer, a firm building data and AI platforms for institutional asset managers.Links & ResourcesSubscribe for weekly analysis on AI and data infrastructure in finance.Learn more about Hedgineer: Hedgineer.ioFollow on LinkedIn: https://www.linkedin.com/company/90976838 Hosted on Acast. See acast.com/privacy for more information.

Welcome back to The Hedgineer Podcast, where host Michael Watson dives into the world of AI, data, and technology within asset management, hedge funds, and financial services. In this episode, Michael sits down with Jonathan Regenstein, who leads AI within Financial Services at Snowflake.This conversation explores the critical role of data and platform strategy in the successful enterprise deployment of AI, moving beyond purely technical wins to focus on commercial outcomes. Jonathan and Michael dissect the evolution of Snowflake from a powerful SQL engine to a unified platform for AI, and debate where the intelligence layer should reside for maximum effectiveness.❄️ In This Episode, We Discuss:The Power of Data Sharing: How Snowflake's seamless data sharing and Marketplace revolutionized the consumption of alternative data on the buy side, drastically simplifying security and licensing workflows.The AI Layer Debate: A deep dive into whether the AI runtime should live natively within the data platform (Snowflake) using tools like Cortex and Intelligence, or be orchestrated externally by hyperscalers or model providers.Beyond the Technical Win: The shift from technology-driven AI Proofs-of-Concept (POCs) to projects scoped by commercial outcomes—revenue generation or cost reduction.Evaluations are the Product: The crucial importance of robust evaluation frameworks (like those provided by TruEra/TruLens) for agentic workflows to avoid "chaos at scale," and how to involve business leaders—not just engineers—in defining what success looks like.The Semantic Layer's Role: The concept of the semantic model as a first-class citizen in Snowflake, acting as the translator between business language and data, driving accuracy in Text-to-SQL (Cortex Analyst), and building trust with non-technical users.The Future of BI: How AI is driving the complete rethinking of the Business Intelligence (BI) stack, moving beyond static dashboards to dynamic, generative BI that surfaces insights and visualizations on demand.👤 About Our GuestJonathan Regenstein is a key leader in the AI for Financial Services division at Snowflake, driving the platform's strategy in machine learning and artificial intelligence for banks, asset managers, and insurance companies.Follow The Hedgineer Podcast:YouTube: (https://www.youtube.com/@hedgineer)LinkedIn: (https://www.linkedin.com/company/90976838)Twitter: (https://x.com/hedgineering)Instagram: (https://www.instagram.com/hedgineer/)Don't forget to like, subscribe, and hit the notification bell to stay updated on our latest episodes!Hedgineer.io Hosted on Acast. See acast.com/privacy for more information.

Welcome back to The Hedgineer Podcast. In this episode, host Michael Watson sits down with crowd-favorite returning guest, Lucas Rooney.Lucas pulls back the curtain on the "0 to 1" journey of building a new fund, from diligencing the initial idea and recruiting top-tier talent to making the critical "build vs. buy" decisions for a foundational technology stack.But how does launching a fund today differ from just a few years ago? One answer is AI.Michael and Lucas dive deep into how the proliferation of AI reframes the entire approach to building systems, forcing a new focus on taxonomy, data labeling, and codifying the "thought process" of an investment from day one.The conversation shifts to one of the most critical questions facing the industry: How do incentive structures change when an individual's knowledge and intellectual property (IP) can be instantly captured and instilled into the organization's systems?. They explore how firms must re-evaluate compensation and talent, as value shifts from executing perfunctory tasks to the high-level synthesis and compounding of IP.🎧 In This Episode, We Discuss:The "0 to 1" process of launching a new fund.Key strategies for recruiting passionate technologists and investors.The foundational tech stack: Designing the data/ETL, analytical, trading, and risk layers from scratch.How AI forces better data hygiene and process documentation.The "IP Capture" Problem: Rethinking talent compensation when AI can learn and retain an employee's knowledge permanently.Why hiring is shifting from "task execution" to "IP synthesis" and "compounding".The "Negative Space": Why capturing the bad ideas and hypotheses you didn't run is the next frontier for evaluating skill.Hosted by Michael Watson, The Hedgineer Podcast dives into AI technology and data in the hedge fund, asset management, and prop trading space.Follow The Hedgineer Podcast:YouTube: (https://www.youtube.com/@hedgineer)LinkedIn: (https://www.linkedin.com/company/90976838)Twitter: (https://x.com/hedgineering)Instagram: (https://www.instagram.com/hedgineer/)Don't forget to like, subscribe, and hit the notification bell to stay updated on our latest episodes!Hedgineer.io Hosted on Acast. See acast.com/privacy for more information.

Beyond the AI Hype with Jason StrimpelIn this episode of The Hedgineer Podcast, host Michael Watson sits down with Jason Strimpel, founder of PyQuant News, long-time Pythonista, and AI enthusiast.They dive deep into the practical and philosophical implications of artificial intelligence in both asset management and daily life. They break down how the agentic loop works with the Anthropic Agent SDK, the components of good evaluation frameworks, and even how to talk to your kids about AI Key topics covered in this episode:Drugs, Sex, and AI: Jason shares his thoughts for new parents: the three things you now need to talk to your kids about are drugs, sex, and AI. Michael and Jason then discuss the difficulty of explaining the difference between humans and AI-powered avatars or toys to children.The "Agentic Loop": The discussion breaks down the simplicity and power of the agentic loop, identifying it as the "core substrate" of modern agentic frameworks. This framework allows a language model to loop, use tools, and determine when to exit to solve complex problems."Evals are the Product": Michael and Jason iterate on the concept that a robust set of evaluations is the real product. If you can use evals to demonstrate that an agent has harnessed intelligence to solve a specific problem space, you "own that problem".AI vs. Python's Rise: They draw parallels between the current AI boom and the rise of Python in the early 2010s. Both technologies were initially met with skepticism for being "black box" interpreted systems, yet they unlocked massive productivity boosts.Capital Allocation and Moats: The conversation tackles the modern challenge of allocating capital and defending a "software moat" when new AI tools and infrastructure are being commoditized by hyperscalers at an incredible speed.The PyQuant News Story: Jason shares the origin story of his popular PyQuant newsletter, which started as a personal WordPress site for bookmarking research papers and grew into a major resource for the quantitative finance community.Hosted by Michael Watson, The Hedgineer Podcast dives into AI technology and data in the hedge fund, asset management, and prop trading space.Follow The Hedgineer Podcast:YouTube: (https://www.youtube.com/@hedgineer)LinkedIn: (https://www.linkedin.com/company/90976838)Twitter: (https://x.com/hedgineering)Instagram: (https://www.instagram.com/hedgineer/)Don't forget to like, subscribe, and hit the notification bell to stay updated on our latest episodes!Hedgineer.io Hosted on Acast. See acast.com/privacy for more information.

Kuzu, Knowledge Graphs, and the AI Revolution with Prashanth RaoIn this episode of the Hedgineer Podcast, host Michael Watson is joined by Prashanth Rao, AI Engineer at Kuzu, for a deep dive into the world of embedded graph databases and their pivotal role in the age of AI. Building on the previous week's discussion of the columnar database DuckDB, this conversation explores Kuzu, a parallel concept focused on creating high-performance, embedded graph databases.Michael and Prashanth explore why Kuzu's unique architecture—an embedded, columnar, and strictly-typed system—is delivering incredible speed and scalability for complex analytical queries. They discuss the resurgence of interest in knowledge graphs, driven by the need to impose structure on data for modern AI and LLM workflows. Prashanth explains how LLMs are revolutionizing both the upstream construction of graphs from unstructured data and the downstream querying of these graphs by translating natural language into the Cypher query language.Tune in to learn about:What Kuzu Is: An in-process, embedded graph database designed from the ground up for query speed and scalability, blending the benefits of columnar processing with the property graph data model.AI and Graph Synergy: How large language models (LLMs) assist in both building knowledge graphs through structured output extraction and accessing them via natural language to Cypher translation.Modern Data Stack Integration: The role of Kuzu as a powerful secondary semantic layer that interoperates seamlessly with primary data stores in data lakes (like Parquet files on S3), DuckDB, and Postgres.Programming with LLMs using DSPy: A detailed look into using DSPy to create structured, modular, and optimizable prompts for more reliable LLM applications, bridging the gap between deterministic code and fully agentic workflows.The Enterprise Knowledge Graph: A discussion on how a knowledge graph can become the single source of truth for understanding complex organizational workflows, data lineage, and interdependencies across an entire enterprise.The Future of Kuzu: A preview of what's next for the Kuzu project, including new graph algorithm capabilities and enhanced concurrency for reads and writes.Whether you're a data engineer, AI practitioner, or a leader in the asset management space, this episode provides a masterclass on leveraging modern database technology to build powerful, scalable, and intelligent applications.Hedgineer.ioFollow The Hedgineer Podcast:YouTube: (https://www.youtube.com/@hedgineer)LinkedIn: (https://www.linkedin.com/company/90976838)Twitter: (https://x.com/hedgineering)Instagram: (https://www.instagram.com/hedgineer/) Hosted on Acast. See acast.com/privacy for more information.