AI Dev 26 X SF | Aman Singla & Aseem Chandra: MarcoPolo, A Workspace for AI to Work with Your...
The video introduces Marco Polo, a middleware platform that provides a dedicated workspace where agentic AI models—such as Claude, ChatGPT, or custom agents—can safely access and manipulate enterprise data across dozens of systems. By running in a secure Kubernetes container, Marco Polo bridges LLMs with raw storage, databases, CRMs, ERPs, and support tools while enforcing architectural boundaries and credential scoping. A core insight is the unified command‑line interface that abstracts over 50+ data sources, offering verbs like list, query, and upload. This reduces the prompt length and token consumption needed for the LLM to understand each source’s API. The platform also pre‑loads schema and connection metadata, solving the “cold‑start” problem and allowing the AI to generate accurate SQL or JQL queries from day one. Persistent workspaces retain query history, schema, and audit logs, enabling the model to reuse prior work and progressively improve its context. A concrete demo shows an ops user asking for churned customers and their support tickets. Marco Polo supplies the correct Salesforce object, joins it with Jira tickets via a temporary DuckDB instance, and even builds a rerunnable revenue‑by‑region dashboard by stitching together Salesforce and census data. The LLM never sees raw credentials; instead, it invokes privileged CLI calls that enforce scoped access. The implications are significant: non‑technical staff can leverage powerful LLM agents without writing code, enterprises gain a searchable, auditable knowledge base, and security teams retain control over data exposure. By turning ad‑hoc data pulls into repeatable, token‑efficient workflows, Marco Polo aims to democratize AI‑driven analytics at scale.
![Relational Foundation Models for Enterprise Data [Jure Leskovec] - 768](/cdn-cgi/image/width=1200,quality=75,format=auto,fit=cover/https://i.ytimg.com/vi/khSSuUyvqno/maxresdefault.jpg)
Relational Foundation Models for Enterprise Data [Jure Leskovec] - 768
The podcast introduces a new relational foundation model that can reason over structured relational data across any enterprise database without additional training. By treating tables and foreign‑key links as a graph, the model applies graph neural networks, eliminating manual feature engineering...
AI Dev 26 X SF | Adit Abraham: Better Agents with Better Data
In this talk Adit Abraham of Reductto outlines the company’s mission to turn raw documents into reliable inputs for next‑generation AI agents. He explains that while large language models have matured, their real‑world utility still hinges on the quality of...
AI Is Building Our Data Pipelines Now (Estuary Live Demo)
The demo introduced Estuary’s “right‑time” data platform, a unified solution that processes both batch and streaming workloads without the traditional split between Kafka‑based streaming and separate batch pipelines. By abstracting the data movement layer, Estuary promises to deliver data at...
![Power BI Full Course 2026 [FREE] | Power BI Tutorial For Beginners | Power BI Training | Simplilearn](/cdn-cgi/image/width=1200,quality=75,format=auto,fit=cover/https://i.ytimg.com/vi/yfkTPw_jIcU/maxresdefault.jpg)
Power BI Full Course 2026 [FREE] | Power BI Tutorial For Beginners | Power BI Training | Simplilearn
This video is a comprehensive, beginner-focused full course on Microsoft Power BI that walks viewers through the end-to-end workflow: installing Power BI Desktop, connecting to 150+ data sources, cleaning and transforming data in Power Query Editor, modeling relationships, building visuals...
What You Need to Know About Palantir | FT #shorts
Palantir is a data-software company that builds platforms to integrate large, disparate datasets for operational decision-making, serving clients from automakers to militaries. Its primary customer is the US government, with notable deployments in Pentagon battlefield systems, ICE immigration operations, and...
Generative AI in the Real World: Chang She on Data Infrastructure for AI
The podcast spotlights the growing gap between legacy analytics stacks and the data demands of generative AI. Chang Shi, CEO of LanceDB, explains how his experience building embeddings at Tubi TV revealed that tools such as Pandas, Spark, and Parquet...
Conversational Analytics in Google Data Studio – Chat With Your Data
Google Data Studio (now Looker Studio) has introduced Conversational Analytics, a Gemini‑powered feature that lets users ask natural‑language questions of their data. By creating a BigQuery agent, analysts can connect Google Analytics 4 datasets and receive instant, SQL‑free insights directly...
Data Engineering Roadmap 2026: Skills, Timeline, Salary
The video outlines a five‑year data‑engineering roadmap designed to engineer three distinct compensation jumps. It argues that a deliberate, long‑term plan—rather than ad‑hoc moves—can transform a $100k salary into roughly $380k total compensation. Key tactics include mapping future interview topics, dedicating...
Generative AI in the Real World: Shreya Shankar on AI for Corporate Data Processing
In this podcast, UC Berkeley PhD candidate Shreya Shankar explains how generative AI is reshaping enterprise data processing. She highlights the long‑standing challenge of extracting structure from unstructured assets—PDFs, transcripts, logs—and shows how large language models now make that feasible....
Teradata Unveils New Product, Exec Says Its ‘Ready to Move Beyond AI Pilots’
Teradata announced its Autonomous Knowledge Platform, a unified AI‑analytics system that fuses enterprise data and decision‑making into a single layer across cloud, on‑premise and hybrid environments. The platform leverages Teradata’s long‑standing scale and performance, adds industry‑specific context for sectors like finance,...
Cut Data Engineering and the Business Starts Bleeding.
The video argues that data engineering is the lifeblood of modern enterprises and that eliminating the function will “bleed” revenue. It stresses that raw data must be cleaned, transformed, and operationalized into pipelines that feed marketing, finance, executive decision‑making, and...
Big Data, Bigger Security Challenges | Dr. Roger Schell
The CIO Talk Radio interview with Dr. Roger Schell focused on how the rapid expansion of big‑data initiatives is creating new security vulnerabilities. Schell argued that every additional server, operating system, or data pipeline becomes a potential entry point, making...
9 Things I Do as a Data Engineer on Real Projects (9AM to 5PM)
The video demystifies the data‑engineer role, showing it is far more than writing ETL code. A typical day begins with client and business‑user meetings to clarify requirements, followed by scoping sessions where engineers estimate effort, identify dependencies, and flag risks.\n\nTechnical...
Arizona Takes ‘First-in-Nation’ Approach to Data Readiness
Arizona is pioneering a statewide data readiness initiative, the first of its kind in the United States, to lay the groundwork for artificial‑intelligence projects. The state has adopted the Data Management (DAM) framework, which lets each agency benchmark its data capabilities,...