How AI Agents Work: Tools, Builders & the Internal Architecture

How AI Agents Work: Tools, Builders & the Internal Architecture

Video by H2O.ai via YouTube
How AI Agents Work: Tools, Builders & the Internal Architecture

Knowing what an agent can do is one thing. Knowing how it works inside is another, and it is more structured than most people expect.

Give a general-purpose agent a goal and it plans the steps, picks its tools, executes, checks its own results, self-corrects when something looks wrong, and delivers a summary or output files. Plan, act, check, self-correct, deliver. That loop is what separates an agent from a chatbot.

Terms covered:
– Agent Tools: the specific actions an agent can take, from web search to running code to calling APIs
– Tool Builder: creating custom tools so an agent can reach internal databases, custom APIs and legacy systems
– Agent Builder: the environment where you set the agent’s goal, tools, instructions and constraints, without deep engineering

The internal loop gives it intelligence. The tools define its reach. The builder is how you put it together.


AI Fundamentals Glossary | H2O.ai University
Full playlist: https://www.youtube.com/playlist?list=PLAWKlIKS-66E
Free courses and certifications: https://h2o.ai/university

#AIAgents #AgenticAI #AI #AIGlossary #H2Oai

Source

Copy of ChatLoopBackOff Episode 82: SlimFaas with Thomas and Guillaume

Copy of ChatLoopBackOff Episode 82: SlimFaas with Thomas and Guillaume

Video by CNCF [Cloud Native Computing Foundation] via YouTube
Copy of ChatLoopBackOff Episode 82: SlimFaas with Thomas and Guillaume

In this episode of ChatLoopBackOff, CNCF Ambassador Henrik Rexed explores OpenEverest for the first time, with CNCF Maintainer Sergey Pronin live on stream to navigate obstacles and elaborate on features as they are encountered.

OpenEverest is a CNCF Sandbox project that provides an open-source database-as-a-service (DBaaS) platform for Kubernetes environments.

Join us on September 24 for this practical, live dive into OpenEverest!

Source

Why your location data is everywhere now 📍 #tech #finance #future

Why your location data is everywhere now 📍 #tech #finance #future

Video by FINOS via YouTube
Why your location data is everywhere now 📍 #tech #finance #future

Learn how location information is becoming a fundamental part of modern business operations rather than just a simple add-on.

This discussion focuses on the shift toward integrating data about the physical Earth into our daily workflows. We examine why this shift is happening and how organizations are moving beyond basic mapping to treat spatial intelligence as a core asset. For professionals and decision-makers, understanding this evolution is critical for staying ahead in a data-driven environment.

As we integrate more geospatial data into our systems, the way we handle complex projects changes significantly. We look at the practical reality of these data operations, where spatial context is no longer optional but essential for success. Recognizing this pattern helps teams prioritize the right technical infrastructure for long-term growth.

Subscribe for weekly insights on industry trends and leave a comment sharing how you currently use location data in your own work.

Source

Building Context-Aware AI Agents with Real-Time Data

Building Context-Aware AI Agents with Real-Time Data

Video by Open Data Science and AI Conference via YouTube
Building Context-Aware AI Agents with Real-Time Data

This event is part of the ODSC AI Skills Accelerator, bringing together AI and data professionals for practical, expert-led sessions on building real-world AI systems.

Just like we don’t put crude oil in a car—we refine it into gasoline—AI can’t run on raw data. It needs continuous, refined context. Serving fresh context is the missing architectural layer for reliable AI.

In this session, learn how IBM, Confluent Intelligence, and Google Cloud turn operational data into fresh context for AI agents to take the right action at the right time. See how Confluent’s data streaming platform turns operational data into automated decisions, and how Google Cloud adds a layer of real-time investigation and explanation on top—all grounded in context that reflects the current state of the business.

We’ll demo a real-time architecture for anomaly detection and investigation—streaming racing telemetry through Confluent’s Real-Time Context Engine, where a Confluent Streaming Agent detects anomalies and recommends pit timing in real time. You’ll then see a Gemini agent in Google Antigravity, connected via MCP, investigate those decisions and explain the reasoning behind them, with governed data synced to BigQuery for historical record and analysis.

You’ll leave with practical, streaming-native patterns to move from brittle pipelines and demos to production-grade AI on Google Cloud while reducing TCO.

Speakers:

– Karan Sachdeva, IBM
– Sean Falconer, Confluent
– Sohrab Rahimi, Google Cloud

Join us on September 9 for a new ODSC AI Skills Accelerator session, bringing together experts from IBM, Confluent, and Google Cloud to explore how real-time data and fresh context can power more reliable AI agents.

Source

Ask The Hosts – Episode 40

Ask The Hosts – Episode 40

Video by The Late Night Linux Family via YouTube
Ask The Hosts – Episode 40

Support us on Patreon and get an ad-free RSS feed with some early episodes. https://www.patreon.com/LateNightLinux

Pop culture phenomena that passed us by, and how long it’s acceptable to wait before replying to a message. With Félim, Gary, Jim, and special guest Shane from Linux Lads.

https://askthehosts.com/ath40/

Source

So, What Exactly is SAP Business AI Platform? 🤔

So, What Exactly is SAP Business AI Platform? 🤔

Video by SAP via YouTube
So, What Exactly is SAP Business AI Platform? 🤔

Every Autonomous Enterprise needs a strong foundation. 🧱🛠️

SAP Business AI Platform brings together business context, unified data, governance, and AI development to build trusted enterprise AI across three core pillars:

➡️ Build: Create AI agents, apps, and workflows grounded in your business.
➡️ Contextualize & Reason: Help AI understand your data, policies, relationships, and business logic.
➡️ Govern: Scale AI securely with built-in governance, compliance, and control.

Learn more: https://sap.to/6056BGJaWQ

Source

Windows Weekly 1000

Windows Weekly 1000

Video by TWiT Tech Podcast Network via YouTube
Windows Weekly 1000

Windows Weekly is about more than Windows. Veteran Microsoft insiders Paul Thurrott and Richard Campbell join Leo for a deep dive into the most valuable company in the world. From consumer to enterprise, AI to Xbox, Windows Weekly is the only Microsoft podcast you’ll ever need.

You can find more about TWiT.tv and subscribe to our full shows at https://podcasts.twit.tv
Join our community at Club TWiT: https://twit.tv/clubtwit

About us:
TWiT.tv is a technology podcasting network located in the San Francisco Bay Area with the #1 ranked technology podcast This Week in Tech hosted by Leo Laporte. Every week we produce over 30 hours of content on a variety of programs including Tech News Weekly, MacBreak Weekly, Windows Weekly, Security Now, Intelligent Machines, and more.

Source

IWSDK: Code That Compiles Is Not Proof

IWSDK: Code That Compiles Is Not Proof

Video by Meta Developers via YouTube
IWSDK: Code That Compiles Is Not Proof

The object ended up in the wrong place. 😵‍💫 Was it physics, the grab, or something else? Watching it happen in a headset rarely tells you how or why.

Immersive Web SDK (IWSDK) gives your agent scene graph inspection and ECS-level debugging, so it can pause the runtime, step forward a frame, and compare the state before and after until the cause shows up in the data.

🔗 Start building immersive web experiences faster with IWSDK at the link in the comments.

#WebXR #WebDev #XRDev

Source