Learning Hub | CLōD AI Inference Control, Governance & RAG Tutorials

Explore the potential of CLōD, an AI platform designed to give you complete control over your projects. Dive into its features, customizable setups, and everything you need to deploy AI effectively and responsibly.

Latest Released

Managing Teams & Permissions in CLōD (API Keys, Projects, Access Control)

This video covers team and member management inside CLōD. You will learn how to invite members, assign them to specific projects, and manage access to models, guardrails, and API keys. This ensures clear separation between environments and maintains secure, structured AI operations across multiple teams.

Features WALKTHROUGHs

Guardrails Explained, Policy Enforcement, Prompt Defense & Static Patterns

A complete breakdown of CLōD’s dynamic and static guardrails, from prompt defense to policy compliance. Learn how teams can enforce HIPAA, GDPR, and custom rules with intelligent detection or deterministic filtering.

How API Keys Work in CLōD (Models, Guardrails, Routing & Access)

This video explains how API keys work inside CLōD and why they inherit the models, guardrails, routing strategies, and knowledge sources from the project they belong to. You will learn how to create keys, assign them to team members, and structure keys across multiple environments such as development, R&D, and production.

Adding RAG & Knowledge Sources in CLōD (HIPAA & GDPR Example)

This video shows how to add RAG (Retrieval-Augmented Generation) and knowledge sources to a CLōD project. You will learn how to upload documents, connect external systems like Google Drive or HubSpot, configure response modes, and apply knowledge to projects for regulated workflows such as HIPAA and GDPR environments. This enables more accurate and grounded model behavior.

Getting Started with CLōD, registration and first project

This is video shows a complete onboarding walkthrough for CLōD, the programmable AI inference platform designed for control, predictability, and customizable model behavior. Engineer Doeun demonstrates how to register, create your first project, add models, generate API keys, and enable guardrails suitable for regulated environments such as healthcare and enterprise workloads.

Projects Overview, How Projects, Models, Keys & Logs Work

This video introduces the Projects page inside CLōD, showing how environments are structured and how teams can manage model access, API keys, logs, and project-level resources. Projects allow teams to isolate workloads, apply governance selectively, and maintain clear separation between R&D, development, and production. This overview helps teams build scalable, predictable AI environments.

Inside CLōD Studio, Selecting Models, Strategies & Regions

This video provides a detailed tour of the CLōD Studio, where developers configure model behavior, inference strategies, and routing options. You will see how to select from CLōD’s model catalog, choose strategy profiles like Price, Latency, or Token Rate, and define regional routing preferences. This demo is essential for teams optimizing cost, performance, and throughput for real-world AI workloads.

How to Build a Custom Guardrail in CLōD (Healthcare + HIPAA Example)

This video explains CLōD’s guardrail system, covering both dynamic AI-powered rules and deterministic static patterns. You’ll learn how Prompt Defense protects against malicious prompts, how Content Moderation and Policy Compliance maintain safety and regulatory alignment, and how regex-based static patterns enforce deterministic constraints. This is essential for teams operating in regulated or safety-critical environments.

Adding RAG & Knowledge Sources in CLōD (HIPAA & GDPR Example)