AIP(AI Platform)란 무엇인가
Foundry에 내장된 생성형 AI 계층을 소개합니다.
이 글부터 읽으세요
처음이라면 이 4편으로 시작하는 걸 추천합니다.
Start With These
New here? These four posts are the best place to start.
Start here
What Is Palantir Ontology? A Practitioner’s Explanation
New to Ontology? Start here
HubOntology Hub — See All Related Posts
Every Ontology post in one place
AIP“Why Not Just Bolt On a Chatbot API?”
Why AIP is built differently
ArchitecturePalantir Foundry Architecture Overview
The whole structure in one page
최신 아티클
Foundry·온톨로지·기업 AI를 이해하는 데 도움이 되는 실전 메모와 가이드입니다.
Latest Articles
Practical notes and guides to help you understand Foundry, Ontology, and enterprise AI.
-
Building an MCP Server: Connect Claude to Your Internal Systems
Summary — In Part 1 we touched on MCP (Model Context Protocol) only briefly, as “the standard interface that lets an agent connect to outside tools and data.” This article goes further and actually builds an MCP server, so that Claude can reach into your internal systems — internal APIs, databases, files. If you’ve already […]
-
I Took Apart the Seven Pieces of an Ontology Using a Single Machine
I Get the Concept, But What Do I Actually Have to Define? You’ve probably heard an Ontology described as “a map that translates a company’s reality into something software can understand.” But the moment you actually try to build one, you hit a wall: “Okay, so what do I actually need to define?” This article […]
-
Building Your First Screen in Workshop: Widgets and Ontology Object Binding
How Palantir Foundry’s Workshop actually works — widget composition, the ontology object binding mechanism, and the mistakes that cause the most rework.
-
When Customer and Client Both Exist in the Same Ontology — What Happens When Naming Falls Apart
Palantir Ontology has no enforced code/description split like SAP master data. Without a naming standard set from day one, Object Type and Property names collapse into chaos as the ontology grows.
-
Palantir Is Expensive. Here’s Why We Use It Anyway
A practitioner’s TCO-based framework for deciding whether Palantir is worth its price: integrated platform vs. tool sprawl, why better LLMs don’t remove the need for an ontology, and whether you can build one yourself.
-
How Foundry Actually Stores Data: ELT (Not ETL), and OSv2
Why Palantir Foundry stores data as file-based Datasets with Git-like branches and transactions, and how OSv2 turns that into an ontology’s actual storage layer.
-
Connecting Claude to Your Ontology with OMCP: A Hands-On Guide
How to make Claude answer questions like ‘analyze last month’s top customer segment’ without opening the Foundry UI. Covers the 4 connection steps and where people usually get stuck.
-
Palantir Foundry Ontology Manager Guide: 5 Mistakes to Avoid When You Design Your First One
Walk through building an Object Type, Link Type, and Action Type end to end using a single Equipment example, with 3 common design mistakes to avoid.
-
Palantir Foundry Architecture Overview: From Connect to AI in Five Layers
Why does Foundry have so many applications? A practitioner’s map of the five-layer architecture — Connect, Pipeline, Ontology, Applications, AI — and how it differs from a traditional BI/ETL stack.
-
What Is Palantir Ontology? A Practitioner’s Explanation
Palantir Ontology explained by someone who runs Foundry in production: what it actually is, how it differs from a data model or knowledge graph, and when you don’t need one.