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.
-
Analyzing Ontology Data on a Personal AIP Developer Account via OMCP
Why You Can Analyze Data on a Personal Account Too The OMCP setup guide covered the basic structure of connecting Claude to an Ontology. This post covers applying that structure to a personal AIP Developer account to actually analyze data. Without any company infrastructure, you can connect an Ontology built inside your own personal account […]
-
Setting Up OMCP: Connecting Claude in the Developer Console
Why OMCP Exists For an LLM like Claude to make use of Ontology data, copy-pasting text in on an ad hoc basis only gets you so far. OMCP (Ontology Model Context Protocol) builds on MCP (Model Context Protocol) — the open-source protocol Anthropic released — to hand an Ontology’s objects and relationships to Claude as […]
-
Quiver: Spotting Patterns Across Time-Series Ontology Data
Why Quiver Exists If Object Explorer is a tool for inspecting objects one at a time, Quiver is for visualizing many objects and time-series data together at once to spot patterns. It’s especially suited to data where the time axis matters — sensor readings, transactions — letting you apply operations like moving averages, interpolation, and […]
-
AIP Logic: Pairing LLM Reasoning with Deterministic Workflows
Why AIP Logic Exists LLMs are flexible, but by nature non-deterministic — nothing guarantees the same question gets the same answer every time. AIP Logic is an authoring tool for visually designing that LLM reasoning ability alongside deterministic logic blocks — conditionals (if/else), loops, API calls — so the unpredictable part stays contained inside controllable […]
-
AIP Assist: Your Ontology-Aware Data Copilot
Why AIP Assist Exists If AIP Logic is a tool for designing a specific workflow, AIP Assist is an operating copilot that sits beside the user and handles query writing, code generation, and data analysis on request, in natural language. What sets it apart from a generic chatbot is that AIP Assist answers with an […]
-
AIP Chatbot Studio: Building Shared Conversational Interfaces
Why Chatbot Studio Exists If AIP Assist is a personal assistant that helps an individual user, Chatbot Studio is a no-code/low-code tool for designing and deploying conversational interfaces that many users share at once. Relying on a pure LLM chatbot alone means even highly standardized tasks (checking a reservation, answering an FAQ) can get answered […]
-
AIP Analyst: The AI Agent That Runs Its Own Analysis
Why AIP Analyst Exists If AIP Assist is a personal assistant that reacts to whatever you ask it in the moment, AIP Analyst is closer to an autonomous agent that carries an entire analysis task through from start to finish. It goes beyond simply writing SQL for you — it plans the analysis itself, executes […]
-
How Palantir AIP Grounds LLMs in the Ontology
-
What Is Palantir Apollo? Automatic Updates Are Great — Until They Aren’t
Palantir Apollo’s Hub/Spoke architecture, release channels, and recall/rollback mechanics, explained from official docs, plus a practitioner’s honest take on the trade-offs of autonomous deployment.
-
Building a House with LEGO, Until You Need a Curved Roof — Workshop UI Design Principles and the Customization Ceiling
A LEGO-building take on Palantir Workshop’s layout design principles (whitespace, hierarchy, typography), plus the real customization limits users actually hit — verified with official docs and real user reviews.