Skip to content
BestHub
Sign in
Linyb Geek Road
Author

Linyb Geek Road

Tech notes

212
Articles
0
Likes
1.8k
Views
0
Comments
Recent Articles

Latest from Linyb Geek Road

100 recent articles max
Linyb Geek Road
Linyb Geek Road
Oct 13, 2026 · Industry Insights

Palantir Ontology Scenarios: Let Agents Fail Safely in Sandboxes Before Production

This article explains Palantir Ontology Scenarios as sandbox environments where agents and humans can simulate business decisions — like rerouting shipments during port congestion — by applying provisional edits to a live data baseline, computing downstream impacts via Functions, and comparing multiple what-if scenarios before committing changes through a controlled merge action.

ActionAgentDecision Simulation
0 likes · 16 min read
Palantir Ontology Scenarios: Let Agents Fail Safely in Sandboxes Before Production
Linyb Geek Road
Linyb Geek Road
Oct 12, 2026 · Artificial Intelligence

Don't Give Your AI Agent a Super Admin: Palantir Ontology Permission Design

The article explains why enterprise AI agents require fine-grained, runtime permission checks across object types, properties, actions, and identity — not just a simple 'allow AI' switch — using Palantir's ontology framework to illustrate layered security for agents.

AI agentsAction PermissionsObject-Level Security
0 likes · 17 min read
Don't Give Your AI Agent a Super Admin: Palantir Ontology Permission Design
Linyb Geek Road
Linyb Geek Road
Oct 11, 2026 · Backend Development

Palantir Ontology Functions: Turning Business Logic into Reusable, Typed Assets for Agents

The article explains how Palantir Ontology Functions centralize scattered business logic into typed, testable, monitorable server‑side functions that operate on business objects, contrasting them with Pipelines, Actions, and Automations, and showing why they provide stable tools for Agents versus fragile prompt‑embedded formulas.

AgentBackend DevelopmentBusiness Logic
0 likes · 15 min read
Palantir Ontology Functions: Turning Business Logic into Reusable, Typed Assets for Agents
Linyb Geek Road
Linyb Geek Road
Oct 10, 2026 · Fundamentals

8 Palantir Ontology Anti-Patterns That Break Your Data Model

This article details eight common Palantir Ontology anti-patterns grouped into four root causes—system silos, department silos, overloaded objects, wrong execution layers, and poor naming—and provides a prioritized repair checklist to keep ontology models aligned with business reality.

Action SprawlGod ObjectOntology Design
0 likes · 25 min read
8 Palantir Ontology Anti-Patterns That Break Your Data Model
Linyb Geek Road
Linyb Geek Road
Oct 9, 2026 · Fundamentals

Palantir Ontology Modeling: 4 Core Principles for Scalable Domain Design

This article breaks down Palantir's four prioritized ontology modeling principles—domain-driven design, DRY with Rule of Three, open/closed extension, and composition over inheritance—illustrating each with concrete anti-patterns and a practical 12-question review checklist to prevent model fragmentation as teams scale.

Composition over InheritanceDRYModeling Review Checklist
0 likes · 20 min read
Palantir Ontology Modeling: 4 Core Principles for Scalable Domain Design
Linyb Geek Road
Linyb Geek Road
Oct 8, 2026 · Fundamentals

Palantir Ontology Explained: Core Concepts, Agent Integration, and Building a Minimum Viable Ontology

This article breaks down Palantir Ontology's core components—Object Types, Properties, Link Types, and Action Types—using a high-risk order example, contrasts it with knowledge graphs, details how Agents leverage it for decision-making, and recommends starting with a minimum viable ontology for practical adoption.

Action TypeAgentFoundry
0 likes · 18 min read
Palantir Ontology Explained: Core Concepts, Agent Integration, and Building a Minimum Viable Ontology
Linyb Geek Road
Linyb Geek Road
Oct 6, 2026 · Operations

AI Writes Kubernetes YAML in Seconds: The Real Value of Ops Engineers

The article tests AI tools like DeepSeek for generating Kubernetes YAML, finding they handle standard templates well but fail on cluster-specific configs, security, probes, resource quotas, and complex multi-CRD scenarios. It argues ops engineers' value lies in troubleshooting, architecture decisions, incident handling, setting standards, and building platforms—not writing YAML—and advises embracing AI for drafts while deepening core expertise.

AIDevOpsKubernetes
0 likes · 13 min read
AI Writes Kubernetes YAML in Seconds: The Real Value of Ops Engineers
Linyb Geek Road
Linyb Geek Road
Oct 5, 2026 · Databases

Beyond RAG: Vector Databases as General-Purpose Similarity Search Engines

This article explains why vector databases are general-purpose similarity search engines beyond RAG, covering embedding model selection (BGE), non-RAG use cases like recommendation and anomaly detection, core operations with ChromaDB and HNSW, selection criteria for ChromaDB, FAISS, Milvus, and Pinecone, and five practical engineering lessons on recall evaluation, API workarounds, distance vs similarity, chunking strategies, and metadata filtering.

ChromaDBEmbeddingHNSW
0 likes · 12 min read
Beyond RAG: Vector Databases as General-Purpose Similarity Search Engines
Linyb Geek Road
Linyb Geek Road
Oct 4, 2026 · Artificial Intelligence

Mastering Claude Code Customization: CLAUDE.md, Rules, Skills, Hooks & Subagents

This article explains the seven customization mechanisms in Claude Code—CLAUDE.md, Rules, Skills, Hooks, Subagents, Output Styles, and append system prompt—detailing their distinct purposes, ideal use cases, and how they collectively enable effective context management for AI-assisted development.

CLAUDE.mdClaude CodeContext Engineering
0 likes · 16 min read
Mastering Claude Code Customization: CLAUDE.md, Rules, Skills, Hooks & Subagents