BestHub
Sign in
Senior Tony
Author

Senior Tony

Former senior tech manager at Meituan, ex‑tech director at New Oriental, with experience at JD.com and Qunar; specializes in Java interview coaching and regularly shares hardcore technical content. Runs a video channel of the same name.

77
Articles
0
Likes
602
Views
0
Comments
Recent Articles

Latest from Senior Tony

77 recent articles
Senior Tony
Senior Tony
Oct 13, 2026 · Artificial Intelligence

Enterprise AI Agent Security: Why Backend Must Enforce Permissions, Not Prompts

This article details six critical layers of permission and data isolation for enterprise AI Agent systems: identity authentication, query-level data filtering, RAG metadata security, tool risk classification, memory isolation, and audit logging — emphasizing that security boundaries must be enforced in backend code, not LLM prompts.

AI AgentAudit LoggingMulti-tenancy
0 likes · 7 min read
Enterprise AI Agent Security: Why Backend Must Enforce Permissions, Not Prompts
Senior Tony
Senior Tony
Oct 8, 2026 · Artificial Intelligence

Enterprise AI Agents: Why Permissions & Data Isolation Must Be Enforced in Backend, Not Prompts

This article analyzes six critical layers of permission and data isolation for enterprise AI agents—identity authentication, query-time data filtering, RAG metadata security, tool risk classification, memory isolation, and audit logging—emphasizing that security boundaries must be enforced in backend code rather than relying on LLM prompts.

AI AgentsAudit LoggingEnterprise Security
0 likes · 8 min read
Enterprise AI Agents: Why Permissions & Data Isolation Must Be Enforced in Backend, Not Prompts
Senior Tony
Senior Tony
Sep 3, 2026 · Artificial Intelligence

8 Agent Intent Recognition Methods: From Keyword Matching to Hybrid LLM Routing

This article compares eight intent recognition approaches for AI agents — keyword rules, traditional classifiers, LLM prompt classification, embedding routing, tool-based selection, hierarchical routing, context-aware recognition, and hybrid rule/vector/LLM pipelines — detailing trade-offs in accuracy, latency, cost, and maintenance for different business scenarios.

AI AgentsLLM prompt engineeringTool Calling
0 likes · 11 min read
8 Agent Intent Recognition Methods: From Keyword Matching to Hybrid LLM Routing
Senior Tony
Senior Tony
Aug 31, 2026 · R&D Management

10 Core Competencies for High-Paid FDEs in AI Deployment

The article outlines ten critical capabilities required for Frontline Deployment Engineers (FDE) to successfully deliver AI projects, covering business research, problem breakdown, scenario judgment, solution design, rapid demo, data preparation, system integration, process orchestration, security governance, and impact review, emphasizing end-to-end delivery from vague requirements to measurable business value.

AI deploymentAgentElasticsearch
0 likes · 10 min read
10 Core Competencies for High-Paid FDEs in AI Deployment
Senior Tony
Senior Tony
Aug 26, 2026 · Industry Insights

What Is a Forward Deployed Engineer (FDE) and Why Big Tech Is Hiring Them

This article explains the Forward Deployed Engineer (FDE) role, tracing its origins from Palantir to its current critical function in deploying AI models into real enterprise systems, detailing the workflow, required skills, and why FDEs command high salaries in the AI deployment era.

AI deploymentAgentEnterprise AI
0 likes · 9 min read
What Is a Forward Deployed Engineer (FDE) and Why Big Tech Is Hiring Them
Senior Tony
Senior Tony
Aug 18, 2026 · Artificial Intelligence

Master DeepSeek Harness: A No‑Excuse Beginner’s Guide

This step‑by‑step guide shows how to set up DeepSeek Harness, configure the API key and workspace, run a Java project analysis, choose the appropriate agent mode, and decide when to install from source, providing practical tips for Java developers.

AI coding agentAgent modesDeepSeek Harness
0 likes · 10 min read
Master DeepSeek Harness: A No‑Excuse Beginner’s Guide
Senior Tony
Senior Tony
Aug 15, 2026 · Artificial Intelligence

How We Boosted RAG Recall by 15% with Practical Query Optimization Techniques

The article details how a 15% recall@K improvement was achieved in a RAG system by building an offline test set and applying six concrete query‑optimization methods—including rewrite, HyDE, multi‑query, query splitting, contextual completion, and keyword enhancement—while discussing their trade‑offs and implementation tips.

HyDEKeyword EnhancementMulti-Query
0 likes · 9 min read
How We Boosted RAG Recall by 15% with Practical Query Optimization Techniques
Senior Tony
Senior Tony
Aug 11, 2026 · Artificial Intelligence

Six Common Pitfalls When Using WorkBuddy – A 4‑Month Review

After four months of heavy use, the author outlines six easy-to‑miss pitfalls of WorkBuddy—including security risks from third‑party Skills, vague prompts, large‑file overload, rapid credit consumption, unrealistic automation expectations, and model‑switch instability—offering concrete warnings and practical advice.

AI AgentFile HandlingModel Stability
0 likes · 6 min read
Six Common Pitfalls When Using WorkBuddy – A 4‑Month Review
Senior Tony
Senior Tony
Aug 9, 2026 · Artificial Intelligence

How to Choose Between WorkBuddy and Codex: A Detailed Comparison

The article compares WorkBuddy and Codex, outlining their distinct positioning, onboarding difficulty, pricing, model architecture, extensibility, and safety mechanisms, and advises which tool fits different user roles and workflow needs.

AI workflowCodexWorkBuddy
0 likes · 8 min read
How to Choose Between WorkBuddy and Codex: A Detailed Comparison