中文

Use Cases

Real-world AI Agent use cases from marketing to engineering, research to productivity — with recommended tool stacks and step-by-step guides

8

Marketing

14

Engineering

7

Research

14

Productivity

8

Industry

⭐⭐⭐
2-3h/batch

Batch Patent Analysis

Batch download and analyze competitor patent documents. AI extracts key technical solutions, protection scope, and filing trends, helping R&D teams quickly understand the technology landscape and avoid patent risks.

Steps

  1. 1.Define target patent scope and keywords
  2. 2.Download USPTO/EPO patent documents via fetch MCP
  3. 3.Analyze patent claims and technical solutions with Claude

Recommended tools

Claudefilesystemfetchbrave-search
Patent AnalysisIntellectual PropertyR&D
⭐⭐⭐
1-2wk setup

Practical OPD for Post-Training of Large Models: From Principles to Framework Construction

Based on Tsinghua's Rethinking OPD paper, various model technical reports, and LiteScale framework practice, this article systematically explains the core conditions, underlying mechanisms, and engineering implementation of On-Policy Distillation. You will learn how to determine whether a teacher model is suitable for distillation, how to avoid training collapse, and master a set of deployable asynchronous OPD training framework construction methods to improve the performance of small models on reasoning tasks.

Steps

  1. 1.Check whether the teacher model satisfies two core conditions: thought pattern compatibility (high initial overlap rate) and possessing new capabilities that the student lacks (e.g., additional RL training).
  2. 2.If the teacher's conditions are insufficient, prioritize models from the same family that have undergone additional RL training, or use multi-teacher OPD to integrate multiple expert capabilities.
  3. 3.In the existing RL framework, replace the advantage function with the reverse KL divergence of the log ratio between teacher and student, enabling single-line code integration of OPD.

Recommended tools

MegatronSGLangvLLMLiteScale
opdon-policy-distillationpost-training