社区文章
来自 awesome-agentic-patterns 的扩展阅读，每篇文章包含 Problem / Solution / How to use / Trade-offs 完整内容。
按分类浏览
最新文章
Abstracted Code Representation for Review
Reviewing large volumes of AI-generated code line-by-line can be tedious, error-prone, and inefficient. Human reviewers are often more interested in v…
Action Caching & Replay Pattern
LLM-based agent execution is expensive (both in costs and latency) and non-deterministic. Running the same workflow multiple times yields different re…
Action-Selector Pattern
Untrusted input can hijack an agent's reasoning once tool feedback re-enters the context window, leading to arbitrary, harmful actions.
Adaptive Sandbox Fan-Out Controller
Parallel sandboxes are intoxicating: you can spawn 10... 100... 1000 runs. But two things break quickly: 1. **Diminishing returns:** After some N, yo…
Agent-Assisted Scaffolding
Starting a new feature, module, or codebase often involves writing a significant amount of boilerplate or foundational code. This can be time-consumin…
Agent-Driven Research
Traditional research methods often lack the ability to adapt search strategies based on emerging results, limiting efficiency and potential discoverie…
Agent-First Tooling and Logging
Most developer tools, CLIs, and application logs are designed for human consumption. They use color-coded, multi-line, or summarized outputs that are …
Agent-Friendly Workflow Design
Simply providing an AI agent with a task is often not enough for optimal performance. If workflows are too rigid, or if humans micromanage the agent's…
Agent Modes by Model Personality
Different AI models have fundamentally different personalities and working styles. Treating all models the same—expecting them to work identically—lea…
Agent-Powered Codebase Q&A / Onboarding
Understanding a large or unfamiliar codebase can be a significant challenge for developers, especially when onboarding to a new project or trying to d…
Agent Reinforcement Fine-Tuning (Agent RFT)
After optimizing prompts and task design, agents may still underperform on your specific business tasks because: - **Domain shift**: Your tools and b…
Agent SDK for Programmatic Control
Interactive terminal or chat interfaces are suitable for many agent tasks, but not for all. Integrating agent capabilities into automated workflows (e…