Tag
The article explores how AI agents should handle user-initiated task changes during execution, proposing solutions like task revision IDs and discussing edge cases to avoid stale or conflicting actions.
The article lists 11 key software engineering principles, including SOLID, DRY, and KISS, that the author wishes they had understood earlier for improved code design and quality.
This article presents architectural metapatterns that generalize software architecture patterns into wider classes for local and distributed systems, illustrated with intuitive diagrams and outdated presentations.
This article explains how to implement functional state machines in Rust using typestate and newtype patterns for type-safe state management in code.
The article discusses techniques in C++ to enforce derived classes to implement a specific non-virtual method, using examples from C++/WRL and C++/WinRT, and critiques a code review scenario where comments were used instead of proper enforcement.
The article argues that AI agent architectures should separate layers like identity, memory, tools, and authority to avoid unintended dependencies and improve system robustness.
A comprehensive Python programming book by Bruce Eckel covering fundamentals, techniques, patterns, and functional programming.
This article presents five design patterns for building long-horizon agent harnesses, with an open-source GitHub repository for implementation.
A non-engineer shares lessons from eight months of building a persistent multi-agent system, focusing on design problems like session management and solutions using file-based mechanisms.
Google expert Antonio Gulli has released a book on agent design, available as open source on GitHub. It includes 21 chapters and 7 appendices, with runnable Jupyter code, and all royalties are donated to Save the Children.
A tweet sharing an online resource that covers game programming patterns, including computer graphics and common design patterns used in game engines.
The article describes a system enabling AI agents to autonomously handle software tickets to pull requests by removing the 'ask-the-user' tool and implementing an assumption budget, reducing interruptions and improving efficiency in a production codebase.
Tweet promoting two machine learning books: Managing Machine Learning Projects and Machine Learning Design Patterns, with a detailed description of the former for project management techniques.
The article argues that retrying messages in eventually consistent distributed systems treats normal state as failure, and instead suggests storing incoming data and processing when all prerequisites arrive, eliminating the need for retries and dead-letter queues.
A blog post exploring emerging UI/UX design idioms associated with AI interfaces, such as sparkle emojis, shimmering text, and tiny icons, and speculating on their lasting impact on software interaction paradigms.
A practical guide on LLM design patterns covering data preparation, model development, fine-tuning, RAG, and advanced prompting techniques.
A handbook explaining the Observer design pattern, its implementation in Dart, and how it integrates with event-driven architecture and Domain-Driven Design in Flutter applications.
Explains four types of agent loops—turn-based, goal-based, time-based, and proactive—and how each shifts automation from human to system, helping engineers choose the right structure for different tasks.
Discussion of two approaches to software design, as documented on the C2 wiki.
This article introduces the definition and classification of AI agent loops by the Claude Code team, including turn-based, goal-oriented, time-based, and proactive loops, and provides practical advice on controlling token consumption and ensuring code quality.