This article provides insights into shifts in programming languages and tools driven by AI, highlighting the growing importance of TypeScript and Python in AI-assisted development, which is crucial for understanding current engineering practices and making informed language choices in enterprise settings.

• — TypeScript has become the leading programming language on GitHub, indicating a shift towards typed languages for AI-assisted development, emphasizing the need for stricter type systems to catch errors early.
• — Python remains crucial for AI projects, evolving from experimentation to production-ready systems, underlining the importance of skills in packaging and orchestration for developers.
• — Fast-growing open source tools favor speed and reproducibility, highlighting the demand for performance-oriented solutions that minimize development friction and enhance contributor onboarding.

This article provides an in-depth exploration of Agentic Engineering Patterns, detailing practical coding practices for leveraging AI agents in software development, which is directly actionable for engineers looking to enhance their workflows.

• — Agentic Engineering focuses on using coding agents like Claude Code and OpenAI Codex to enhance development efficiency, allowing for both code generation and execution without constant human oversight.
• — The project will document coding patterns that improve agent-assisted development, starting with ideas like 'Writing code is cheap now' and 'Red/green TDD' to guide engineers in adapting to these tools.
• — The author maintains a strict policy against publishing AI-generated content under his own name, ensuring all published material is in his own words, while still leveraging AI for supportive tasks like proofreading.

This article provides comprehensive insights into API design principles, addressing critical aspects such as user experience, versioning, and maintaining backward compatibility, which are essential for engineers working on customer-facing APIs in enterprise settings.

• — Good API design prioritizes familiarity over complexity; developers should be able to use an API effectively without extensive documentation.
• — Avoid breaking existing users' setups when making API changes; maintain backward compatibility and only use versioning as a last resort.
• — The ultimate success of an API is tied to the product it serves; a valuable product will attract users even if the API is poorly designed.

This article details a new engineering approach that leverages AI coding agents to enhance productivity and efficiency, providing actionable insights into changing software development practices, which is particularly relevant for enterprise engineering teams navigating similar transformations.

• — Transition to 'compound engineering' allows software development to leverage AI agents for increased efficiency.
• — Focus on a four-step engineering loop: Plan, Work, Review, and Compound to continuously enhance development processes.
• — A single developer can achieve the output of five previous developers by effectively utilizing AI tools like Claude Code, promoting rapid scalability and product iteration.

This case study provides an in-depth look into the real-world challenges and decisions involved in building an AI agent for financial advisors, highlighting practical engineering insights and lessons learned that are crucial for anyone working with AI tooling in enterprise settings.

• — The team eliminated RAG and MCP due to complexity and performance issues, opting for one-shot LLM calls that improved latency and stability.
• — The initial approach with multi-index RAG led to overengineering and slow queries; simplifying back to fundamentals resolved major performance bottlenecks.
• — Emphasize strategic decision-making on when to use agentic RAG, as it can significantly increase costs and response times for complex queries.