Article:https://simonwillison.net/guides/agentic-engineering-patterns/

Agentic Engineering Patterns

Writing code is cheap now
The biggest challenge in adopting agentic engineering practices is getting comfortable with the consequences of the fact that writing code is cheap now.

Code has always been expensive. Producing a few hundred lines of clean, tested code takes most software developers a full day or more. Many of our engineering habits, at both the macro and micro level, are built around this core constraint.

Article: https://huyenchip.com/2025/01/07/agents.html

Agents

At its core, the concept of an agent is fairly simple. An agent is defined by the environment it operates in and the set of tools it has access to. In an AI-powered agent, the AI model is the brain that leverages its tools and feedback from the environment to plan how best to accomplish a task. Access to tools makes a model vastly more capable, so the agentic pattern is inevitable.

While the concept of “agents” sounds novel, they are built upon many concepts that have been used since the early days of LLMs, including self-critique, chain-of-thought, and structured outputs.

This post covered conceptually how agents work and different components of an agent. In a future post, I’ll discuss how to evaluate agent frameworks.

The agentic pattern often deals with information that exceeds a model’s context limit. A memory system that supplements the model’s context in handling information can significantly enhance an agent’s capabilities. Since this post is already long, I’ll explore how a memory system works in a future blog post.

AI-Powered App Development - Steve Sanderson - NDC London 2026
https://www.youtube.com/watch?v=L1w6wBxhpgE

Common pitfalls when building generative AI applications

Article: https://huyenchip.com/2025/01/16/ai-engineering-pitfalls.html

In short, here are the common AI engineering pitfalls:

  1. Use generative AI when you don’t need generative AI
    Gen AI isn’t a one-size-fits-all solution to all problems. Many problems don’t even need AI.

  2. Confuse ‘bad product’ with ‘bad AI’
    For many AI product, AI is the easy part, product is the hard part.

  3. Start too complex
    While fancy new frameworks and finetuning can be useful for many projects, they shouldn’t be your first course of action.

  4. Over-index on early success
    Initial success can be misleading. Going from demo-ready to production-ready can take much longer than getting to the first demo.

  5. Forgo human evaluation
    AI judges should be validated and correlated with systematic human evaluation.

  6. Crowdsource use cases
    Have a big-picture strategy to maximize return on investment.

New blog post: Don't fall into the anti-AI hype by antirez

https://antirez.com/news/158

12 Predictions for 2026 by tomtunguz

https://tomtunguz.com/2026-predictions

Article: https://blog.algomaster.io/p/scaling-a-system-from-0-to-10-million-users

How to Scale a System from 0 to 10 million+ Users

“Do not disturb yourself by imagining your whole life at once.”
Marcus Aurelius

Some AI Readings

https://x.com/gdb/status/2019566641491963946
https://github.blog/ai-and-ml/github-copilot/how-to-write-a-great-agents-md-lessons-from-over-2500-repositories/
https://martinfowler.com/articles/exploring-gen-ai/context-engineering-coding-agents.html
https://github.blog/ai-and-ml/github-copilot/how-to-maximize-github-copilots-agentic-capabilities/
https://github.com/skills/expand-your-team-with-copilot
https://github.com/skills/build-applications-w-copilot-agent-mode
https://github.com/skills/modernize-your-legacy-code-with-github-copilot

El saber no ocupa lugar
- A natural English equivalent is: “Knowledge takes up no space.”
- You can also say: “Learning never takes up space.”

A close English idiom is You can never know too much.