https://jupaygon.dev/en/posts/ Recent content in Blog on Code & AI https://jupaygon.dev/images/og-default.jpg https://jupaygon.dev/images/og-default.jpg Hugo en 2026 Juanjo Payá Fri, 04 Sep 2026 00:00:00 +0000 https://jupaygon.dev/en/posts/2026-09-04/agent-as-a-user/ Fri, 04 Sep 2026 00:00:00 +0000 https://jupaygon.dev/en/posts/2026-09-04/agent-as-a-user/ What your agents actually do on your machines, if you let them. Watch out for the sudoers that grants root, the SSH allowlists that let them hop anywhere, and other hazards of trusting them too much. https://jupaygon.dev/en/posts/2026-06-17/loop-engineering/ Wed, 17 Jun 2026 00:00:00 +0000 https://jupaygon.dev/en/posts/2026-06-17/loop-engineering/ Addy Osmani and Boris Cherny gave it a name: you stop prompting the agent and start designing the loop that prompts it. Here are their six pieces, which I've spent months trying out in my own setup, plus some critical small print. https://jupaygon.dev/en/posts/2026-05-13/determinism-in-ai-workflows/ Wed, 13 May 2026 00:00:00 +0000 https://jupaygon.dev/en/posts/2026-05-13/determinism-in-ai-workflows/ An AI agent is non-deterministic by design. To make it reliable, you take the decisions that are already made out of the LLM and crystallise them into hooks, scripts and tables. What stays inside the model is bounded execution; the human is who decides. https://jupaygon.dev/en/posts/2026-04-14/context-window/ Tue, 14 Apr 2026 00:00:00 +0000 https://jupaygon.dev/en/posts/2026-04-14/context-window/ The context window is the scarcest resource in AI-augmented development. When your policies, protocols, and sessions grow, the agent starts ignoring instructions. Here is how we fixed it. https://jupaygon.dev/en/posts/2026-04-07/ai-fear-vs-opportunity/ Tue, 07 Apr 2026 00:00:00 +0000 https://jupaygon.dev/en/posts/2026-04-07/ai-fear-vs-opportunity/ Developers fear AI will take their jobs. History says otherwise. AI is the next abstraction layer — and it multiplies whoever uses it. But you cannot multiply by zero. https://jupaygon.dev/en/posts/2026-04-01/claude-code-internals/ Wed, 01 Apr 2026 00:00:00 +0000 https://jupaygon.dev/en/posts/2026-04-01/claude-code-internals/ The Claude Code source was briefly leaked and someone made a public port. We analyzed it in depth. Here are some useful things to get more out of it as a developer. https://jupaygon.dev/en/posts/2026-03-29/ai-skills/ Sun, 29 Mar 2026 00:00:00 +0000 https://jupaygon.dev/en/posts/2026-03-29/ai-skills/ Your AI agent does not know what changed in the latest version of the technologies you use. AI Skills fix that: structured, verified documentation optimized for machines. Here is how we build and use them. https://jupaygon.dev/en/posts/2026-03-26/ai-augmented-development/ Thu, 26 Mar 2026 00:00:00 +0000 https://jupaygon.dev/en/posts/2026-03-26/ai-augmented-development/ I have been working with an AI agent as a development collaborator for months. It is not autocomplete. It is another developer on the team. This is what I have learned.