Skip to content

ELIXIR / BLOG

Notes on how systems are built.

Articles from ELIXIR on the problems we diagnose, the systems we design and build, and the decisions behind them.

Browse by topic

Four disciplines, one archive.

Latest

5 articles

  • AI & automation11 min read

    AI agents for business: where they actually fit — and where they don't

    Where AI agents can earn a place in a business, where they're a poor fit, and what a process, its data and its owners need before an agent is worth building.

    ELIXIR Creative

  • AI & automation10 min read

    AI agents vs automation: what's the difference — and when to use each

    Automation follows rules you define; an AI agent decides its next step within limits you set. How they differ, when each fits, and how they work together.

    ELIXIR Creative

  • AI & automation11 min read

    RAG vs fine-tuning: which approach does your AI product need?

    RAG changes what a model can read; fine-tuning changes how it behaves. How to tell which problem you have, when to combine them, and when to use neither.

    ELIXIR Creative

  • AI & automation11 min read

    What is an AI agent? How agents use tools, data and workflows

    An AI agent is a language model in a loop: it reads its context, chooses a tool, acts, checks the result and decides what comes next. Its parts, and its limits.

    ELIXIR Creative

  • Digital transformation13 min read

    What AI crawlers can actually read on a website — and what robots.txt does and doesn't control

    AI crawlers read what your server publicly returns. robots.txt is a public request that cooperating crawlers follow — not access control, and not noindex. What each control actually governs, with sources.

    ELIXIR Creative