Putting AI to work

For a company to truly adopt AI and be transformed by it at the deepest level, it must be process-driven rather than person-driven.

A process-driven business delivers value through documented, up-to-date, and repeatable protocols rather than the "personal expertise" of the founder or specific staff members.

To be ready for AI at a deep levet, you must first perform "pre-AI" work.

This "pre-AI" work include, but is not limited to:

Document existing processes, systematize them, and improve them before AI can be applied effectively.

For a simple editorial workflow, I would almost certainly choose reduce, but the "cool" choice (and the one that feels more like an autonomous agent) is generate.

Here is how to decide based on what your "workflow" actually looks like:

Option 1: Use reduce (The "Linear Polisher")

Use reduce if you have a fixed set of operations you want to run on a piece of text (e.g., "Fix Grammar" "Shorten" "Change Tone").

In Nushell, reduce is all about taking a list and folding it down into a single value. When you plug an LLM into that "folding" process, you’re essentially giving the model a "memory" of everything it has processed in the pipeline so far.

Here are three high-level patterns for using reduce with an LLM in your terminal.

How reduce Works (The LLM Mental Model)

Before we dive in, remember the syntax: list | reduce { |it, acc| ... }.

Imagine being able to create graphics in all kinds of popular formats.

Directly from the command line!

I know, that is not the dream of everyone. But then again, you really should try the command line with Nushell.

So many things can be done faster and more consistently that way.

Anyway, here is a small Nushell module I made to work with Google's Gemini 3 pro image preview model. (Google, you gotta come up with a shorter name.)

Do you know all the AI lingo? Let's play the AI bingo here:

1. AI Agents: These are AI systems that can reason and act autonomously to achieve goals. Unlike chatbots that respond to individual prompts, AI agents go through a cycle of perceiving their environment, reasoning about the best next steps, acting on their plan, and observing the results. They can perform various roles, from booking travel to analyzing data or managing IT infrastructure.

This article discusses the growing threat of AI-powered cyberattacks by presenting five examples:

1. AI-Powered Fraud (Deepfakes): Generative AI can create realistic audio and video deepfakes by mimicking a person's voice or appearance. These can be used to impersonate individuals and trick employees into transferring large sums of money, as seen in real-world examples. Even short audio clips can be enough to create a convincing deepfake.

AI slop is a growing issue online. About 50% of new online articles may be AI-generated. This means the internet is filling with content without human involvement.

People create AI content to make money. They can produce many articles quickly this way. This content is often filled with ads.

The goal often is to create websites with low cost. These sites are then filled with advertisements. Small amounts of money can then be earned.

Political reasons also drive AI content creation. People can spread their viewpoints. They can support or refute certain positions.

Record-setting performance, highlighting its ability to manage and extract information from very long texts.

A lot of small companies are struggling with the connection between their own domain specific expertise and the general AI models, the LLM's, of the main providers.

Moonshot AI from China has released Kimi K2. And it is very strong on tool calling.

And maybe most importantly, it is open source.

Here's a breakdown of the key information about Kimi K2:

What is Kimi K2