5 min
Where do you start with AI? With one thing you want to do.
You have opened an AI chat. Now what? Let’s turn a few lines about a picnic into a useful task list. See what to ask for, what to check and how to fix an answer that fills in too much.
AI guides: practical instructions
Guides on prompts, research, data, automation, choosing a model and generating images. With examples and a way to check the result.
Where to start
A good guide helps you finish a specific task. Here you will find instructions, example prompts and ways to judge the result.
Articles: Guides
3 min
AI Motion Designer: animation you can revise in After Effects
The product intro looks good, but the price has changed and a caption appears too soon. This example explains why AI Motion Designer's promise of an editable After Effects project matters.
4 min
AI judging AI: what JEV can tell you about a model’s answer
One model answers; another judges it. Sounds sensible, until we ask who checks the judge. We take a look at JEV and share an exercise of our own.
3 min
GPT-6 Astra at work: a report, a spreadsheet and a post search
A large context window sounds impressive. What can you do with it? We suggest three tasks for Astra: untangling documents, an editable budget and a search feature you can run.
2 min
Veo 3.1: plan the shot, camera movement and sound
Let’s start with a mug, steam and a slow push-in. One scene makes it easier to describe the image, camera and sound to Veo, then fix what does not fit.
2 min
MCP at work: connecting a conversation to order data
The assistant knows the conversation, but the order status lives in another system. MCP helps connect the two. Let’s look at an ordinary question about fulfillment.
2 min
Prompt injection: when a document tries to give your agent orders
The document was supposed to provide information. Instead, it tries to direct the assistant. We explain prompt injection with a simple example and look at where to set boundaries.
2 min
Gemma 4 on your own hardware: from choosing a variant to a first app
Running a model on your own hardware sounds appealing. With Gemma 4, we start with one task, then look at variants, memory and everyday maintenance.
3 min
Nano Banana 2 Lite: three illustrations, one blog style
Three topics, three illustrations, and a blog that still feels like one place. Let’s plan a series with Nano Banana 2 Lite, starting with a few shared rules.
3 min
How to choose an AI model for working with your documents
Which model should you choose? Give both the same proposal and see what they do with the price, deadline and missing information. Time spent correcting them counts too.
3 min
NotebookLM: organize your sources before asking for a summary
We put documents into NotebookLM and ask questions. But what if one describes a new feature and another an old limit? Let’s sort the sources before producing a tidy summary.
3 min
n8n: show the finished email before pressing Send
AI writes the reply; a person decides whether to send it. Let’s build that process in n8n, with the full text to review and a plan for rejection, silence and retries.
3 min
Research with AI: from a list of links to facts you can publish
An answer has three links, so it looks trustworthy. Let’s open them. They may all lead back to one announcement, while the most interesting sentence has no support.
3 min
Wrong RAG answers? Look at the passages used to write them
You upload the current policy, but the chat still gives the old terms. Before changing the model, let’s inspect the passages it actually received.
3 min
Your first AI-assisted prototype: a calculator on one screen
Start with a small tool: two fields, a button and a number of hours. We go from an idea to a prototype someone else can use without our instructions.
3 min
Save a good prompt so it works in a new conversation too
A good result, a saved prompt, a new conversation — and something goes wrong. The important agreements may have stayed in the old chat. Here is how to bring them along.
3 min
A small editorial team with AI: from sources to publication
Someone gathers sources, someone writes from them, someone revisits the suspicious sentence. Let’s divide the work into those three roles, even if one person takes all of them.
3 min
Qwen-Image-2.1: transparent objects for your own composition
Imagine a paper tower on your own background and a moon moving behind it. Qwen-Image-2.1 supports transparency, but its license has a specific research scope.
6 min
Clawdbot: an AI assistant you message in your chat app
You message an assistant in a chat app, and it uses connected tools. That was the idea behind Clawdbot, now developed as OpenClaw. We explain it and correct a common shortcut about local data.
6 min
An AI voice agent: from a phone call to a calendar booking
Instead of “press one,” a conversation about an available appointment. We look at what voice agents need to book a visit and how to tell whether they actually help.
7 min
Claude Cowork: from a folder of material to a document
A folder full of material and a report to prepare. Cowork lets you delegate file work in ordinary language. Here is how to define the task and check what comes back.
5 min
AI in analytics: what to do when a chart suddenly drops
Sales fell. But why? AI can help inspect data and find a lead, but first we need to check the numbers. Start with one question, rather than the promise of an automatic report.