Practical instructions for research, documents, animation and automation, with ways to check the result.
Try editing a short text or organising sources. Keep your first result so you can compare later changes.
Claude Code, ChatGPT, Codex, skills, plugins, MCP… If you want to try AI and are already fed up with all these names, let’s start with one ordinary task. Open a chat and turn a short note into something useful.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.