You write a clean, clear, well-turned prompt, and the answer comes back completely off the mark. Nine times out of ten, the problem isn't your sentence: it's everything the model had (or didn't have) in front of it when it answered. Context engineering is the discipline of choosing that information, ordering it, and shaping it so the model works with the right raw material.
Here you'll see what a language model's context actually contains, how to structure it into five reusable layers, which mistakes pollute it without you noticing, and where to practice for real. No technical prerequisites: if you can hold a conversation with ChatGPT, Claude, or Gemini, you're ready. By the end, you'll have a context template to copy for your own tasks, and you'll finally understand why a conversation that runs too long almost always goes off the rails.
What exactly is context engineering?
Context engineering is deciding which information enters a model's context window, in what order, and in what form, before it even starts answering.
A language model remembers nothing between two requests. Every time you hit send, it rereads everything it's given: the starting instructions, the conversation history, the attached files, the tool results. That whole bundle is called the context window. It's measured in tokens, word fragments of roughly three to four characters (the word „context" weighs one or two tokens, a page of text around 400).
That window is large, but it's finite. Recent Claude models accept 200,000 tokens, or several hundred pages, according to the official documentation on context windows. Large doesn't mean unlimited, and above all: the more you fill the window with useless material, the more the decisive information gets diluted.
| Prompt engineering | Context engineering | |
|---|---|---|
| Focus | how you phrase your request | everything the model reads |
| Scope | one message | a session, a project, an agent |
| Typical question | „how do I word this?" | „what does the model need?" |
| Example | adding „answer in 5 bullet points" | supplying the style guide and 3 already-published articles |
The two complement each other. Prompt engineering optimizes the request; context engineering prepares the material. If you're just starting out, the complete method for writing a good prompt is still the foundation everything else rests on.
What an LLM's context really contains
Context isn't just your question: it stacks at least six blocks of information, and your question is often the smallest of them.
- System instructions. The invisible frame set by the tool or by you: role, tone, prohibitions, response language. In ChatGPT these are the custom instructions; in Claude, the project instructions.
- Conversation history. Every previous message, yours and the model's, is sent back on every turn. A 40-message exchange gets paid for again with each new question.
- Documents and data you provide. PDFs, spreadsheets, a pasted web page, a database extract. This is where the volume explodes fastest.
- Examples. Two or three samples of what you expect are worth ten lines of adjectives. That's the whole principle behind few-shot prompting.
- Tools and their results. Web search, code execution, API calls: every result comes back into the window, sometimes thousands of tokens' worth.
- Your actual request. Often a single sentence, buried at the end of everything else.
Out of 20,000 tokens of context, your final question might weigh 40. That's exactly why a model that „isn't listening" is usually a badly fed model, not a broken one. The Anthropic team describes context as a finite resource you have to budget, the same way you budget time or money.
Structuring your context: the five-layer method
Always arrange your context in the same order: role and goal, constraints, reference data, examples, then task and output format.
That order isn't decorative. It puts the frame before the material, and the action instruction right before generation, in the spot the model reads last.
Layer 1: role and goal. Who's speaking, to whom, for what purpose. Two sentences are enough. „You're the content lead at an accounting firm that serves tradespeople. Goal: make tax topics understandable without oversimplifying them."
Layer 2: constraints. Length, tone, banned vocabulary, legal obligations, target audience. Write them as a list, not a paragraph: one constraint per line gets respected far more often than a constraint hidden inside a sentence.
Layer 3: reference data. The facts the model can't guess: your prices, your numbers, your client list, the source text to rewrite. Fence them off clearly, for example between <data> and </data> tags, and tell the model explicitly that it must invent nothing beyond them.
Layer 4: examples. One or two representative samples of what you call „good." If you have a bad one, show that too and explain what's wrong with it.
Layer 5: task and output format. The exact action, then the expected shape: word count, structure, table, JSON, headings. Always end here.
Here's what the result looks like, in short form:
You're writing a newsletter for independent florists.
Constraints: 250 words max, informal tone, no marketing jargon, one idea per paragraph.
Data: our January offer (bouquet subscription at €24 per month, delivery included in Lyon, cancel anytime).
Example of the expected tone: „This month we got ranunculus in. They'll last eight days if you change the water every couple of days."
Task: write the February edition. Format: one headline, three paragraphs, a closing sentence with a call to action.
That block becomes a template. From then on you only rewrite layers 3 and 5, which cuts the time spent preparing each request by two thirds.
The five mistakes that pollute a context
Most bad answers come from a context that's overloaded, contradictory, or badly ordered, not from a lack of intelligence on the model's part.
- The massive copy-paste. Pasting an 80-page report to get two chapters summarized is asking the model to find a key in an attic. Pull out the useful passages, or split the work into several requests.
- Stale context. You said „formal tone" in message 3, then „loosen up" in message 25. Both instructions coexist in the window and the model arbitrates on its own. When you change your mind, rewrite the full instruction instead of patching it a bit at a time.
- Key information buried in the middle. What matters most goes at the beginning (the frame) or at the end (the task). The belly of the context is where attention slackens.
- No output format requested. With no instruction about shape, the model picks its own, and it changes every time. It's one of the recurring errors detailed in the prompting mistakes that ruin your results.
- The never-ending conversation. After 50 messages, your context mostly contains back-and-forth, abandoned attempts, and apologies from the model. Open a new conversation and start again from your updated five-layer block. That's often the move that unsticks a session going in circles.
Where to practice context engineering: three approaches
Three possible routes depending on your budget and level: a guided program with the tools included, the project features of the AI you already use, or the vendors' technical consoles.
Approach 1: a guided program, tools included (Skilzy)
This is the fastest route if you're starting from zero. The Skilzy context engineering program has you build your own context blocks on real cases (product page, newsletter, customer support, automation), with feedback and reusable templates. Skilzy is a French platform with more than 15 programs, from image and video creation to automation with n8n, and its built-in AI Lab gives you access to the real tools with credits included: you practice without stacking up three €20-a-month subscriptions.
Access starts at €29.90 per month, no commitment. Two state-recognized, fundable certifications are available (RS7439 in AI content marketing, RS6792 in AI and sales). To try before you pay, the discovery demo opens for 7 days with 1 image, 1 video, 1 music track, and 10 messages, no credit card.
Approach 2: your AI's projects and custom instructions
Free, or included in your current subscription. ChatGPT and Claude Projects, like Gemini's Gems, exist for exactly this: you drop in your system instructions, reference documents, and examples once and for all, and every new conversation starts with that context already loaded. Perfect for testing the five-layer method today. The limit: you're working without outside feedback, and it takes several weeks of trial and error to figure out on your own what works.
Approach 3: official documentation and vendor consoles
This is the most precise route, and the most demanding. The Anthropic, OpenAI, and Google docs cover context window management, caching for long preambles, and message structuring. The developer consoles let you count tokens and compare two versions of the same context. Useful as soon as you want to scale things up, indigestible if you've never touched an API.
Key takeaways
A good result rarely comes from a magic sentence. It comes from a clean context: a clear role, listed constraints, verified data, two examples, a task, and a format. Build that block once, reuse it, and clean it out as soon as the conversation gets heavy. You'll spend less time fixing vague answers than preparing what you give the model to read, and that's exactly the right balance.
