Key Takeaways
- When AI answers the wrong question, it's rarely the model's fault — it's an unclear prompt. AI can only read what you actually wrote, not what you meant.
- A good prompt has four building blocks: Role, Goal, Output and Constraints. Get all four right and the first draft is usually usable.
- Thirty seconds spent stating role, goal, output and constraints saves several rounds of back-and-forth — or stops the model quietly deciding things on your behalf.
- Prompt Wizard turns those four building blocks into fields you fill in — no prompt-engineering skill required.
- Context engineering goes further still: giving AI the documents, data and background a colleague would already have, not just a well-worded request.
- This is article 2 of the five-part AI Essentials series — next up, turning your best prompts into reusable templates the whole team can use.
When AI gets it wrong, the fault may not be AI's
Think back to the first time you used ChatGPT. You typed something short and confident — ‘Write me a thank-you letter’ — and received a paragraph that was correctly formatted, entirely polite, and of no practical use.
That was disappointing. But the model wasn't being unintelligent. It had misread you.
The problem was never the AI. The problem was how we spoke to it.
AI cannot read your mind. It can only read your prompt.
This article explains how to express a request in a way AI can act on — moving from the prompt, to prompt engineering, and then to context engineering.
It also introduces Prompt Wizard, the guided prompt builder inside AnyInsight.ai, which lets people new to AI get useful results from their first attempt.
1. What is a prompt? A set of instructions written for AI
A prompt is what you give the AI to work from: your question, your task, your requirements, your instructions.
An incomplete or vague prompt leaves the AI to guess what you meant. A clear prompt turns it into a produce a useful result.
2. Prompt engineering: treating the prompt as a skill
Prompt engineering is the practice of designing and refining prompts so the AI understands your intention accurately and responds in the most useful form.
It rests on four building blocks:
- Role. What kind of expert should the AI act as?
- Goal. What are you trying to accomplish?
- Output. What form should the result take: an explanation, a comparison of options, or a draft you can use directly?
- Constraints. What rules apply: language, tone, length, or anything to avoid?
You can also develop your own conventions for instructing AI. Test them, examine the results, and keep whichever ones communicate your intention most reliably.
Figure 1: The four building blocks of a prompt
3. One task, two ways of asking, two very different results
Consider again the thank-you letter that was correct in form but empty in substance. It makes a useful demonstration.
❌ A typical first attempt
‘Write me a thank-you letter.’
Current models aren't naive, so a request like this usually produces one of two behaviours:
- The model asks you questions. ‘Who is this for? What are you thanking them for? How formal should it be?’ You then answer one question at a time, and several exchanges are required before you have a usable letter.
- The model writes something anyway. With too little to work from, it fills the gaps itself. It may insert [Recipient] and [Reason] placeholders, or silently select a generic tone and length. Its choices may not match your intention, and you may not notice that it made them. The result simply feels unfocused.
The difficulty hasn't disappeared. It has only changed form: either you spend time answering the model's questions, or the model makes decisions on your behalf that you never see.
✅ Stating the request clearly, using the four building blocks
Combine those four and you have a prompt the model can act on:
| Building block | What to decide | In this example |
|---|---|---|
| Role | Who the AI should act as | An experienced client relationship manager |
| Goal | What to accomplish | Thank a client who has just signed, and leave them confident about the work ahead |
| Output | What form the result takes | An email in English, approximately 120 words, with a subject line |
| Constraints | What rules to follow | Sincere but not excessive; mention next week's kickoff meeting; no sales language |
‘You are an experienced client relationship manager. Write a thank-you email to Mark at Heartbot AI, a client who has just signed with us. The purpose is to thank him for choosing our solution and to leave him confident about the work ahead. Write in English, approximately 120 words, and include a subject line. Keep the tone sincere and professional rather than excessive. Mention that we will schedule a project kick-off meeting next week. Avoid sales language.’
This time the AI doesn't need to question you and doesn't need to guess. The first response is usable, and you can refine the details or the wording from there:
Figure 2: A weak prompt vs. a well-structured prompt
Key difference: the additional effort was thirty seconds of thinking about role, goal, output and constraints.
What you avoided was the sequence of exchanges, along with every decision the model would otherwise have made silently on your behalf.
This is the most basic and most powerful step in prompt engineering — and it's precisely what Prompt Wizard places in front of you: those four fields, ready to complete, with no syntax to memorise.
Prompt Wizard: the four building blocks as fields to complete
This is why Prompt Wizard is built into AnyInsight.ai. The four things you've just considered are the four fields in the wizard:
- Role: who you want the AI to act as
- Goal: what you want done
- Desired Output: what form the result should take
- Constraints: what to require or avoid
Complete the fields and the wizard assembles a well-structured prompt for you. This way of composing a prompt means you don't need to be a prompt engineer to write prompts that work, which makes it the simplest way to begin.
4. Context engineering: helping AI understand the situation
Prompt engineering makes clear what needs to be done. Context engineering goes further and explains why it's being done and under what circumstances.
Context engineering concerns the working relationship between you, the AI, and the environment around a task. It systematically provides the AI with the relevant documents, working reports, surrounding discussion, the people involved, and the current state of progress — in other words, everything a colleague would already know.
Figure 3: From a prompt, to prompt engineering, to context engineering
5. Putting context engineering into practice
The objective is straightforward: give the AI access to the conversation history, current data, background material, and any rules defined in advance, and only then ask it to respond.
(1) Provide the relevant material
Suppose you want the AI to evaluate a media campaign proposal. Instead of asking whether the campaign is good, provide what you would give to a colleague:
- A target market analysis report (PDF)
- Customer behaviour charts (images)
- Performance data from the previous campaign (Excel)
- Feedback notes from your team (text file)
If you don't have the material, or the material you have is incomplete, two further options are available:
- Web Search. The AI searches the open web for the information that's missing.
- Connectors. The AI connects to your company systems, such as a customer support system or a knowledge base, and retrieves, reads and organises the relevant records on your behalf.
Figure 4: Giving AI what a colleague would already know
Only when the AI genuinely understands the context — your reasoning, your objective, and sufficient supporting material — does it stop producing plausible marketing language and begin proposing something that addresses the actual problem.
(2) Work in rounds, and divide the prompt into steps
Once the material is available, a first round of collaboration usually proceeds as follows:
- Describe the background and the objective. The AI needs to understand the current situation and the outcome you're working towards.
- Establish the wording and the tone. The AI needs to understand how you work and how you regard the task before it can represent you well.
- Decide the format and the action. State what the finished result should be: a table, a file you can download, or an email sent directly through a Connector.
- Review and correct. Whenever a response takes the wrong angle, uses the wrong wording, or misses the point, say so and ask the AI to revise. Repeat until the result is correct.
(3) Use a dedicated AI agent
You can browse the Agent Storefront from the AnyInsight.ai home page and select a ready-made AI agent by category.
When a recurring task has no matching agent, or when the task depends on knowledge specific to your organisation — such as internal policies or particular operating requirements — Agent Builder addresses that need. Following the same context-engineering principles, you can create an agent with a defined role, for example:
- A first-pass contract review agent
- A brand copywriting agent
- A marketing campaign analyst
Everything the agent requires — the supporting material, the principles it should reason by, and the rules it must follow — is defined once. You never have to instruct the AI again, and you can share the agent with your team. This is what turns an AI agent into something that understands your work: less repetition, consistent quality, and a genuine digital colleague.
Conclusion: context is how you direct AI
Models continue to become more knowledgeable and better at interpreting prompts and attachments. To collaborate with a human team and solve real problems, however, an AI still needs the context around the task — and that context has to come from you.
AnyInsight.ai protects that context, which is the point of the platform. You can give the AI your real work rather than only the questions that feel safe to ask. For an explanation of how the platform protects your data, see the first article in this series.
Getting AI to work for you begins with knowing how to instruct it.
In the next article, we examine what happens to an entire team's output once those four building blocks are completed in advance and saved as a template.
📚 This article is part of the AI Essentials series
Figure 5: The AI Essentials series learning path
The Series, Start to Finish
- Part 1 — So Many AI Tools. Where Should You Start?
- Part 2 — Why Does AI Answer the Wrong Question? ← You are here
- Part 3 — How Prompt Templates Boost Team Efficiency
-
Part 4 — Which LLM Should You Actually Use?
- Part 5 — Solving Complex Tasks with Multi-AI Architecture (MAIA)
