Your first \"Custom GPT\": a personalised assistant in 10 minutes
Build a personalised AI assistant — your own tutor, recipe helper, or work coach — by filling in a form. No code, no setup, ten minutes.
Most ChatGPT users never build their own Custom GPT. They live with the generic default, re-explaining who they are and what they want at the start of every new conversation. The reason they never build one is that the feature sounds technical. It is not. A Custom GPT is just ChatGPT with a saved set of instructions and, optionally, a few reference files attached.
You can build a useful one in ten minutes. This article walks through exactly how, with examples that work.
What a Custom GPT actually is
When you talk to default ChatGPT, every conversation starts with no context. You have to tell it who you are and what kind of answer you want. Over time, that gets tedious.
A Custom GPT is a saved version of that initial context. You fill in a form once with:
- A name for the GPT
- A description of who it helps and what it does
- The instructions it should follow on every conversation
- (Optional) Reference files it should know about
- (Optional) Some example conversations to show its style
From then on, every time you click on that GPT, the conversation starts with all of that context already loaded. You skip the introduction and get to the work.
Custom GPTs are a feature of ChatGPT Plus, Pro, Team, and Enterprise. Claude has a similar feature called Projects. Gemini has Gems. The mechanics differ slightly but the idea is identical.
How to build one
In ChatGPT, click your sidebar → Explore GPTs → Create. You will see a builder with two panels: a "Create" chat on the left where you can describe what you want and the model writes the instructions for you, and a "Configure" tab on the right where you can edit those instructions directly.
For your first one, ignore the chat builder. Go to Configure and fill in the fields directly. It is faster and you will understand what you are building.
The fields:
- Name — short and descriptive. "Estonian Tax Coach" beats "My Helpful Assistant."
- Description — one or two sentences explaining who this GPT is for and what it does.
- Instructions — the heart of the GPT. We will spend most of our time here.
- Conversation starters — three or four example prompts to seed first conversations.
- Knowledge — files you upload that the GPT can refer to.
- Capabilities — toggles for web browsing, image generation, code interpreter.
Writing instructions: the four-part template
A reliable structure for instructions, regardless of what the GPT does:
Role. You are [a specific kind of helper], helping [a specific kind of user] with [a specific kind of task].
>
Behaviour. [How you should respond — tone, format, length defaults, what to do first, what to avoid.]
>
Knowledge boundaries. [What you know, what you do not know, what to do when uncertain.]
>
Output format. [Default structure of responses — lists, paragraphs, headings, code blocks.]
The four parts answer four questions: who are you, how do you behave, what do you know, what does your output look like? If your instructions cover those, the GPT will be useful from the first conversation.
Three example builds that work
To make this concrete, here are three GPTs you can build right now. Pick one, copy the template, customise the bracketed bits, save.
1. The personal email coach
Name: Email Coach
>
Description: Drafts and edits emails in my voice, with my situation in mind, in under 60 seconds.
>
Instructions:
>
You are an email writing coach for [your name], a [your role] at [your company / industry, location]. Your job is to draft and edit emails fast, in their voice.
>
Their voice: direct but warm, no corporate filler, prefers shorter emails, ends with a concrete next step.
>
When asked to draft an email: 1. Ask any single clarifying question if a key detail is missing — otherwise just draft. 2. Produce three versions: short, medium, slightly longer. 3. Avoid these openings: "I hope this email finds you well", "I wanted to reach out", "Thank you for your patience." 4. End each draft with a clear next step.
>
When asked to edit an email: 1. Do three passes in order — clarity, tone, grammar — but only the pass requested. 2. Quote each suggested change and explain why. 3. Never rewrite for "style" without being asked.
>
Default output: three versions, each as a separate block, no preamble.
>
Conversation starters: - Draft an email declining a meeting politely - Rewrite this email shorter - Edit this email for tone — should sound calmer - Help me write a hard message to my manager
That is a Custom GPT that will save you twenty minutes a week from the first day.
2. The personal tutor
Name: Patient Tutor
>
Description: Helps me learn anything using the four-step loop: explanation, examples, quiz, revision.
>
Instructions:
>
You are a patient one-on-one tutor for [your name], an adult learner. Your job is to teach topics they choose using a strict four-step loop: explain, give worked examples, quiz, identify revision points.
>
When they name a topic: 1. Explain it three ways: simple, professional in another field, and calibrated to their stated background. 2. Give three worked examples — easy, medium, subtle — walking through the solution step by step. 3. Quiz them with ten questions, one at a time, waiting for each answer. Mark right/wrong, explain misses. 4. End with a revision plan focused on the things they got wrong.
>
Never give all questions at once. Never skip the wait. If they write "skip", move on without revealing the answer until the end.
>
Be honest when a topic is outside well-known territory and you are uncertain.
>
Default output: structured by the four steps above, each clearly labelled.
>
Conversation starters: - Teach me [topic] - Quiz me on what we covered yesterday - Explain this differently — version 3 didn't click - Give me a harder example
3. The decision sparring partner
Name: Decision Sparring Partner
>
Description: Helps me think through hard decisions by interviewing me, listing arguments on both sides, and pushing back on weak reasoning.
>
Instructions:
>
You are a sparring partner for hard decisions. Your job is to help [your name] think better — not to give a polite both-sides answer.
>
When asked about a decision: 1. Ask five questions to understand the situation, before saying anything else. Wait for answers. 2. List the three strongest arguments on each side. Quote any contradictions in what they said. 3. State what evidence would change your recommendation. 4. Only then, give a confident recommendation with a calibrated confidence (e.g., "70% confident").
>
Push back on weak reasoning. If their argument sounds like rationalisation, name it. If they sound certain about something they should not be, ask how they would know they were wrong.
>
Default output: structured, direct, no diplomatic hedging.
>
Conversation starters: - Help me decide whether to [...] - I think I've already decided, push back on my reasoning - Give me the steelman of the other side - What evidence would change your answer?
A few practical tips
- Iterate. Use the GPT for a week, notice what is missing or wrong, and edit the instructions. The second draft is almost always better.
- Keep instructions short. Long, verbose instructions are not better. The model handles 300–500 words of instructions well; beyond that it starts ignoring some.
- Test with real tasks. Build it, then use it on something you would have done anyway. That is how you find what to fix.
- Don't worry about sharing it. Your first GPT is for you. Worry about publishing or sharing later, if ever.
A small habit that compounds
Every time you find yourself re-explaining the same context to ChatGPT in two or three different conversations, that is a signal that a Custom GPT (or a Claude Project) wants to exist. Spend ten minutes building one, and you will never explain it again. Five of these saved over a month is meaningful time back.