The AIM method: Actor, Input, Mission

Start here. Three simple parts turn a vague request into a useful answer: who should answer, what it needs to know, and exactly what you want back. No technical background needed.

Mohd FikriMethods & frameworks6 min readBeginner
Baca dalam Bahasa Melayu
  • Draft: this article is under editorial review and may change.

Walk up to the counter at your favourite mamak and say “teh”. You will get a teh: hot, sweet, in a glass. Nothing is wrong with it. But if you wanted teh tarik, less sugar, to take away, it is not your drink.

Asking an AI works the same way. Many disappointing AI answers come from the request, not the AI. Ask for “a KRT activity report” and it has to guess the activity, the audience, the template and the length. So it gives you the most common answer, and the most common answer rarely fits your district.

AIM fixes this with three parts you can remember on the way to your next meeting. It works in any ChatbotAn AI you talk to in a chat window. You ask, it answers, and you decide what to do next. or AI agentAn AI that does a multi-step job for you (planning, opening files, using tools and checking its work) instead of only replying once., and you need no technical background.

The idea in 30 seconds

Actor: who answers

Pick the expert you need, such as "a unity officer at a district office".

The idea in 30 seconds0:00 / 0:26
  1. Actor: who answers Pick the expert you need, such as "a unity officer at a district office".
  2. Input: what it can't guess Your district, your rules, your material.
  3. Mission: exactly what to produce Start with an action verb. Say how much and in what form.
  4. Check against your Mission Tick off each thing you asked for. AI can sound sure and still be wrong.
  5. Vague in, average out. Clear in, useful out.

Key takeaways

If you remember nothing else, remember these.

  • Actor: who the AI should be while it works.
  • Input: everything it needs to know but cannot guess.
  • Mission: exactly what to produce, and in what form.
  • Then check the answer against your Mission before you use it.

Order your AI like you order teh tarik

A regular at the mamak never just says “teh”. They give the full order, and the tea maker gets it right first time. Tap between the two orders below.

Boss, teh tarik satu, kurang manis, ikat tepi.

What you typically get back

Your drink, first time. You chose who to ask (the tea maker), told them what they could not guess (less sugar), and said exactly what to hand over (teh tarik, packed to take away).

The AI is the tea maker. It is skilled and fast, but it has never met you. AIM is your full order: Actor is who you ask, Input is what they cannot guess, and Mission is exactly what you want handed back.

Why a clear order beats clever wording

Every request starts with a huge number of possible answers. A vague PromptThe message or instructions you type to an AI. A better prompt usually means a better answer. leaves all of them open, so the AI drifts towards a safe, middle-of-the-road reply. Each part of AIM closes off answers you did not want.

How AIM narrows the space of possible answersA cloud of dots, each a possible answer. Actor removes answers from the wrong perspective, Input removes answers that do not fit your facts, and Mission removes the wrong deliverable and format. With all three, only a few dots remain: the answer you need.AIM

Switch A, I and M on and off to watch the answers narrow.

Each part of AIM removes a band of unwanted answers. By the time the Mission is clear, very few answers fit, and they are the ones you need.

You do not need fancy phrasing or secret words. A plain, complete order works better than a clever, incomplete one.

Anatomy of an AIM prompt

Here is a typical request from an officer at a JPNIN district office. Tap each coloured part to see what it does.

Dissect a prompt

A district officer's activity report request

Tap a coloured part of the prompt to see what it does.

You are an experienced unity officer at a JPNIN district office who writes KRT activity reports for the state office. Activity: a gotong-royong and community breakfast by KRT Taman Seri Contoh on Saturday, with about 80 residents from three communities. My rough notes and the attendance count are pasted below. Names and phone numbers have been removed. Use our state office template: Objective, Activity summary, Attendance, Outcome, Follow-up. Write the report in formal Bahasa Melayu, in no more than 300 words, under those five headings. Put the attendance in a small table and mark any detail missing from my notes as [TO CONFIRM].

New words in that example: Jabatan Perpaduan Negara dan Integrasi Nasional, the department under KPN that runs unity work in the states and districts. and Kawasan Rukun Tetangga: a neighbourhood area whose volunteer committee runs activities that bring residents together.. Tap either of them for a one-line meaning.

A for Actor: choose who answers

The Actor tells the AI which knowledge, priorities and vocabulary to bring forward. Think of it as choosing which colleague to ask. “You are a helpful assistant” adds nothing, because that is already the default.

A useful Actor has three ingredients:

  1. A role: “unity officer”, “secretariat officer”, “community mediator”.
  2. A setting: “at a JPNIN district office”, “in a KPN ministry division”, “preparing a brief for the Minister”.
  3. An audience: “who writes for KRT committee volunteers” changes the tone and difficulty for you.

You can also choose a critic on purpose. “You are a sceptical state director reviewing this report” is a good way to get honest criticism of your own draft instead of praise.

I for Input: give it what it cannot guess

The AI has never met your KRT committees, seen your department’s template or read your notes. Input is everything it needs to know but cannot work out alone. Before you send a request, run through five quick checks:

  • Context: who, where, which community, and why the task exists.
  • Material: the text, figures or notes to work on. Paste them or attach them.
  • Rules: templates, word limits, official terms, policies and deadlines.
  • Example: one sample of the style you want often says more than a paragraph of description.
  • Limits: what it must not do, such as “use only the notes I give you” or “do not add figures that are not in my notes”.

M for Mission: say exactly what you want back

The Mission is where most prompts go wrong. Usually it is one vague verb: “help”, “look at”, “improve”. A strong Mission starts with a clear action verb and answers four questions:

Question Weak Strong
What action? help me with write, list, rewrite, summarise
What exactly? a report a KRT activity report for the state office
How much? — five headings, under 300 words
What form? — the state template, with attendance in a table

The verb leads the Mission, and it matters more than people expect. Our guide on Bloom and Simpson, two lists of precise verbs for what the work must know and do, shows how a sharper verb makes the answer noticeably sharper and easier to check.

Here is the same idea in the office. Tap between the vague and the precise version.

You are an admin officer at a JPNIN district office who writes short, friendly notices for KRT chairpersons.

This year's KRT activity claims must reach the district office by 15 November, with the activity report and receipts attached. Late or incomplete claims move to the next processing cycle. Many KRT sent claims without receipts last year. Contact: Encik A at the district office, extension 2104.

Write a notice of no more than 120 words in simple Bahasa Melayu. Give it a subject line, put the deadline in one bold sentence, and add three bullet points: what to attach, what happens if a claim is late or incomplete, and who to contact.

What you typically get back

A short notice you can check in ten seconds: subject line, one bold rule, three bullets, under 120 words. It usually needs a light edit, not a rewrite.

Build your own AIM prompt

Your turn. Choose a scenario, pick an Actor, tick the Inputs you would include, then choose a Mission. Watch the prompt build itself and the score change. Try the weak options too: seeing the score drop is the fastest way to feel why each part matters.

Interactive

Build an AIM prompt

Pick a scenario, then tap one Actor, two or more Inputs and one Mission.

ActorWho should the AI be?
InputWhat does it need to know? Tick all that apply.
MissionWhat exactly should it produce?
Your prompt
Choose an Actor, some Inputs and a Mission to assemble your prompt.

0/5

Prompt strength

Keep going

  • Specific actor (not "a helpful assistant")
  • At least two pieces of context
  • A clear mission
  • Output format is specified
  • Starts with a precise action verb

AIM for AI agents

A chat app answers once. An AI agent plans, opens files, uses tools and takes several steps on its own, like a new staff member working through a job sheet. That makes AIM even more important, because a misunderstanding at step one repeats at every step after it.

When you brief an agent, add three things to the Mission:

  • Done criteria: “you are finished when all 40 files appear in the table”.
  • CheckpointA planned pause where the AI shows its work and waits for your OK.: “show me the first 5 rows before you continue”.
  • Limits: “do not email anyone; save drafts only”.
AIM brief for an AI agent
You are a careful assistant to a district unity officer who checks KRT activity reports against a checklist.

The folder "Activity reports October" contains 40 anonymised reports named K01 to K40. Names and phone numbers have been removed. Each report should have a date, an activity type, an attendance count and at least one photo caption. Use only these files.

Open every report and save a table with the columns File, Complete (Yes / No / Partly) and Missing (the items that are missing, or "none"). Stop after the first 5 files and show me the table so I can check you are reading them correctly. If a file will not open, write "Could not read" instead of guessing. Do not contact any KRT and do not change the files.

The agent can save that table as a CSV fileA simple spreadsheet file Excel or Google Sheets can open. that opens in Excel. Our guide on work activities shows how to describe a job like this one step by step, from the input to the decision at the end.

For developers: technical detailsOptional: skip this if you only use the chat app

If you call a model through an APIA way for software to talk to an AI directly, without the chat app. Developers use it to build AI into their own systems., AIM maps neatly onto the request:

  • Actor usually goes in the System promptStanding instructions set up before the conversation starts, such as "always answer in Bahasa Melayu". They apply to every reply., so it applies to every turn.
  • Input goes in the user message. Wrap pasted material in clear labels such as <notes>…</notes> so the model can tell instructions from material.
  • Mission goes at the end of the user message, after the material, so it is the last thing the model reads.
  • For agents, put done criteria, checkpoints and limits in the task description or the project’s instruction file, and give the agent the narrowest file and tool access that does the job.

Common mistakes

  • Stacking roles. “You are a unity officer, a lawyer, a data analyst and a poet” blurs the view. Pick one, or ask for separate reviews from separate roles.
  • Burying the Mission. Put what you want at the start or the end, never in the middle of a long paragraph.
  • Forgetting the format. If you need a table, a list or 150 words, say so. Reformatting is wasted time.
  • Treating AIM as one message only. AIM is your opening order. Reply, correct and refine. The OODA guide shows how to work in short loops: look at the answer, judge it, decide and act again.

Check your understanding

Check yourself

AIM in five questions

Pick an answer, then tap Check answer. You can also use the arrow keys to move between answers.

Question 1 of 5: Which of these is the weakest Actor?

Nice work!

Lesson complete

You made it to the end. Take the quiz above if you have not yet, for bonus XP.

  • 0 XP
  • 0 day streak