Kamus AI
Prompt
The instruction you write for an AI: what you want, for whom, from which material.
A good prompt answers our checklist: Goal, Reader, Material, Limits, Shape and Check, with examples when needed. Writing prompts is not a search for special words; it is like briefing a fast new colleague who knows nothing about your office yet. Prompts improve over a few rounds: try, read the result, clarify the part that missed. In InfraLoka Academy, the Indonesian word "perintah" on its own means a terminal command, so for AI we write prompt.
Also called: Prompt, instruction
Related terms
Appears in 88 lessons
- AI as a fast new colleague
- The request checklist: six parts
- Limits and shape: output you can use as is
- Improving the result over a few rounds
- From request to finished document
- Making a prototype to test an idea
- Choosing your next level
- Screening CVs with a rubric
- Prompts for job posts and screening
- Prompts for interviews and candidate communication
- Prompts for offers, onboarding and HR policy
- From the need to the shortlist
- From interviews to closing the round
- Building a safe recruiting kit
- Ready-to-use HR templates
- Prompt library: legal research and summaries
- Prompt library: contracts and documents
- Prompt library: compliance and communication
- New vendor case, part 1: facts and contract review
- Mini project: a PDP Law compliance starter kit for one process
- Legal and compliance template pack
- Patient communication templates
- Prompt library: administration and schedules
- Prompt library: SOPs and quality
- Prompt library: communication and general education
- A new service day, part 1: roster, slots and SOP
- A new service day, part 2: announcement, briefing and review
- Mini project: a clinic admin AI kit
- Clinic template pack
- Safety decisions stay with people
- Drafting fleet and dispatch plans
- Shift handover notes
- Following up with vendors and carriers
- Prompts for fleet plans and exceptions
- Prompts for SOPs and handovers
- Prompts for vendors and operations data
- Late route case, part 1: reading the delay data
- Late route case, part 2: from finding to SOP
- Mini project: a safe operations kit
- Ready-to-use logistics templates
- Bank and ledger reconciliation
- Monthly reports and their commentary
- Invoices and tax documents
- Prompts for reconciliation and verification
- Prompts for reports and commentary
- Prompts for invoices, tax and approval
- Month-end close, part 1: preparation and reconciliation
- Month-end close, part 2: report and approval
- Mini project: a safe finance work kit
- Ready-to-use finance templates
- Honest listing titles and descriptions
- Prompts for catalogues and listings
- Prompts for chat, complaints and reviews
- Prompts for pricing, stock and promotions
- Case: preparing Eid hampers
- Case: running and closing the season
- Project: a safe shop kit for one product
- Ready-to-use shop templates
- Question banks and rubrics
- Prompts for material and plans
- Prompts for assessment and feedback
- Prompts for communication and admin
- One teaching unit from start to reflection
- Project: a safe AI teaching kit for one unit
- Ready-to-use educator templates
- Official letters and announcements in language citizens understand
- Prompt library: letters, memos and announcements
- Prompt library: meetings, minutes and public input
- Prompt library: staff analyses, service templates and citizen complaints
- One service change, from data to announcement and FAQ
- Mini project: a communication kit for one of your agency's services
- AI features that read other people's text
- Prompts for plans and specifications
- Prompts for testing and debugging
- Prompts for review, migrations and releases
- Ready-to-use developer template pack
- An agent: model, tools and a loop
- When to use an agent, and how freely
- Reading an agent's trace
- Project: a team instruction file and permission rules
- Project: a ten-task test set for your agent
- MCP from the inside, and how to choose a server
- Skills as procedures
- Secrets out of the agent's reach
- Injection that arrives through data
- Layered fences
- The cost of one agent task
- Project: an agent with gates