Intake targets, compliance deadlines and struggling students are reviewed once a semester, which is too late to act on any of them. Counsellors and programme heads get early warnings weekly, and leadership sees enrolment and accreditation risks in time to respond.
Admissions & FeesProgrammes & AccreditationLecturer WorkloadClassrooms & LabsStudent Support
A worked example for a typical Malaysian Private University & College Group, not a description of any real company. Go through the six stages in order: paste each prompt into Claude, check the answer against how your business really works, then continue. Change the profile at the start to match yours.
Stage 1 of 6
Map how the operation really runs
Act as an operations consultant. I run a Private University & College Group in Malaysia. Profile: A Malaysian private education group — three campuses, ~15,000 students, 60+ programmes, regulated by MQA and the Ministry of Higher Education.
Interview me, one question at a time, to map how decisions actually get made today. Cover: the recurring meetings and reports, who decides what, which numbers people trust, and where decisions are late or made on gut feel.
Known friction: More students vs. Smaller classes; Affordable fees vs. Good facilities; Research time vs. Teaching hours; Spare rooms vs. Running costs; Rules vs. Moving fast.
After 8 to 10 questions, summarise the five decisions that cost us the most when made late, in a table: decision, current owner, current delay, cost of delay.
Stage 2 of 6
Design the specialist agents
Using the decision map above, design 5 specialist AI agents for our Private University & College Group: Admissions, Accreditation, Lecturer Load, Campus Space, Student Support.
For each agent give: the one question it answers every day, the data it reads, what it may recommend, what it must never do alone, and the format of its output.
Starting points for what each should watch:
- Admissions: enquiry-to-enrolment conversion, scholarship yield, agent-channel quality
- Accreditation: MQA accreditation milestones, curriculum gaps, industry-demand fit
- Lecturer Load: teaching loads, adjunct needs, research-time protection
- Campus Space: room and lab utilisation, maintenance backlog, energy spend
- Student Support: attendance, LMS activity and grade trends that signal drop-out risk
Keep every agent narrow. If an agent covers two jobs, split it.
Stage 3 of 6
Wire up data and compliance
For the agents above, list the data feeds needed. Likely systems: Student information system; LMS activity logs; CRM for enquiries and agents; HR and timetable systems.
Output a table per agent: field, source, how often it refreshes, data-quality risk, and what the agent should do if the feed is stale or missing. Mark every personal-data field and say how to minimise it.
Rules we operate under: MQA and MOHE requirements, PDPA 2010 for student records (including minors), and the institution's own academic-integrity rules. Student-level flags go to counsellors, never to automated action.
End with a short list of actions that always need human sign-off.
Stage 4 of 6
Design the morning brief
Design the single daily brief that pulls the 5 agents together for the Vice-Chancellor, ready before the first meeting of the day.
Specify how the brief merges overlapping or conflicting recommendations, how it ranks items (impact, urgency, reversibility, confidence), and the exact fields per item: what to decide, recommended action, evidence, owner, deadline, and the cost of doing nothing.
Then write a realistic sample brief of five items. Items might resemble: Open one extra intake for the Computing foundation — enquiries are 28% above forecast / Assign counsellor outreach to 41 students with falling attendance / Defer lab refurbishment: utilisation is 38% in Block C.
Stage 5 of 6
Build and automate it
Turn the design into a working automation for our Private University & College Group.
Needs: a scheduled daily run; the 5 agents run in parallel and each saves structured JSON; a final step reads them all and sends the brief by email or chat; every run is logged with inputs, outputs and cost.
Propose the build with Claude plus a workflow tool (for example n8n or the Claude Agent SDK). Give the steps in order, what happens when a data feed fails, and a human-approval step before anything that spends money or makes a customer commitment.
Stage 6 of 6
Roll out and measure
Write a rollout plan for the Private University & College Group agent team that starts small and earns trust.
Stage 1: one agent, advisory only, run alongside the current process. Stage 2: add the other agents. Stage 3: switch on the daily brief. Stage 4: let agents prepare low-risk actions for approval.
For each stage give duration, owners, what "ready to move on" means, and the metrics to track: time to decision, how often recommendations are accepted, hours saved, and errors caught. Close with the three biggest risks and how we contain them.
