Practical notes from the engineers who build agents, copilots and AI products.
Modernize in phases with no changes during exams or fees, parallel runs for admissions and tests before every cutover. Education ERP modernization succeeds when the plan is drawn on the academic calendar first: replace the old system module by module, keep the data, and never cut over in a week that matters.
Track active users, tasks completed in-system, workarounds still in spreadsheets and support tickets at 30, 60 and 90 days. Those four software adoption metrics, read by role and by site, tell you whether the platform is doing the work it was bought for, and each review should end with three fixes rather than a slide.
Sellers use AI for listing copy, price monitoring, review responses and support across marketplaces from one system. The value is in the "one system" part: a catalogue of record that pushes listings to each marketplace, pricing rules with floors the seller owns, and a support agent that sees orders on every channel.
Marketplaces succeed on supply onboarding, payments and settlement, trust and disputes; the storefront is the easy part. Budget most of the build for the seller side, the ledger and operations tools, and treat the buyer app as the thin layer it is. Here is what the plumbing contains, what it costs and who builds it.
Logistics ERP centres on order intake, dispatch, fleet, proof of delivery, cash reconciliation and seller settlements. The build order matters: get order intake and dispatch working with a driver app first, because proof of delivery and cash data from the field are what make reconciliation and settlements possible.
Use ML for prediction, classification and detection on structured data; use LLMs for language; many systems need both. The LLM vs machine learning choice comes down to the shape of the input, the cost of a wrong answer, the volume of decisions and the budget per decision; most production systems route between the two.
Modernize around the academic calendar: no changes during exams or fee windows, parallel runs for admissions, tests before every cutover. Keep the system the institution runs on, wrap it with an API, replace one module per quiet period, and put the registrar, finance office and exam cell in charge of every go/no-go.
Minors' data needs verifiable consent, strict access scopes, retention limits and grounded AI that cannot free-associate. Student data privacy for AI is an engineering problem as much as a legal one: consent checked at query time, access scoped per role, retention run by the system, answers traceable to sources.
Every question the agent cannot answer becomes a ranked list of help-centre gaps, turning failures into content work. The report clusters unanswered and escalated questions by topic, ranks them by volume and cost, and assigns each to an owner, so the help centre improves weekly instead of when someone remembers.