Searchable workflow library
Find copy-ready prompts for Codex, ChatGPT, Claude, Gemini, and practical AI workflows. Filter by outcome, category, tool, difficulty, or keyword.
Implement a bounded AI-assisted support-triage integration in a sandbox or shadow environment, with abstention, grounded drafting, routing, injection tests, manual fallback, and disablement evidence.
Convert an approved n8n blueprint into a disabled importable workflow or staging implementation, with node-level traceability, synthetic execution evidence, retry tests, and rollback instructions.
Implement a repeatable KPI-reporting process from approved metric definitions, with traceable calculations, authoritative reconciliation, failure and rerun tests, disabled delivery, and recovery evidence.
Implement and verify CRM lead capture, consent, deduplication, qualification, routing, and SLA behavior in an authorized sandbox using synthetic test leads and disabled production activation.
Implement an internal operations dashboard from approved metric contracts, with source reconciliation, enforced access rules, observable data states, performance evidence, and a reversible release handoff.
Reconcile teaching, research and administrative AI initiatives against mission outcomes, cost, risk, duplication, inclusion and evidence quality for a bounded portfolio decision.
Compare a programme with dated primary standards, credible research and labour evidence to separate durable AI competencies from short-lived vendor fashion.
Evaluate an educational AI purchase against learning need, evidence, accessibility, privacy, security, equity, retention, lock-in and total cost before an accountable decision.
Translate supplied university AI policy into traceable role-specific rules, evidence requirements, escalation routes and fair appeals without inventing institutional authority.
Test whether a student AI prototype has documented users, data rights, evaluation evidence, limitations, risks and a safe accountable owner before demonstration or reuse.
Cross-check hypotheses, outcomes, exclusions, power assumptions, models, multiplicity controls and decision rules before data inspection, with deviations made explicit.
Test whether a research question can be answered with the proposed design, population, variables, data and estimand, separating repairable gaps from fatal limitations.