Intangiriro amasomo · Ubuntu
Ushinzwe gukoresha AI
Koresha AI kubyara umusaruro mugihe urinda ubuzima bwite, kugenzura ibisubizo, no kubungabunga ibyo abantu babazwa.
Kuri: Abanyeshuri, abakozi, abarema, hamwe nabakoresha AI burimunsi
- Kubaza hamwe n'imiterere2 Kuyobora
- Gusubiramo ibisubizo2 Kuyobora
- Ibanga hamwe na nyirubwite2 Kuyobora
- Akazi ko kwizerwa2 Kuyobora
- 4Module
- 8Amasomo
- ~5hKurangiza
- 10Ubushobozi
Ibisubizo
Icyo uzashobora gukora
- Design clear prompts with useful context and constraints.
- Review outputs for factual, privacy, bias, and copyright risks.
- Build a repeatable human-in-the-loop workflow.
Basabwe mbere: Urufatiro rwa AI
Loading your course evidence…
Inyigisho
Amasomo
- Module 1
Kubaza hamwe n'imiterere
Ibisubizo: Turn vague requests into testable instructions.
Imyitozo: Rewrite a weak prompt with audience, context, constraints, examples, and success criteria.
Prompt and context designLanguage-model mechanics - Module 2
Gusubiramo ibisubizo
Ibisubizo: Detect unsupported claims and decide what requires verification.
Imyitozo: Annotate an AI answer as verified, attributed, uncertain, or unsupported.
Output review and error detectionKubogama no kurenganuraInkomoko no gusaba kugenzura - Module 3
Ibanga hamwe na nyirubwite
Ibisubizo: Choose safe inputs and understand content rights.
Imyitozo: Create a red/yellow/green data policy for an AI workflow.
Amabanga no gukoresha amakuruCopyright and content provenance - Module 4
Akazi ko kwizerwa
Ibisubizo: Combine AI assistance with checkpoints and human ownership.
Imyitozo: Map an existing task and mark where AI may draft, check, or never decide.
Igishushanyo mbonera cya AIGuhitamo ibikoresho no kugereranyaAutomation boundaries and safeguards
Ikoreshwa rya capstone
Umuntu-muri-loop akazi
Design and test an AI-assisted workflow for a real recurring task.
Urutonde rwibimenyetso
- Before-and-after process
- Prompt or configuration
- Verification checklist
- Privacy and failure safeguards