Hagati amasomo · Ubuntu

Kubaka hamwe na sisitemu ya AI

Sobanukirwa nururimi rwicyitegererezo, kugarura, abakozi, gusuzuma, ikiguzi, hamwe nuburyo bwo kurinda ibicuruzwa ukoresheje igishushanyo mbonera cya sisitemu.

Kuri: Abiga tekinike n'abubatsi bakeneye sisitemu-urwego rwo guca imanza

Hagati
  1. Sisitemu y'icyitegererezo3 Kuyobora
  2. Impamvu hamwe no gushaka3 Kuyobora
  3. Intumwa n'ibikoresho2 Kuyobora
  4. Isuzuma n'ibikorwa2 Kuyobora
  • 4Module
  • 10Amasomo
  • ~8hKurangiza
  • 12Ubushobozi

Ibisubizo

Icyo uzashobora gukora

  • Choose an architecture based on task and evidence needs.
  • Evaluate quality, latency, cost, and safety together.
  • Design monitoring and incident response before launch.

Basabwe mbere: Urufatiro rwa AI, Ushinzwe gukoresha AI

Loading your course evidence…

Inyigisho

Amasomo

  1. Module 1

    Sisitemu y'icyitegererezo

    Ibisubizo: Reason about tokens, context, generation, and model tradeoffs.

    Imyitozo: Compare two model options using quality, latency, context, privacy, and cost.

    Language-model mechanicsIcyitegererezo, umwanzuro, n'imbibiIgiciro cyicyitegererezo no gucuruza ibikorwa
  2. Module 2

    Impamvu hamwe no gushaka

    Ibisubizo: Know when and how retrieval can improve evidence access.

    Imyitozo: Design a retrieval test set with answer and citation requirements.

    Kubona-ibisekuru byongereweInkomoko no gusaba kugenzura
  3. Module 3

    Intumwa n'ibikoresho

    Ibisubizo: Bound multi-step systems with permissions and checkpoints.

    Imyitozo: Write an agent permission model and failure-recovery path.

    Agents, tools, and long-running tasksAutomation boundaries and safeguardsAI security and misuse risk
  4. Module 4

    Isuzuma n'ibikorwa

    Ibisubizo: Measure system performance before and after deployment.

    Imyitozo: Create an evaluation suite covering quality, refusal, latency, cost, and regressions.

    Isuzuma n'ibipimo byo gusoma no kwandikaIntsinzi y'ibipimo no gukurikiranaIgisubizo cya AIIgishushanyo nigishushanyo mbonera

Ikoreshwa rya capstone

Isubiramo rya sisitemu ya AI

Produce an architecture and evaluation plan for a source-grounded AI application.

Urutonde rwibimenyetso

  • Architecture diagram
  • Evaluation dataset
  • Cost and latency budget
  • Security, monitoring, and rollback plan
Finished the path?Emera icyemezoTurn what you learned into a free, shareable certificate.