Open · structured · practical
Search 中文 Find your starting point

AI VISTA COURSES

Build an AI workflow step by step, like taking a real course.

Choose a course and follow its syllabus in order. Every lesson has one problem, one working output, and a saved completion state so you can resume later.

4complete courses19sequenced lessons1real task to begin
LEARNING ARC / FOUR COURSESFROM TASK TO SAFE OPERATION
RECOMMENDED SEQUENCEEnter where your problem begins
01 4 lessonsBuild your first testable AI workflow 02 6 lessonsMake AI answers reliable enough to use 03 2 lessonsDesign answers that can show their evidence 04 7 lessonsAutomate with permission, recovery, and cost controls
EVERY COURSE LEAVES YOU WITH
01A syllabus
02Working artifacts
03Acceptance checks

LEARNING ROUTE / STAGE 03 · COURSES

This stage is not article browsing. It is continuous practice through a syllabus.

Each course follows one complete job, and later lessons reuse decisions or artifacts from earlier ones. Once you choose a course, following the syllabus produces a more reviewable result than scattered reading.

BRING
The task direction found in the decision map
DO HERE
Complete decisions and outputs lesson by lesson
LEAVE WITH
A connected set of reviewable artifacts
WHEN THIS STAGE IS DONE Read for a specific gap Use the reading list when a branch needs more depth.

CHOOSE THE RIGHT COURSE

Choose by the problem in front of you—not by beginner or advanced labels.

The four courses are not isolated knowledge tracks. They address task fit, output reliability, evidence, and controlled automation.

IF YOU ARE SEEINGSTART WITHDONE WHEN
01
You are turning a repeated knowledge task into a first AI workflow
Build your first testable AI workflow

Another person can run the pilot and reach the same pass/fail decision.

↗02
The prompt looks good in a demo but varies across real inputs
Make AI answers reliable enough to use

Each failed case is assigned to a fixable category instead of a vague quality complaint.

↗03
Answers must cite evidence that is traceable and current
Design answers that can show their evidence

A reviewer can trace every important answer claim to a current, permitted source.

↗04
An agent is about to use tools, write to systems, or change external state
Automate with permission, recovery, and cost controls

Every automated action has an owner, approval rule, observable result, and recovery path.

↗

HOW EACH COURSE WORKS

A lesson is not an article you finish. It is a small read, make, review, continue loop.

All four courses use the same learning actions on different problems. Bring one real task, move one decision per lesson, and let the artifacts assemble into one workflow.

  1. 01
    READ

    Identify the one decision this lesson changes

    Compare the case and boundary with real work; do not try to memorize every term.

    DONE SIGNAL · You can state the decision in one sentence.
    →
  2. 02
    MAKE

    Replace the blank tool with your own material

    Use current inputs, criteria, owners, and failure handling instead of copying the example.

    DONE SIGNAL · The artifact contains real fields, cases, or constraints.
    →
  3. 03
    REVIEW

    Ask a second person to apply the same standard

    Offer no verbal explanation. Let the reviewer decide pass, revise, or stop from the artifact alone.

    DONE SIGNAL · Disagreement becomes a named issue for the next iteration.
    →
  4. 04
    CONTINUE

    Carry the artifact into the next lesson

    Keep the same task. Open the reading list only when practice exposes a precise gap.

    DONE SIGNAL · The syllabus shows connected changes, not scattered notes.
    ✓

CHOOSE A COURSE

Start with the problem already on your desk.

Every course has a continuous syllabus, working artifacts, and a clear finish line.

60–90 minutes4 lessons

Build your first testable AI workflow

Move from an attractive idea to a bounded task, a one-page brief, and a ten-case pilot you can review with another person before investing further.

01Should this task use AI at all?02Turn an AI idea into a testable task brief03Draw the data boundary before AI sees the input
FOR
For anyone turning a repeated knowledge task into a first AI-assisted workflow.
OUTCOME
A task brief and a ten-case pilot sheet.
COURSE PROGRESS0 / 4
View syllabusStart course →
2 hours6 lessons

Make AI answers reliable enough to use

Expose the context, define acceptance, test difficult cases, and diagnose whether failures come from input, evidence, instructions, capability, or handoff.

01Map the context before rewriting the prompt02Write the acceptance contract before the prompt03Run a ten-case AI pilot before you scale
FOR
For teams whose prompt works in a demo but changes quality across real inputs.
OUTCOME
A context map, acceptance contract, and failure log.
COURSE PROGRESS0 / 6
View syllabusStart course →
75 minutes2 lessons

Design answers that can show their evidence

Decide whether retrieval is necessary, then test source support, version, access, freshness, and no-answer behavior before building a maintenance-heavy system.

01Decide whether RAG is worth building02Test citations for support and freshness
FOR
For knowledge assistants, policy search, support systems, and internal research workflows.
OUTCOME
A RAG decision and a citation audit sheet.
COURSE PROGRESS0 / 2
View syllabusStart course →
2–3 hours7 lessons

Automate with permission, recovery, and cost controls

Set the authority boundary, prepare failure recovery, choose a model with real cases, and calculate the full operating cost before automation reaches production.

01Draw the data boundary before AI sees the input02Give an agent the smallest useful permission03Put human review where it can change the outcome
FOR
For teams moving an agent or tool-using workflow from prototype toward production.
OUTCOME
A permission ladder, recovery runbook, model scorecard, and cost map.
COURSE PROGRESS0 / 7
View syllabusStart course →