Open · structured · practical
Search 中文 Find your starting point

DECISION MAP / SIX CRITICAL CHOICES

Name the symptom. Find the decision underneath.

Do not start with a tool name or trend. Locate the layer where the job is stuck, then leave with a decision tool you can use.

Start with a symptom ↓Follow a complete course →
AI VISTA / ROUTING SHEET01—03
SYMPTOMLAYERARTIFACT
  1. 01Should this task use AI?→Task framing→Fit matrix
  2. 02Why is the answer unstable?→Context / evaluation→Failure tree
  3. 03How far may automation go?→Agent safety→Permission ladder
?ENTER BY QUESTION
INPUTDECISIONARTIFACTNO GLOSSARY ROUTES

LEARNING ROUTE / STAGE 02 · DECISIONS

This stage turns a vague symptom into a question you can learn and test.

You do not need a model name, technical term, or course title. Describe where the work gets stuck and the map routes you to the most relevant decision.

BRING
The clearest symptom in one real job
DO HERE
Locate the earliest decision layer
LEAVE WITH
A topic entry and a course direction
WHEN THIS STAGE IS DONE Continue to courses Choose the syllabus closest to the problem.

WHAT ARE YOU SEEING?

Choose the nearest symptom first.

One job may cross several topics. Begin with the earliest issue that can still change the downstream result.

01You have not decided whether AI belongs3 practical guidesWhat exactly should AI do—and should it do it at all?→02Output quality changes across inputs2 practical guidesWhat must the model see to produce an acceptable answer?→03You cannot locate the failing layer3 practical guidesWhat evidence would make this workflow safe to expand?→04Answers must show evidence2 practical guidesWhen does external evidence improve the answer enough to justify a retrieval system?→05An agent will change external state3 practical guidesHow much authority can this agent safely hold?→06You need a model and a cost boundary3 practical guidesWhich model makes this workflow dependable and affordable in operation?→

HOW ONE JOB MOVES THROUGH THE MAP

One support-routing workflow creates four different decisions in sequence.

The map does not assign a permanent category. It finds the earliest decision worth resolving now. If that decision stays vague, evaluation and automation inherit the wrong assumptions.

AI VISTA / WORKED ROUTEEXAMPLE: ROUTE SUPPORT EMAILS
  1. 01
    Task framing

    Set the task boundary first

    Classify support emails, but never reply. Low-confidence cases must go to the support lead.

    ↗
  2. 02
    Context and prompts

    List what the model must see

    Provide only the email, approved queue definitions, and urgency rules—not unrelated customer data.

    ↗
  3. 03
    Evaluation

    Test whether it actually works

    Use ordinary, ambiguous, cross-queue, and high-risk emails; record the label, reason, confidence, and human override.

    ↗
  4. 04
    Agent safety

    Decide how far automation may act

    Begin with suggestions only. Consider automatic routing only after acceptance passes, with recall and human takeover.

    ↗
RULE OF USE

Stop at the earliest unresolved step. Produce that topic’s artifact before deciding whether to move deeper.

SIX PROBLEMS / FIELD REFERENCE

Start from a signal, prepare enough evidence, then enter the matching course.

This is not a maturity score. It identifies the earliest unresolved decision and makes clear what to bring and what to produce before moving on.

SIGNALEVIDENCE TO BRINGARTIFACT TO LEAVENEXT COURSE
  1. 01
    Task framingThe goal is still ‘improve efficiency’ and no exact AI action is named ↗

    Current human steps, real inputs, and failure consequences

    Fit matrix and one-page task briefOpen course →
  2. 02
    Context and promptsThe same prompt omits fields or resolves conflicts differently across inputs ↗

    Complete input, source precedence, and required output fields

    Context-flow map and acceptance contractOpen course →
  3. 03
    EvaluationThe team can only say output is ‘mostly fine’ and cannot isolate failing cases ↗

    Real task slices, failure labels, and severity

    Evaluation-set blueprint and diagnostic treeOpen course →
  4. 04
    Grounded answersConsequential answers need evidence, but citations may not support the claim or may be stale ↗

    Authoritative sources, version, effective date, and access scope

    RAG decision gate and citation-freshness auditOpen course →
  5. 05
    Agent safetyThe system is about to write, notify, pay, or change external state ↗

    Actions, reversibility, owners, and failure states

    Permission ladder, human gates, and recovery runbookOpen course →
  6. 06
    Model operationsModel choice relies on a leaderboard and unit price while operating cost is unknown ↗

    Task cases, quality floor, latency, retries, and human cost

    Model scorecard, cost map, and drift watchboardOpen course →

A USEFUL BOUNDARY

First check whether the problem needs a system at all.

If one deterministic fact is missing, look it up first. Move to a more complex path only when the job needs judgment, context, or a sequence of actions.

THREE QUICK CHECKS01—03
  1. 01
    Look it up firstIs the answer already in a reliable source?
    →
  2. 02
    Check the variationDoes changing input require ongoing judgment?
    →
  3. 03
    Set the boundaryCan the work stop and hand off when it fails?
    ✓
Search published guides↗