Skip to main content

Operations Process — Who Does What When

This document covers how to run the AI stack in your organization. AI is not 「install it and it runs itself」— it needs people to feed in material and judge the results to become useful.

Different from the tutorial

The tutorial is 「get your first answer from one document」. This document is 「keep it useful over time」.


Roles

RoleAccountResponsibilities
AI OperatorAdmin console account (env)Service status · document indexing · pipeline management
Field UserPlatform account systemAsk the chatbot and judge answers
System AdministratorServer accessInstallation · key rotation · backups

The console account is one shared by the teamChange initial password.


Full workflow

Where arrows cross swimlanes, that's a handoff point.

This loop is the core

현장 피드백 → 문서 보강 → 재색인 If it doesn't run, AI stalls at the level of documents you loaded initially. Set up a channel to collect feedback — most loops break because there's nowhere to send it.


1. Onboarding — Until it becomes useful

StepTaskOwner
1Install → One-line installSystem Administrator
2Set up console account & keys → Change initial passwordSystem Administrator
3Check overall status green from home → Admin consoleAI Operator
4Choose which documents to loadAI Operator + Field
5Index documents + validate with Query TestAI Operator
6Release to field
Step 4 decides success

Loading many documents at random doesn't help. Start with what the field actually asks about often — equipment manuals, work standards, troubleshooting history, in that order. Old documents teach the chatbot to answer wrong with confidence.


2. Operations — Regular tasks

FrequencyTaskOwner
DailyHome status summary (outages = 0?)AI Operator
WeeklyPipeline status · execution historyAI Operator
WeeklyGPU utilization · XID, LLM response time (P95)AI Operator
MonthlyRe-index new document versions, collect wrong-answer casesAI Operator + Field
QuarterlyKey rotation → Change password & API keysSystem Administrator

Everything is viewable in the admin console.

If XID is not 0, report immediately

GPU hardware or driver error. Even if it's running now, the next symptom is usually node failure.


3. When an answer is wrong — Where to fix it

「The chatbot gave a bad answer」has multiple layers. Narrow it down in this order.

CheckIf true, then
1. Is the source document indexed?No → add the document (Documents)
2. Does search find it?No → try different search modes (hybrid/local/…) (Query Test)
3. Search finds it but answer is wrong?The source document is probably outdated — update it
4. Answer is slow or cuts off?LLM or GPU issue → check LLM and GPU screens
Suspect the material before the model

Most complaints from the field that 「AI is dumb」are really missing or outdated documents.


Common failure points

SymptomUsual cause
「We rolled it out but nobody uses it」Field questions don't match loaded documents
「The analytics screen is empty」Feature pipeline is stuck — check pipeline, not the model
「It confidently gives wrong answers」Old documents still in the index
「It got slow」GPU contention or LLM queue — check P95