---
name: tbt-ai-troubleshooting-decision-tree
description: "Translate approved rules into testable branches and leave unsupported routes unresolved for Build a source-grounded troubleshooting decision tree with AI. Use permitted source material; this kit does not authorise external actions."
---

# Build a source-grounded troubleshooting decision tree with AI

Translate approved rules into testable branches and leave unsupported routes unresolved.

Use the supplied source as authority. Check the account supports the actual file or image operation before attempting it.

## Task instruction

Build a troubleshooting decision tree from these approved rules only.
For each node, include the question, allowed action, source rule ID and
stop/escalation boundary. Preserve missing-source and failed-check paths.
Leave unsupported cases unresolved with a focused question.
Do not invent resets, external writes, integrations or account controls.
Provide editable source/file, readable path list and a few cases that
should expose a missing or incorrect branch.

## Source boundaries

- File readable?
- Units and keys resolved?
- Known-answer case passes?

## Review and correction

Each failure should lead to a focused input or method repair, not another vague request to try harder.

Branch [ID] continues after [stop condition], but rule [ID] says [exact
boundary]. Restore the stop/escalation path and update the text path
list. Keep confirmed branches unchanged. Repeat the awkward case and
state what was actually checked. Do not invent a workaround or claim
the real system was repaired because the local diagram now looks right.

Use references/practice-source.json for the labelled example. The practice HTML is a local teaching tool; it does not call an AI service. Apply this method to the user's supplied facts rather than copying fictional example values. Do not infer approval or permission to publish.