01 — Taxonomy & When to Use — select a category to explore
01.A
Large Language Models
Systems that generate, reason over, or transform natural language using foundation models. Probabilistic by nature — output varies, requires calibration, and cannot be fully predicted.
01.B
Machine Learning
Models trained on historical data to predict, classify, or rank. Deterministic at inference time. Requires labeled data and degrades when distribution shifts.
01.C
Automation
Rule-based logic that executes defined sequences without inference. Predictable, auditable, zero ambiguity. Commonly misattributed to AI.
01.D
UX Debt
Friction that appears to be an AI problem but is a design or information architecture problem. Adding AI here treats symptoms, not cause.
02 — Cost of Misclassification
LLM — if misapplied
Calling automation or ML "AI-powered" sets expectations of reasoning the system can't meet. Users attempt edge cases it can't handle. Trust erodes faster than it was built.
Using an LLM for something deterministic burns tokens on every call. At scale that's a real line item — you're paying inference cost for a lookup that should be a query.
Primary failure: Expectation gap → trust collapse + unnecessary compute cost
ML — if misapplied
Using an LLM where a trained model is needed introduces unpredictability into decisions that require consistency. Risk scores that vary by phrasing are not risk scores — they're opinions.
You're also paying for variability you didn't want. A trained model runs inference cheaply and consistently. An LLM doing the same job costs more per call and produces less stable output.
Primary failure: Inconsistency → liability + inflated inference cost
Automation — if misapplied
Labeling rule-based logic as AI inflates perceived value short term. When users discover the system is a conditional, not a model, they recalibrate downward — and take other AI claims with them.
Teams build LLM scaffolding around something that should be an if/then statement. That's weeks of work and ongoing maintenance on a problem that didn't need a model.
Primary failure: Credibility debt + over-engineering cost
UX Debt — if ignored
Layering AI onto unresolved structural problems compounds complexity. Every AI interaction that fails because the underlying IA is broken trains users to distrust AI rather than the design decision that preceded it.
You've now funded two problems instead of one. The IA still needs fixing, and you've added an AI layer that will need its own maintenance and iteration — on top of a foundation that was never sound.
Primary failure: Compounding confusion + compounding cost
02 — Anti-Patterns
| What was said | What it actually was | Why it matters | Correct label |
|---|---|---|---|
| "AI-powered notifications" | Scheduled sends triggered by user actions — no model involved | Positions a deterministic feature as intelligent. When the notification misfires, users blame the AI rather than the rule. | Automation |
| "Smart search" | Keyword matching on a poorly structured data model | Solving a findability problem with a search label doesn't fix the underlying IA. Adding "smart" adds expectation without capability. | UX Debt |
| "AI recommendations" | A ranked list sorted by a static scoring formula last updated 18 months ago | Static ranking presented as adaptive intelligence. Users adjust behavior expecting the system to learn — it doesn't. Misplaced trust. | Automation |
| "Use AI to explain the dashboard" | Too many unlabeled metrics, no clear hierarchy | An LLM narrating a confusing UI doesn't make it less confusing. It adds a layer of text to a layout problem. | UX Debt |
| "Add AI to generate buyer insights" | LLM request without defining what a good output contains or what decision it supports | LLMs produce output that matches the shape of the request. Without a defined output standard, the feature ships as plausible-sounding text with no evaluable quality. Prompt design is a design problem, not an engineering one. | LLM |
03 — Human Decision Governance
LLM
Output is probabilistic. Human review required before any external send or irreversible action.
ML
Predictions affect decisions. Human required when scores influence risk classification or financial outcome.
Automation
Deterministic by definition. Human decision required at rule-authoring time, not execution time.
UX Debt
No AI governance applicable. Requires a design decision, not an oversight model.
Requires human decision
- —Any output that affects a financial transaction or commitment
- —Content that will be sent externally under the user's name
- —Recommendations that affect risk classification of a record
- —Actions that are irreversible or difficult to audit after the fact
- —Conflicts between model output and user-provided context
AI may act autonomously
- —Drafting, summarizing, or reformatting — when output is reviewable before use
- —Sorting, ranking, filtering within a clearly defined and auditable ruleset
- —Surfacing suggestions when the user retains explicit accept/reject control
- —Routine automation with full audit trail available
- —Low-stakes personalization with an accessible override
Before shipping any LLM feature — define the output
What signals matter
Which data inputs should shape the output? Outputs are only as good as the inputs they're allowed to use.
What decision it supports
What should the user be able to do after reading this that they couldn't before?
What a bad output looks like
Define what bad looks like before launch — not after users start ignoring the feature.
Who owns the definition
Prompt design is a design problem, not an engineering one. Set criteria before implementation begins.