Module 1 • Lesson 145 mins

What are AI and Models?

Distinguish traditional Rule-based software from Model-based AI systems, pattern learning from data, and trade-offs between determinism and adaptability.

Boundary between Rule-based and Model-based
Difference between AI (concept) and Model (engine)
Trade-off between determinism and adaptability

Distinguishing Rule-Based vs. Model-Based Mindsets in Product Design

The fundamental difference between traditional software and AI is the decision-making engine: hardcoded rules versus a trained predictive model. This choice directly determines UX, operating cost, and edge-case handling.

Example: E-commerce platform EcoCart - needing to automatically classify thousands of support tickets daily:

Two ways to build the same ticket classifier

Rule-based hardcodes the logic by hand. Model-based learns it from labeled examples.

RULE-BASED

Ticket
IF subject contains "FREE MONEY"
IF body contains "exchange" / "refund"
IF body contains "defective" / "won’t turn on"
Output: Spam / Customer Care / Warranty

Rule count as the product scales

10505005,000+
Rule explosion

MODEL-BASED

100,000 labeled tickets
Training
Learned patternsCo-occurrence frequency of phrasesEmotional toneSentence structure & send time
New ticket“Item received this morning does not match the image, please assist ASAP”
  • Product Return / Item Misrepresentation92%
  • Warranty5%
  • Spam3%
Rule-based hand-codes logic by hand (line by line if-else). Model-based learns logic from data - needing no code changes for new phrasing if patterns generalize.

1. Limits of Rule-Based Programming at Scale

Rule-based software runs on fixed if-else statements. Within defined rules, output is 100% consistent, but scaling reveals 3 limits:

  1. Rule evasion: Changing phrasing (e.g. "F.R.E.E M.O.N.E.Y") bypasses filters, forcing teams to continuously patch rules.
  2. Overlapping edge cases: A ticket carrying both warranty and return context easily triggers conflicting logic or misclassification.
  3. Exponential maintenance cost (Rule Explosion): Every new policy adds rules without being able to break existing ones.

2. The Core of Models: Learning Patterns from Data Instead of Fixed Instructions

A Model (AI Model) is trained on data to recognize patterns and make predictions on new input (Labeled dataset → Training → Learned patterns → Prediction). For EcoCart, instead of writing if-else, engineers feed the model 100,000 labeled tickets to learn autonomously.

Analogy: A Rule-based chef memorizes recipes (stalls on unfamiliar ingredients); a Model-based chef has cooked thousands of dishes (reasons out dishes from experience).

3. Disambiguating AI vs. Model in Solution Architecture

"AI" and "Model" are often used interchangeably:

  • AI: The high-level machine capability to perform tasks requiring intelligence (concept/expectation).
  • Model: The specific algorithmic engine that executes that capability (output of training on data).

When working with engineers, specify the concrete model rather than just saying "use AI" - the model is what incurs cost, latency, and accuracy constraints.

AI is the capability, the Model is the engine that runs it

An AI system in a product is always powered by one or more concrete models underneath.

AI

Concept / umbrella term

EcoCart example: “AI-Powered Customer Support Assistant”

PM focus: the product value it delivers to users

Model

Concrete execution engine

EcoCart example: the distilbert-ticket-classifier model

PM focus: cost, latency, and accuracy to track

When working with engineers, specify the concrete model rather than just saying “use AI” - the model is what incurs cost, latency, and accuracy constraints.

4. Trade-offs: Predictability vs. Adaptability

Moving from Rule-based to Model-based is an architectural and UX trade-off: The more adaptable to messy inputs, the less predictable the output.

  • Rule-based: Precise but brittle when conditions conflict.
  • Model-based: Always returns ranked probabilities even on messy input. However, models never refuse to answer, so low-confidence guesses can appear confident - requiring a confidence threshold and fallback plan.
  • Hybrid (Production Reality): Combine both - Model handles ambiguous inputs flexibly, Rule gates and blocks downstream risks.

The trade-off in one picture

More adaptability to messy input costs predictability of the output - and vice versa.

Predictability →Adaptability →Rule-basedHybridModel-based
  • Rule-based - 100% predictable, rigid on new phrasing
  • Hybrid - Model output, rule-gated before it ships
  • Model-based - Handles messy input, output is probabilistic
Rule-based sits high on predictability, low on adaptability. Model-based is the mirror image. A hybrid - model output gated by a rule or a human - is how most production features actually sit between the two.
FeatureRule-Based SoftwareModel-Based Product
DeterminismAbsolute. Same input always yields exact same outputNon-deterministic. Outputs are probabilistic predictions
ExplainabilityClear. Traceable to exact if-else code linesLow (Black box). Output is the aggregate of billions of parameters
Upfront CostLow. Write code logic directlyHigh. Requires data collection, labeling, and training infrastructure
ScalabilityPoor when facing complex dataHigh when processing unstructured data (text, images, audio)
ECOCART TRIAGE ENGINESIMULATOR
TICKET #4891

“FREE MONEY - claim your 100% discount right now!”

1. Rule-Based EngineDeterministic
IF subject IN ['FREE MONEY', '100%'] → SPAM
IF body IN ['refund', 'return'] → CSKH
IF body IN ['defective', 'power'] → WARRANTY
Verdict: SPAM
2. Model InferenceProbabilistic
Spam97%
Warranty2%
Refund1%
Inference: Spam
97% conf
PM TAKEAWAY

Clear input: Both Rule & Model succeed. Rule is cheaper and faster for obvious patterns.

Product Mindset Exercise: Classify the following 3 features in EcoCart as Rule-based or Model-based and justify briefly:

  1. Automated VAT & Shipping Fee Calculation: Applies exact tax rates by category and distance tiers according to published price tables. → Rule-based (Requires absolute precision, fixed legal logic).
  2. Cross-Sell Recommendations on Checkout: Analyzes purchasing behavior across millions of similar shoppers to display items likely bought next. → Model-based (Processes large pattern datasets with no fixed rules).
  3. Refund Button Activation Check: Verifies whether an order status is "Delivered" and within the 7-day return window. → Rule-based (Closed business logic check).

When evaluating a new product requirement, PMs need to ask 3 boundary questions to pick the technology. Toggle the options below to see the recommendations:

Would you pick Rule-based or Model-based?

Toggle each boundary question from the decision framework - watch the recommendation change.

Q1: Does the problem require 100% precision and legal compliance?

Q2: Is the input data structured or unstructured?

Q3: Is the Cost of Failure for a wrong prediction high or low?

RecommendationRule-Based, or Model-Based with Human-in-the-LoopUnstructured data but a high cost of failure → a human must approve before the system acts on its own.
Don't pick a model just because it's trendy: if a problem is solved well, cheaply, and durably with a few if-else lines, Rule-based is still the right call.