Use Case Catalog
Twelve sub-categories. Around forty concrete use cases. One predictive database underneath.
Browse by capability. Each use case shows the outcome, the demo that showcases it best, the Aito operator(s) it uses, and the vertical(s) where it commonly lives. The catalog is the index β for code examples and full query patterns, follow the "Read more" link into the docs. For the live application, follow the demo tag.
What is a predictive application? Read the architectural argument β
Analyze
Find what's already in the data.
Pattern discovery, calibration, forecasting, segmentation. The decisions a user makes after seeing the data β and the patterns the data already contains.
Pattern Discovery
Co-occurrence, lift, persona-affinity, statistically discoverable AND predictive patterns. Find what's already in the data.
Pattern Explorer
Co-purchase lift and persona-affinity patterns ranked by statistical significance. Dog dry-food cross-sells to dental treats at 2.72Γ in the PetNord fixture.
Rule Mining
Statistical patterns (category=telecom & gl_code=6200 β approver=Timo, 15.8Γ lift) mined live. Promote to rules with audit trail; dismiss to record the decision.
Supplier Intelligence
Spend leaderboard plus delivery-risk discovery via _relate. "Supplier X Q4 lift 1.4Γ (33% late rate)" mined from the transaction history.
Lift Analysis
Conditional lift between any two attributes. "Customer segment X is NΓ more likely to buy in category Y." General-purpose statistical discovery primitive.
Quality & Calibration
Score your own predictions. Surface where the system can and cannot help.
Honest Evaluation
System scores its own predictions on held-out data. Return Risk reports +0.0 pp gain over baseline and renders as a red row β the system says when it cannot help.
Quality Dashboard
Per-field accuracy and per-confidence-bucket calibration on held-out samples. Green/red diff vs. always-predict-majority baseline.
Calibration Monitoring
ECE tracking over time. "When the system says 95% confident, the realized error rate matches." The property that makes confidence-tiered automation safe.
Forecasting
Predicted quantities at query time. No separate forecasting model to maintain.
Demand Forecast
_predict units_sold blended with seasonality factors from same-month historical data. Drives replenishment without a separate forecasting model.
Project Success Probability
_predict success per active project, with $why factor decomposition. Staffing simulator β swap a team member, watch P(success) move.
Utilization Forecast
Per-consultant load via _predict allocation_pct. Capacity planning that respects role and project mix without a separate forecasting model.
Price Estimation
Fair-price band via _estimate, flagged outliers, Purchase Price Variance with annualised exposure.
Segmentation
Discover groupings from behavior, not from hard-coded rules.
Customer Segmentation
Behavioral segments derived from purchase and engagement history. No pre-labeled training set; segments emerge from co-occurrence in the data.
Persona Detection
Derived persona affinity from purchase history. Same shopper, persona-conditioned ranking changes downstream search and recommendations.
Assist
Suggest the next best action β with calibrated confidence.
Search, recommendations, smart forms, conversational. The human stays in control; the system boosts speed and accuracy.
Search & Discovery
Personalized ranking. Match similar items. Find what the visitor is actually looking for.
Smart Search
Persona-conditioned re-ranking. Same query returns different rankings for different shopper segments β derived from the data, not from a curated rule.
Match Similar
Find products, tickets, or records similar to a given one via column-distribution similarity. Catalog matching without an embedding model.
Recommendations
Cross-sell, similar items, bought-together, for-you. All from the same _recommend operator.
Bought Together
Cross-sell ranked by co-purchase lift. Mined live from order data β not from a curated rule.
For You
Personalized tile rankings per shopper. Same query different per-customer; reranking from purchase, browse, and segment history.
Win-back Ranking
Lapsed customers ranked by predicted recoverable revenue. Drives outreach prioritization with empirical ROI per cohort.
Similar Items
Vector-style item similarity without a vector index. Use _relate over catalog attributes to find nearest neighbors in attribute space.
Smart Forms
Multi-field prediction wired into input UI. One field in, the rest predict.
Smart Form Fill
Type any field, the rest predict. Vendor β fills GL, approver, cost centre, VAT %. The form does the thinking, the user confirms.
Smart Entry
Pick a supplier and four fields predict in parallel β cost center, account code, project, approver. Tab to accept, Esc to reject.
Cart Autofill
One click prefills the basket with the customer's predicted weekly purchases. Used in grocery; same pattern works for B2B reorder flows.
Smart Autocomplete
Predict text completions from user history and corpus patterns. Lower-cost than an LLM and conditioned on actual usage.
Conversational
Natural language interfaces backed by predictions, not by an LLM-only stack.
AI Assistant
Conversational shopping or support interface backed by predicted product/answer rankings. The LLM frames; the predictive database decides.
Question Answering
Predict canonical answers from a prompt corpus. Question-shaped input, predicted-answer output, calibrated confidence to decide auto-vs-route-to-human.
Help Drawer
In-app help articles ranked by _recommend against click history (CTR-ranked, like product recommendations). Users read what other users with similar queries clicked.
Automate
Put predictions into the workflow β auto, review, manual tiers.
Categorization, routing, anomaly detection, multi-field prediction, optimization. Calibrated confidence decides what auto-processes and what routes to human review.
Categorization & Routing
The decisions where the user picks from a menu and the right pick is statistically determined by surrounding fields.
PO Queue Routing
Every purchase order arrives with predicted account code, cost center, and approver β three confidence tiers, bulk-approve for rule-matched rows.
GL Coding
Predicted GL code, approver, payment method, cost center per invoice with $why factor decomposition. The core of predictive AP.
Ticket Classification
Auto-route tickets via _predict on description. Confidence-tiered β high auto-routes, mid suggests, low routes to manual.
Tag Prediction
Auto-classify content (products, tickets, documents) into a multi-label taxonomy. Saves manual labeling effort with calibrated confidence per tag.
Approver Routing
Predict the right approver from invoice or PO content. Same pattern as GL coding, applied to the person dimension instead of the account dimension.
Anomaly Detection
Inverse prediction β low confidence on a normally-predictable field is the anomaly.
Inverse Prediction Anomaly
If the actual GL or routing isn't in the predicted top-3, the row is flagged for review. The system surfaces what it didn't expect.
Amount-Spike Detection
An invoice or PO amount that's an order of magnitude off the supplier-and-category norm. Surfaced before posting.
Unknown-Vendor Detection
A vendor without prior history triggers the no-prediction-yet path. Visible flag at the PO entry point.
Multi-field Prediction
One query, several predicted fields. The same pattern that powers smart forms, applied to bulk data fill.
Catalog Gap Fill
Predict category, HS code, unit price one-shot across workflow-blocking products. Smart-forms pattern applied to data instead of input UI.
Product Filling
Predicted product attributes β title, category, weight, dietary tags β for new SKUs entering the catalog. Multi-field, multi-output.
Optimization & Triggers
Predicted thresholds that drive auto-action. Predicted ranking that drives outreach order.
Markdown Decisions
_estimate across discount levels picks the level where predicted demand recovers cost. Auto-trigger above a confidence threshold.
Win-back Triggers
Auto-fire campaign at the confidence threshold where predicted recoverable revenue exceeds outreach cost. Combines _predict and _estimate.
Churn-ranked Outreach
Predict churn probability, route the top-N to retention. The retention team works the highest-leverage queue first.
Address
Episto Oy
Putouskuja 6 a 2
01600 Vantaa
Finland
VAT ID FI34337429
