Make better decisions
What information, capacity and protection do I need?
Explore the topics
6 subject areas, 23 guides and 20 interactive tools. Explore a specific question or follow a learning path, from basic ideas to decisions in practice.
Find your starting point
Start with a question. Each guide stands on its own; the order is a suggestion, with no account or required steps.
What information, capacity and protection do I need?
Is the difference reliable, and what causes it?
How do examples and feedback become a strategy?
How do attention, sources and verifiable rules fit together?
23 articles
No matches. Try a broader term or select all subject areas.
5 articles
Learn from data without hiding uncertainty: prior, likelihood and posterior, and what they mean for experiments.
Interactive: Bayesian update visualiser, Bayesian A/B test calculator, Bootstrap: estimating uncertainty by resampling, Calibration: can predicted probabilities be trusted?, Causal inference: separating effects from associations
How reliable is a success rate with little data? Understand prior, likelihood and posterior through a business example and try the Bayesian calculator.
How likely is B to be better, and what would a mistake cost? Beta posteriors, expected loss, uplift intervals and honest stopping rules.
Bootstrap explained: compare mean and median, resample observations with replacement and explore a confidence interval in an interactive local example.
Understand probability calibration through a reliability diagram, Brier score and temperature correction using interactive, fully synthetic predictions.
Understand causal inference through confounding, Simpson’s paradox and standardisation in an interactive comparison of training and success rates.
6 articles
Expected value, utility, decision trees and mathematical optimisation: from weighing alternatives to the best feasible action.
Interactive: Value of information: when is a test worthwhile?, Bayesian optimisation: which experiment comes next?, Linear optimisation, Robust decisions
From payoff matrices through expected value and expected utility to decision trees: comparing options under uncertainty—and valuing additional information.
Decision variables, objectives and constraints: how linear programs work, what shadow prices reveal, why rounding fails and how scheduling rules affect results.
Bayesian optimisation explained: explore a real Gaussian process, model uncertainty and expected improvement while searching for a good parameter setting.
How should limited labour and material be shared between two products? A small production model shows how constraints shape feasible plans and why whole units can change the answer.
Understand EVPI and EVSI through a market-test decision tree. Compare uncertainty, test accuracy and cost in an interactive example with explicit assumptions.
How much should you order when demand is uncertain? The same numbers produce different quantities under different decision rules. This calculator makes explicit which uncertainty and which kind of loss each rule addresses.
2 articles
When formulas are not enough: use randomness deliberately, explore scenarios and make risks visible.
Interactive: Monte Carlo demo, Queue simulation
How likely is a project to meet its deadline? Simulate durations, understand P80 and identify key risks, with a worked example and free calculator.
A team can have enough average capacity and still create long queues. This simulation explores how utilisation, variable service times and a second server interact.
6 articles
From regression and clustering to bandits and reinforcement learning: recognise patterns, test predictions and learn from consequences.
Interactive: Bandit simulation, Gridworld (value iteration & Q-learning), Contextual bandits, Reward design, Regression and overfitting, k-means clustering
Use the best option or try something new? Regret, ε-greedy, UCB1 and Thompson sampling, with a worked step and an interactive simulation.
How an agent learns by acting and receiving feedback: rewards, Markov decision processes, the Bellman equation, value iteration and Q-learning—with a worked example.
Why the same action can perform differently in different situations.
An optimal route can produce a poor outcome when its reward ignores important consequences.
A curve can fit familiar observations extremely well and predict new ones poorly. Compare polynomial degrees on the same training and holdout data, and see when additional flexibility becomes harmful.
Which customers are similar? The answer also depends on how similarity is measured. Group the same synthetic customers by order count and monthly revenue, and explore the effect of scaling.
2 articles
See how attention combines information and retrieval supplies sources. Learn where a language model needs checks and explicit rules.
Interactive: Transformer attention, RAG and sources
How similarity scores become weights and weighted values become a new representation.
Finding a relevant source is a separate calculation, and does not yet produce a verified answer.
2 articles
How statistics, simulation, optimisation and learning combine into an understandable decision system.
Interactive: Rules and optimisation
How data becomes decisions we can evaluate: a definition, the distinction from BI and Predictive Analytics, the methods involved and a fully worked example.
A plausible schedule must satisfy its rules before its value can be optimised.
smartlytics is the learning hub of NyxAI GmbH.
Explore the methods we work with, explained openly, with sources and calculations you can reproduce.
NyxAI is developing a Decision Core for Decision Intelligence that combines optimisation, simulation, statistics and reinforcement learning: compare options, make uncertainty visible and learn from outcomes, with people in control.
Explainable chess AI with human playing styles: NyxAI’s testing ground for understandable decisions under time pressure.