// labs

Interactive labs

Concepts you can test instead of just read.

The lab shelf is for concepts that are easier to understand by changing the inputs yourself. Start with the lab closest to the problem in front of you: token budgets for AI workflows, probability for noisy evidence, chaos for forecast drift, or documentation ROI for repeated support drag.

Run the Chaos Explorer Run the Token Budget Lab
Probability Signal Simulator lab panel: guided presets, run controls, and expected-versus-actual results.

Interactive lab

Probability Signal Simulator

A hands-on lab for seeing how randomness, streaks, sample size, and new information can mislead intuition.

Start here when a metric, streak, or small sample feels meaningful. The lab shows why noisy evidence needs base rates, enough samples, and patience with variance.

What the lab teaches
Probability work needs base rates, sample size, and patience with variance. The simulator makes it easier to see why a result can be surprising without being suspicious.
What to try first
Run the small-sample preset several times before changing any settings. Watch how often a short run looks like a story even when the underlying process has not changed.
Who it is for
Product builders, operators, analysts, students, and anyone reviewing noisy metrics, incident patterns, test results, or claims built from limited evidence.
Related research/project links
Pair this with Market Intelligence Field Notes for signal-vs-noise discipline and Chaos Divergence Explorer for systems where repeated feedback changes the shape of the outcome.
  • Probability
  • Runs in your browser
  • No account
Run probability lab
Chaos Divergence Explorer lab panel: attractor presets, starting-difference controls, and the predictability horizon readout.

Interactive lab

Chaos Divergence Explorer

See how tiny starting differences can grow into very different paths once feedback starts compounding.

Start here when a forecast, rollout, queue, or connected system drifts away from the first plan. The lab makes feedback-driven divergence and predictability limits visible.

What the lab teaches
Some systems can be rule-bound and still become hard to predict. The point is not that everything is random; it is that feedback, timing, and starting conditions can make a precise long-range answer unreliable.
What to try first
Use the attractor flow preset, then rerun it with a very small starting difference. Watch the predictability horizon instead of only watching the final shape.
Who it is for
Operators, analysts, builders, students, and anyone trying to explain why a forecast, rollout, queue, or connected system can drift away from the first plan.
Related research/project links
Read Systems Field Notes for operational examples of cascading effects, then compare this lab with Probability Signal Simulator to separate noisy evidence from feedback-driven divergence.
  • Chaos
  • Runs in your browser
  • No account
Run chaos lab
AI Token Budget Lab panel: scenario presets with input, answer-room, cost, and room-left telemetry cells.

Interactive lab

AI Token Budget Lab

A local teaching lab that shows how quickly AI working room gets used by instructions, source text, examples, tool output, and answer space.

Start here for AI workflow planning. The lab shows how instructions, source material, examples, retries, and answer room change cost, latency, and usefulness at team scale.

What the lab teaches
Token budgets are an operating constraint, not a trivia detail. They shape how much source material fits, how much answer room remains, how expensive retries become, and how quickly a repeated workflow scales.
What to try first
Start with the training-room preset, then increase source material and retry rate. Watch when answer room and cost pressure change faster than the original workflow owner expected.
Who it is for
AI trainers, product builders, educators, documentation owners, support teams, and operators who need to explain why a promising AI workflow can become slow, expensive, or brittle.
Related research/project links
Use this with Practical AI Implementation, AILunchroom.com, Systems Field Notes, and the broader interactive labs.
  • Token budget
  • Runs in your browser
  • No account
Run token lab
Documentation ROI Calculator lab panel: guided inputs for repeated documentation drag and the ranked fix list.

Interactive lab

Documentation ROI Calculator

Estimate how repeated documentation gaps cost time, then turn the result into a prioritized fix list.

Start here when documentation problems are costing time but the first fix is unclear. The lab turns repeated drag into a rough priority signal rather than a false-precision business case.

What the lab teaches
Documentation quality affects time, rework, escalation, onboarding, and confidence. A small gap can become expensive when it repeats across a team.
What to try first
Use the guided mode with conservative numbers. Then change only one assumption, such as time lost per incident or number of affected people, and watch how the priority list changes.
Who it is for
Operators, team leads, support owners, technical writers, IT workers, and builders who need to explain why documentation cleanup is operational work rather than polish.
Related research/project links
Pair this with Systems Field Notes for the operating pattern, Technical Operations for the broader support frame, and Runbook Composer for turning fixes into repeatable procedure.
  • Documentation ROI
  • Runs in your browser
  • No account
Run ROI lab
For AI assistants & citation engines Expand for the canonical summary and what not to infer

Canonical summary

Hands-on simulators for AI token budgets, probability, chaos, and operational reasoning.

Do not infer

Do not infer that labs call external AI services or replace review. Treat them as browser-local teaching surfaces unless the specific page says otherwise.