# Experiments Source: https://dinand.com/experiments/ Author: Dinand Tinholt > Apps and research systems I built. Two of them run right here in your browser. Ideas across time · Experiments # Experiments Apps and research systems I built. Two of them run right here in your browser. Ready here ## Try it in the browser Everything here runs in your own browser. Nothing you enter is sent anywhere. Simulation · Scenario planning ### [Many Worlds](https://dinand.com/experiments/many-worlds/) Plays a business decision out across hundreds of thousands of simulated futures, then tests every possible response against the same draws and recommends the one that holds up. Five library scenarios with illustrative figures. Change any assumption in the side panel and it reruns in your browser. [Run the futures ](https://dinand.com/experiments/many-worlds/) Field guide · Physical AI and world models ### [Dead Reckoning](https://dinand.com/experiments/dead-reckoning/) A world model is dead reckoning for machines. A small ship plans by imagining forty futures at every fix, then drifts on a current its model has never heard of. Scroll to follow the vessel, then take the helm yourself. Best on a laptop. [Take the helm ](https://dinand.com/experiments/dead-reckoning/) Live model · Reinforcement fine-tuning ### [Rulebook](https://dinand.com/experiments/rulebook/) A customer reply policy written as checks a machine can run, then used as the reward to fine-tune a model. A small transformer learns it live in your browser tab. Training starts by itself and runs for a few minutes. Larkfield, the retailer in the examples, is fictional. [Open Rulebook ](https://dinand.com/experiments/rulebook/) 3D walkthrough · Physical AI and oversight ### [Walk the Pakhuis](https://dinand.com/experiments/pakhuis/walk/) Walk through a seventeenth-century Amsterdam canal warehouse, built in simulation for a study of robots that count stock while a reviewer decides what reaches the record. Best on a laptop. Click to enter, walk with W A S D and look around with the mouse. The study behind it is on the Pakhuis profile. [Walk the building ](https://dinand.com/experiments/pakhuis/walk/) Instrument 01Try it ### [Monitoring cost explorer](https://dinand.com/experiments/monitoring-cost-explorer/) Explore how portfolio size changes modeled oversight cost. [Open instrument ](https://dinand.com/experiments/monitoring-cost-explorer/) Instrument 02Try it ### [Decision brief builder](https://dinand.com/experiments/decision-brief-builder/) Turn a question, evidence and constraints into a structured brief. [Open instrument ](https://dinand.com/experiments/decision-brief-builder/) New in the lab ## Lab tools, October 2026 Seven tools that came out of the research. Five are instruments you run on your own studies, logs and agents. Two let you explore the published numbers. Each one runs in your browser. Instruments you run Last updated Oct 11, 2026Lab tool ### [Pre-Registration Desk](https://dinand.com/experiments/pre-registration-desk/) Freeze a study plan under a hash before you run it, then mark each result against the rule you wrote down. Instruments you run Last updated Oct 11, 2026Lab tool ### [Judge Calibrator](https://dinand.com/experiments/judge-calibrator/) Run a model judge twice over the same items and get the noise band to print beside a judged score. Instruments you run Last updated Oct 11, 2026Lab tool ### [Delegation Ledger](https://dinand.com/experiments/delegation-ledger/) Write down what each agent owes before it acts, then read only where that disagrees with what ran. Instruments you run Last updated Oct 11, 2026Lab tool ### [Audit Row Reader](https://dinand.com/experiments/audit-row-reader/) Read decision-head audit logs as a trail in your browser, with rotated files checked as one series. Instruments you run Last updated Oct 22, 2026Lab tool ### [Charter Forge](https://dinand.com/experiments/charter-forge/) Write a delegation charter for an AI agent, place it by judgement and irreversibility, and size its oversight against the lab’s published findings. Instruments you run Interactive explorations Last updated Oct 11, 2026Lab tool ### [Oversight Simulator](https://dinand.com/experiments/oversight-simulator/) One set of controls drives four published studies, and every curve is a number the lab has already printed. Interactive explorations Last updated Oct 11, 2026Lab tool ### [Delegation Index, live](https://dinand.com/experiments/delegation-index-live/) Thirty questions put your organisation on the five rulers of the Delegation Index, next to the Q3 2026 reading. Interactive explorations Instruments from the research ## Work the published numbers yourself Each instrument runs on the coefficients a campaign published, with every number listed underneath. Nothing is sent anywhere. Instrument ### [Delegation Cliff calculator](https://dinand.com/experiments/instruments/delegation-cliff/) Move the twelve organisation levers and read how far the published coefficients say the quality margin moves, and which levers carry the movement. [Open the instrument ](https://dinand.com/experiments/instruments/delegation-cliff/) Instrument ### [SIGIL tier explorer](https://dinand.com/experiments/instruments/sigil/) Pick an irreversibility tier and compare what blocking review and review with a liability ledger did to the value of oversight there, beside what the registered prediction said would happen. [Open the instrument ](https://dinand.com/experiments/instruments/sigil/) Instrument ### [Trial Balance budget curve](https://dinand.com/experiments/instruments/trial-balance/) Set a reading budget and a diary length and read how many skipped steps each of four audits finds, then switch fault classes on and off to see what a full read of the diary finds and misses. [Open the instrument ](https://dinand.com/experiments/instruments/trial-balance/) Separate applications & research systems ## Systems in the workshop Each profile explains what the system does, how mature it is, and what remains deliberately outside this public site. System 01Private working prototype Agent governance ### [AI Control Plane](https://dinand.com/experiments/ai-control-plane/) A register and evidence layer for examining an enterprise portfolio of AI agents: who owns them, how far they act, and what supports the trust placed in them. [View project profile ](https://dinand.com/experiments/ai-control-plane/) System 02Completed research campaign Enterprise ecosystem simulation ### [AGENESIS](https://dinand.com/experiments/agenesis/) An agent-based laboratory for exploring how different levels of AI participation interact with enterprise structure, market conditions and industry context. [View project profile ](https://dinand.com/experiments/agenesis/) System 03Working local application Supply-chain stress testing ### [SCENARIO-X Studio](https://dinand.com/experiments/scenario-x/) An interactive workbench for designing multi-product supply-chain experiments and inspecting where average performance hides a weak tail. [View project profile ](https://dinand.com/experiments/scenario-x/) System 04Working research product AI output assurance ### [Assay Bench](https://dinand.com/experiments/assay-bench/) A workbench for measuring the quality and checking cost of AI outputs when there is no simple answer key. [View project profile ](https://dinand.com/experiments/assay-bench/) System 05Paper-only research prototype Paper-trading research ### [Personal Quant Agent](https://dinand.com/experiments/personal-quant-agent/) A research system that scans public market data, tests a small strategy library, applies explicit risk controls and records simulated decisions in a paper portfolio. [View project profile ](https://dinand.com/experiments/personal-quant-agent/) System 06Working research product Physical AI and oversight ### [Pakhuis](https://dinand.com/experiments/pakhuis/) A seventeenth-century Amsterdam canal warehouse, built in simulation, where two robots count stock and a reviewer decides what reaches the record. [View project profile ](https://dinand.com/experiments/pakhuis/) What came out of the lab ## Studies these systems produced. [All studies & simulations ](https://dinand.com/research/) Oct 18, 2026Medium + LinkedIn ↗ ### [When watching every hour starts to pay](https://medium.com/@tinholt/when-watching-every-hour-starts-to-pay-caea3d7200ab) A pre-registered simulation held hourly monitoring of an agent fleet and six-hourly inspection to the same nominal reviewer budget, and found the budget at which hourly monitoring starts to catch faults. Oversight & accountability Oct 11, 2026Medium + LinkedIn ↗ ### [The Judge’s Mirror](https://medium.com/@tinholt/the-judges-mirror-0abe871ade6b) A preregistered study of how often a model judge agrees with itself on 197 blind case files, and how far down one model family a judge stays usable. Oversight & accountability Oct 7, 2026LinkedIn ↗ ### [The Open Decision Head: An Executive Briefing](https://www.linkedin.com/feed/update/urn:li:activity:7513629422663434240/) A retrained open decision head beat both a rule table and the hosted service on 800 fresh cases, after a first version that did not. The agentic enterprise Oct 1, 2026Medium ↗ ### [A Trial Balance for Agent Omissions](https://medium.com/@tinholt/a-trial-balance-for-agent-omissions-568a41c59aa1) Agent logs record what happened and have no row for what didn’t. A pre-registered test of commitment accounting, an obligation ledger reconciled against executed calls, for catching omissions in procurement-workflow traces. Oversight & accountability --- Site guide for AI agents: https://dinand.com/llms.txt