AlphaIQ mark

AlphaIQAutoSimAn AlphaIQ product

Describe any system in plain language. Get a validated simulation.

AutoSim reads your description or PDF, writes the simulator, fits it by Bayesian calibration and scores it out-of-sample — in your browser, in minutes. Every number traces back to an executed computation.

See the process. Change the outcome.

How it works

The problem

Serious decisions run on simulation. Building one is broken.

6 months
What a bank, insurer or supply-chain team spends building one production simulation model with a specialist quant team.
$500K+
Fully-loaded cost per model — before validation, documentation and model-risk review double it.
0 trust
What an LLM-generated model earns from a risk committee: no calibration, no out-of-sample test, no audit trail.

The new failure mode: anyone can ask an AI for a model that looks right. Nobody can tell you if its numbers mean anything. The bottleneck moved from writing models to trusting them.

The solution

The AI writes the model. Executed code decides if it is right.

The AI does

  • Reads your description or PDF
  • Proposes parameters with literature citations
  • Writes the Python simulator, streamed live
  • Diagnoses failures and proposes repairs

Executed code does

  • Runs real Python in your browser via WebAssembly
  • Fits parameters by Bayesian calibration (ABC-SMC)
  • Scores validity out-of-sample on held-out data
  • Exports an auditable model-risk report

AI narrative is never folded into a numeric score. Every number traces to an executed computation.

What AutoSim simulates

Six families of model, one description away.

AutoSim is not a template gallery. It picks the modelling paradigm the system actually needs, writes the simulator, and calibrates it against your data.

Agent-based models

Heterogeneous agents with behavioural rules, interacting on a grid, a network or a market. Emergent outcomes rather than assumed ones.

Traders, households, drivers, patients, firms

Compartmental & system dynamics

Stocks, flows and feedback loops. Continuous or discrete time, fitted to observed trajectories rather than hand-tuned.

SIR epidemics, adoption curves, inventory loops

Discrete-event & queueing

Arrivals, servers, capacity and waiting. Utilisation and tail latency come out of the run, not out of an average.

Triage, warehouse picking, call centres, ports

Network diffusion & contagion

Spread over an explicit graph, with topology treated as a parameter you can stress rather than a fixed assumption.

Information cascades, default contagion, outages

Monte-Carlo risk ensembles

Thousands of stochastic paths from the calibrated model, returning full distributions, probability cones and tail measures.

VaR and ES, ruin probability, delay distributions

Policy & intervention search

Sweeps and optimisation on top of the simulator, so you compare interventions under the same uncertainty instead of one point forecast.

Pricing, staffing, lockdowns, rebalancing rules

Every family ships as readable Python, calibrated with ABC-SMC and scored out-of-sample — the paradigm changes, the evidence standard does not.

From one sentence to a running model

What you describe, what you get back.

“Simulate how a two-week port strike moves my delivery times.”
Discrete-event logistics model with capacity shocks, calibrated to your shipment history, returning a delay distribution per lane.
“Model a flu outbreak in a city of 2 million with school closures.”
Age-structured compartmental model with mobility, priors cited from literature, intervention timing as a swept parameter.
“What happens to my order book if the two largest market makers withdraw?”
Agent-based market microstructure model, calibrated to observed spread and depth, with a stressed-liquidity ensemble.
“How much staffing do I need to keep ER waits under 30 minutes?”
Queueing model of triage and beds, fitted to arrival logs, with a staffing sweep and the cheapest policy that holds.

The product

This is live today — not a mockup.

AutoSim Studio — the six-stage pipeline seeded from a book chapter, with parameter roles and citations visible.
AutoSim Studio — the six-stage pipeline seeded from a book chapter, with parameter roles and citations visible.
The guided classic workflow with live usage metering — six steps from description to validation.
The guided classic workflow with live usage metering — six steps from description to validation.
The template library — 500+ scenarios and all 17 handbook models, one click from a validated run.
The template library — 500+ scenarios and all 17 handbook models, one click from a validated run.

Pipeline, calibration, validation and billing are all in production right now.

See the proof

AutoSim overview

Nine simulations already built on AutoSim — open and run any of them

Pricing

Start free. The demo is the product.

Free

$0

500K AI tokens / day

The full pipeline and unlimited in-browser simulation.

Start free

Pro

$99 / mo

10M AI tokens / day

For power users: bigger models, priority AI, unlimited saved projects.

Go Pro

Enterprise

Custom

On-premises available

Model-risk reports, SSO, audit logs and private deployment. Priced per model-risk seat.

Talk to us

Simulations run in your browser, so compute is yours and pricing tracks AI usage — metered per user with quotas and live cost tracking.

AlphaIQ

AutoSim is how AlphaIQ ships its method.

AlphaIQ builds calibrated, validated agent-based simulations of the markets, portfolios and institutions our clients operate in. AutoSim is the self-serve product; bespoke engagements are the hands-on path for teams who want the model built with them.

Bespoke engagementsApplicationsInsights

Next step

Bring a system you need to defend.

Describe it in plain language and AutoSim will build, calibrate and score a simulation of it while you watch. If the question needs more than the product alone, AlphaIQ will build it with you.

Talk to AlphaIQ