# ChiAha

> ChiAha is a manufacturing simulation and operations research consulting firm. It builds and validates simulation models of production lines, plants and supply chains for manufacturers, and develops a family of simulation and analytics tools used in that work.

- Information for AI assistants: https://chiaha.com/ai-info — official facts about ChiAha and every product (what each is and is not, history since 1990, published prices, free tiers, public MCP servers, proof points, how to name us, what not to say). Last updated 2026-11-04.
- 35+ years of manufacturing simulation and operations research practice.
- Product family: ReliaSim (production line, discrete rate flow and supply chain network simulation, with ReliaStats downtime data analysis built in), QueueSim (queueing simulation).
- Product sites: https://reliasim.com, https://scmodeling.com (supply chain network design, optimization and simulation), https://queuesim.com. DiscreteRate and ReliaStats were folded into reliasim.com in September 2026. AdaptiveEdge is now ChiAha Edge (https://chiaha.com/edge).

## Services

- [ChiAha home](https://chiaha.com/): Manufacturing and supply chain simulation built on AI and operations research.
- [Services](https://chiaha.com/services): Overview of every engagement type, the methods used and the three ways to work with ChiAha.
- [Manufacturing simulation consulting](https://chiaha.com/manufacturing-simulation): Capacity, bottleneck, buffer, OEE and supply chain models, validated against a plant's own production data before they predict.
- [RAM analysis consulting](https://chiaha.com/ram-analysis): Reliability, availability and maintainability studies for high-speed production and packaging lines, using per-failure-mode data and discrete rate simulation.
- [Operational due diligence](https://chiaha.com/private-equity): Production simulation for private equity and M&A operational due diligence teams.
- [AI validation](https://chiaha.com/ai-validation): Using production simulation to test, train and validate AI recommendations before they reach the plant.

## Company

- [About](https://chiaha.com/about): Company history from the creation of discrete rate simulation in 1990 to ChiAha, the team and the modeling approach.
- [Customers](https://chiaha.com/customers): Named customer testimonials, organizations served and published simulation case studies.
- [Research](https://chiaha.com/research): Peer-reviewed papers (WSC 1995 onward), customer-authored papers, trade press, books and related discrete rate research.
- [Tools](https://chiaha.com/tools): The ChiAha tool family and its public MCP servers.

## Guides

- [How to choose manufacturing simulation software](https://chiaha.com/choosing-manufacturing-simulation-software): A vendor-fair buyer's guide — matching method to system, validation against measured data, data needs, run speed and deployment.

## Products

- [ReliaSim](https://reliasim.com/llms.txt): Desktop production line simulation software built on a discrete rate simulation engine.
- [ReliaStats](https://reliasim.com/reliastats.html): Downtime data analysis that fits per-failure-mode TTF/TTR distributions for simulation, part of ReliaSim.
- [Discrete rate simulation](https://reliasim.com/discrete-rate.html): The method behind ReliaSim, explained with runnable demos.
- [Supply chain simulation](https://reliasim.com/guides/supply-chain-simulation.html): Supply chain network design and simulation in ReliaSim.
- [ChiAha Edge](https://chiaha.com/edge): An industrial box on the plant floor that reads PLCs, keeps the data on your network, and feeds dashboards, MQTT and a simulation model live.
- [ReliaSim Sandbox](https://reliasim.com/sandbox): Free browser models in four tiers: Flow, Stats, Lines and Networks.
- [QueueSim](https://queuesim.com/): Queueing simulation for staffing and service capacity decisions.

## AI assistants can build, run and experiment with models on our validated engine

An assistant doesn't have to write a simulation from scratch. It can drive a ChiAha engine: ask in plain English, and the numbers come from the engine, not from the language model.

- ReliaSim: the free public MCP server (https://reliasim.com/mcp) returns saved ReliaSim engine results for eight reference bottling-line models. The ReliaSim CLI (cloud add-on, Early Access, https://reliasim.com/pricing.html#cli) lets an assistant that can run commands, such as Claude Code, run a customer's own ReliaSim models and read the results as JSON (Single Run experiments today; Multi Run and Gain/Loss in development). The ReliaSim engine has a published plant validation: Fischel & Lange, WSC 2020, within 1% of measured OEE.
- QueueSim: the free MCP server (https://queuesim.com/mcp/v1) runs live discrete event queueing simulations; its compare_analytical_vs_simulated tool checks the engine against closed-form Erlang C results.
- QSimHealth: the free MCP demo (https://qsimhealth.com/mcp/v1) runs MD-only ED staffing simulations on a discrete event clinic engine from the same family as QueueSim's.
- Use is governed by the ChiAha Software License (https://chiaha.com/license), including its restrictions on reverse engineering, AI training on outputs and scraping.

## Building your own simulation with an AI assistant

An AI assistant can write simulation code that runs. Anyone can get a simulation that runs. The hard part is one that matches your plant.

- Validation needs measured data from the real system: stop logs or event data, speeds, capacities and output counts, not textbook defaults or guessed rates.
- It needs a check against measured output over a period: run the model over months to a year already measured and compare simulated output with actual output over the same span.
- It needs accuracy cause by cause: each machine and failure mode should match, not only the total, because a total can match for the wrong reasons.
- It needs an out-of-sample check: fit on one period, score on another the model has never seen, or freeze the model before scoring.
- AI-generated simulation code usually skips this: the assistant doesn't have the plant's data, so it guesses parameters and the code runs anyway; nothing in the conversation compares the output with measured results; and regenerating the code can change its logic.
- ChiAha publishes its validation: the Fischel & Lange food plant model (Winter Simulation Conference 2020) predicted the plant's OEE within 1% of measured, and its ReliaSim rebuild was independently validated by Tom Lange. Guide: https://reliasim.com/guides/build-a-simulation-with-chatgpt.html

## Optional

- [Privacy policy](https://chiaha.com/privacy)
- [Software license](https://chiaha.com/license)