Skip to content
‹ Back to IndustriesIndustrial IoT

Aegis: Simio builds simulations from FactoryLogix MES data

Aegis Software's Simio unit launched four simulation-based scheduling products on November 18, ranging from ready-to-use Simio Essentials to full Simio APS. For FactoryLogix MES users, the factory model is generated from live production data instead of built by hand. Data quality becomes the real test.

This story was produced through MarketScale. See how Industrial IoT teams put it to work with AI Visibility (GEO).

By MarketScale Newsroom · Aegis SoftwareSimioFactorylogixSimio Aps
Share
Aegis: Simio builds simulations from FactoryLogix MES data

Key takeaways

01

For plants already on FactoryLogix, simulation-based scheduling can start from existing MES data—so routing, bill-of-material and WIP record quality strongly affects the schedule.

02

Working in ranges lets Simio APS put an on-time probability on each order before a date is promised, a different input for customer commitments than a single capacity number.

03

The fair test for neural-network routing is the plant's best existing dispatch rule, not random assignment; if the network does not clearly win, the simpler rule stays.

Free workspace

Turn your Industrial IoT expertise into content.

Record interviews, organize footage, and write with AI on a free trial of the MarketScale platform for qualifying companies. No demo required, no credit card.

Try it Free

In many plants, late material or a machine that goes down still ends the same way: someone reopens the spreadsheet and rebuilds the production schedule by hand. Aegis Software's answer, released November 18, is a schedule produced by a simulation that nobody on the plant staff has to build.

Simio, the simulation company Aegis acquired and now operates as a subsidiary, has introduced four products: Simio APS, Simio Essentials, Simio Essentials Plus and Simio Virtual Factory Designer. According to Assembly Magazine, each one combines Simio's discrete-event simulation engine with adaptive AI. A planner can preview how the factory is likely to perform before committing to a plan, get a plain-language answer on why a given order is going to run late, and replan in near real time.

Simulation-based scheduling is not new. Dennis Pegden, Aegis's chief product officer for APS and simulation, said neural networks have been making decisions inside Simio for years. The change is where the model comes from. For customers of FactoryLogix, Aegis's manufacturing execution system (MES), Simio generates the simulation from live production data and refreshes it on demand, which the company says replaces the weeks of manual setup simulation has traditionally needed.

If that claim holds on the floor, the weeks of hand-built modeling that kept simulation-based scheduling in a specialist's corner become a refresh button for any plant already running FactoryLogix.

A twin generated from MES records

The inputs are records an MES already keeps: orders, routings, bills of material, resources, materials and work in progress. Aegis's Business Wire announcement describes a company founded in 1996 that sells MES software to discrete manufacturers in aerospace, defense, electronics, medical and automotive, and supports more than 2,200 factories across North America, Europe, Asia and Latin America. That installed base is the audience for the two no-configuration tiers, which generate a schedule in a click.

The design has a practical consequence. A simulation built from MES records can only be as faithful as those records. A routing with the wrong cycle time, or a bill of material nobody updated after an engineering change, would flow straight into the twin. Aegis appears to anticipate this: Simio Essentials checks for the data it needs before it runs.

For a plant weighing the tools, the first pilot task is an audit of routings and bills of material on the lines in scope. CEO Jason Spera said customers can grow from Essentials to full APS and factory design without revisiting the foundational data, so cleanup done for the entry tier would carry forward to the next one instead of being redone.

Event by event, with odds attached

Aegis positions the launch against the way most scheduling software works. In its description, traditional APS tools, including the scheduling add-ons bundled with many MES and ERP systems, run on rules and historical averages. That holds while the plant stays close to normal. Rules cannot capture how constraints interact, though, so when something changes the plan breaks, regenerating it can take hours, and planners patch it by hand. Hand-built simulations kept apart from live data drift out of date, and newer lightweight tools tend to answer one question, such as whether a new line will hit its target output, rather than schedule production every day.

Simio steps through the operation one event at a time against equipment, labor, materials, changeovers and business rules. Because it works with ranges rather than single values, Simio APS reports how likely each order is to ship on time. Pegden tied that to the moment a customer gets a date: the point is to see the risk of a late order before the promise is made.

That probability may be the most useful output for people outside the planning office. A team quoting delivery from a single capacity figure gets a yes or a no. A likelihood per order could let the plant separate safe commitments from the ones that need an extra shift or a different line to hold.

Aegis goes further, saying Simio schedules can go to production with zero intervention. That is a vendor claim, and a testable one. Running the Simio schedule alongside the current process for a few weeks and counting the hand edits would show how close a given plant gets.

Four tiers, split by data source

All four products sit on one simulation foundation, so a manufacturer can start at one level and move up without switching platforms. Here is what each includes, per the announcement:

  • Simio Essentials: ready-to-use scheduling for FactoryLogix customers who have no modeling or simulation expertise. The twin is built automatically, and every run comes with six preconfigured dashboards: bottleneck analysis, schedule summary, schedule detail, order performance, throughput and work in progress, and a capacity heatmap.
  • Simio Essentials Plus: builds on Essentials with a longer scheduling horizon, what-if analysis, comparison between plans, and support for additional or expected demand. It still requires no simulation expertise.
  • Simio APS: complete planning and scheduling for complex operations. It handles labor, tooling and material handling constraints, schedules primary resources automatically, embeds AI and gives each order its own on-time probability.
  • Simio Virtual Factory Designer: a digital twin used to design, optimize and validate layouts ahead of commissioning, so the plant ends up running the design that was validated.

Read closely, the line between tiers follows where the data comes from as much as how complex the plant is. The two Essentials tiers exist only for FactoryLogix customers. A manufacturer on another MES can buy Simio APS or Virtual Factory Designer standalone, but it starts at the full-depth end, and the announcement describes automatic twin generation only for FactoryLogix plants.

Beyond the listed features, the materials do not spell out what a line supervisor would notice differently between tiers in the first week, so a demo on the plant's own data is the way to find out. Virtual Factory Designer closes a different loop: the layout a team validates before commissioning becomes the model that later schedules the floor. Aegis's own shorthand is that the same simulation designs the system and schedules it.

Neural networks inside, chat assistants outside

The AI operates in two places. First, neural networks embedded in the simulation learn from shop floor context and from data the simulation itself produces, and Simio APS calls on them while a plan is running, for example to choose the best line for a job given the factory's current state. Second, built-in Model Context Protocol (MCP) support lets a company's existing assistants, such as Claude Code, Codex and GitHub Copilot CLI, connect straight to the simulation. Planners can ask which orders will be late and why, or launch a new scenario in plain language, and the responses are based on the factory's real orders and constraints.

A November 5 post on Simio's blog explains the mechanics. MCP is an open standard, so the software is not tied to one AI provider, and Simio ships two MCP servers: one for its documentation and one for the model that is open. The case for embedded networks is that lead time often depends on the mix of products already on a line, which a rule like shortest queue cannot see. A simulation can also generate as much training data as needed, including scenarios that have not happened yet, and networks trained elsewhere can come in through the ONNX format.

What Simio's AI demos did on sample models

More than a third
Cut in time to finish a set of orders when a neural network routed jobs across three lines, compared with random assignment
About 10.5 minutes
Time for an AI assistant to design, run and document a full verification of a three-station line model
About 90 seconds
Time to get an accurate plain-language explanation of a fuel supply model with 75 truck routes
Under 1 minute
Time to build and connect a three-station production line from a plain-language description

Simio

Those figures come from demonstrations on sample models, not customer projects, and Simio's own guidance is blunt about the routing result. Random assignment is an easy baseline to beat. The right comparison is the plant's best existing dispatch rule, and if the network does not clearly win, Simio advises keeping the rule because it is simpler to explain and maintain. The same post calls AI answers a strong first draft that can vary between runs and should be reviewed before anyone acts on them.

A January 2026 preprint on arXiv from a multi-university research team offers a useful yardstick. It sorts AI in digital twins into four stages: modeling the physical system, mirroring it with real-time synchronization, intervening through prediction and optimization, and autonomous management by language models and agents. By that map, the Simio launch covers mirroring through the MES feed and intervention through embedded networks, with language models acting as a question-and-answer layer for a planner who still makes the call. Asking a vendor which stage its AI actually operates in is a quick way to read any scheduling demo.

Testing it against last month

For production planning managers on FactoryLogix, Essentials Plus maps most directly to daily decisions: adding a resource, running an extra shift or accepting a rush order, each tested before the commitment. High-mix plants where orders shift and machines go down often stand to gain the most. A plant whose schedule rarely changes may find the spreadsheet is still good enough.

Before a pilot, pull last month's schedule and every edit made to it. Run the same orders through Simio and count how many changes the floor would still need. That count tests the zero-intervention claim against the plant's own constraints.

One item belongs on the IT list too. MCP connects coding assistants to live order and constraint data, and Simio notes that MCP support varies by AI product and plan. The CIO will want to confirm which assistant accounts can connect, and who gets that access, before planners start asking it which orders will be late.

Featured companies

Your experts belong here

Every story in MarketScale Industrial IoT starts with a company putting its controls engineers, plant-floor specialists, and integration partners on the record. Buyers are already reading this topic. The only question is whose experts they find.

Plant and controls buyers research deep before contact, and your engineers get to shape that research.

Book DemoSee how it works15 minutes, straight to a calendar.

About the author

MarketScale Newsroom
MarketScale NewsroomEditorial Team, MarketScale

The MarketScale Newsroom reports on the companies, technologies, and trends shaping 16 B2B industries. It turns primary sources and expert commentary into clear, useful coverage for the people doing the work.

B2B Weekly

The week in Industrial IoT, and sixteen other industries, every Monday.

Ten stories, one-line takes, five minutes. Free.

Industrial IoT: are you visible to AI?

Before they reach out, Industrial IoT buyers ask AI engines which vendors to trust. Explore how your experts, customers, and partners can become useful content for buyers and AI search.

Free Trial

You just read one Industrial IoT expert. Your company is full of them.

This article was produced through MarketScale. The same platform turns your controls engineers, plant-floor specialists, and integration partners into the articles, video, and social content Industrial IoT buyers are searching for. Start a free trial and see it with your own people. For qualifying companies, no credit card, no demo required.

NPS +73 · 1,000+ creators · 38+ countries

What your free trial includes

Hands-on access to the MarketScale platform
Media requests to your crowd, remote recording, AI writing tools
No demo required. No credit card.
For qualifying companies. Company confirmation required.

More Industrial IoT Insights

Rockwell's Emulate3D adds NVIDIA Omniverse to test whole factories before startup

Rockwell's Emulate3D adds NVIDIA Omniverse to test whole factories before startup

Rockwell Automation has built NVIDIA Omniverse, RTX rendering and OpenUSD into Emulate3D, stretching its virtual commissioning software from single machines to whole factories. Bigger models raise the stakes on scope. Plant engineering teams now have to decide how much of a factory is worth modeling, and who will build and maintain that model.

  • 01Emulate3D's core job hasn't changed: it hands a real controller a convincing virtual plant so the logic gets debugged before startup. What changed is how much plant it can hand over.
  • 02Software is the small part of a digital twin’s cost; the bigger cost is the engineers who build and run it. With factory-scale models, staffing and scope decisions need to be budgeted alongside the license.
  • 03ABB has published performance claims for its Omniverse-based RobotStudio HyperReality. Treat those claims as a reminder to ask any simulation vendor for measurable, application-specific evidence—without assuming ABB’s results translate to factory-scale Emulate3D projects.

Nov 18, 2026

Hyungji Elite will tag 4 million 2027-season garments with Beontag RFID

Hyungji Elite will tag 4 million 2027-season garments with Beontag RFID

South Korean uniform maker Hyungji Elite will tag 4 million pieces of one brand's 2027-season merchandise with Beontag RFID tags. The near-term gain is automated inspections and inventory audits. Better demand forecasting comes later, and only if item-level reads carry through production, logistics and sales.

  • 01At 4 million pieces for one brand's season, Hyungji Elite is sizing its first RFID step at production volume, with every garment carrying its own identity from the factory onward.
  • 02Manual stock checks fail in two directions at once: missing items cost sales, phantom gaps trigger overstock. An RFID business case should measure both, not just count speed.

Nov 17, 2026

Tutor Intelligence raises $75M for robot work priced from $14 an hour

Tutor Intelligence raises $75M for robot work priced from $14 an hour

Tutor Intelligence raised a $75 million Series B led by Andreessen Horowitz, bringing its total funding to $117 million. Its Sonny and Cassie robots are billed by the hour or by the pick, and the company's pricing page lists palletizing at $14 to $18 an hour. With no upfront purchase, that model could let sites pay for robots from operating budgets instead of capital requests.

  • 01For stacking and unloading pallets, Tutor charges $14 to $18 per robot hour, with an 80-hour monthly minimum and a flat $10,000 implementation fee, according to Inc. Customers make no upfront purchase and sign no long-term contract.
  • 02Tutor's robots are working in almost four times as many facilities as a year ago, the company said. Nearly a third of organizations that received Tutor robots in the past 12 months were existing customers installing more robots.
  • 03Nearly a third of the organizations that got robots in the past year were existing customers adding to their fleets—a repeat rate worth watching alongside Tutor’s broader growth goals, which Dealroom notes are still targets rather than proof at scale.

Nov 17, 2026

Explore More Industrial IoT Insights

Read more expert perspectives from across Industrial IoT.

Browse Industrial IoT Hub

About the Expert

MarketScale Newsroom
MarketScale Newsroom

Editorial Team

MarketScale

The MarketScale Newsroom reports on the companies, technologies, and trends shaping 16 B2B industries. It turns primary sources and expert commentary into clear, useful coverage for the people doing the work.

For B2B teams

Your experts could be publishing here

Stories like this one run on content MarketScale captures from real practitioners. See how your team's expertise becomes coverage in Industrial IoT and beyond.

Book a Demo

Or call us. No forms required. We pick up. 214-945-2512