PLC fault diagnosis
Investigate faults, trace restart blockers and deliver an evidence-backed recovery plan.
Explore use caseIndustrial work.
Handled by your agent.
Agents for specific industrial use cases, powered by tailored models and context.
We provide the agent and runtime as open source, with model and context licensing and lifecycle support from IA Foundry.
Pre-registration is open
Our first
AI-native PLC.
Industrial intelligence, built into the controller.
- Launch
- Event
- HANNOVER MESSE 2027
Register your interest and receive launch updates.
Pre-register by emailOpens your email app. Send your message to pre-register.
Industrial use cases
Assign a recurring workload. Receive completed work, with specific exceptions for your team and results that stay current as evidence changes.
PLC change review
Review PLC changes, build regression tests and run the checks before deployment.
Explore use caseOT vulnerability triage
Connect advisories with your assets and keep OT risk decisions current as conditions change.
Explore use caseMES integration mapping
Turn machine signals into a validated mapping for your manufacturing systems.
Explore use caseStandards evidence assessment
Keep release evidence connected to requirements, with gaps surfaced as your systems change.
Explore use caseBuilt around your operation
Specialized models.
Your industrial context.
Model and context licences
Your agent, powered by a specialized industrial model and context licensed from IA Foundry. Context includes industrial knowledge and task instructions.
- A model tailored to your industrial task
- Industrial knowledge and task instructions
- Lifecycle support with your IA Foundry model
Custom adaptation Optional
Adapt a model to your machines, documentation and workflows, using agreed data and evaluation criteria.
- Machine and process context
- Customer-specific terminology
- Agreed data use and evaluation
Autonomous work
Assign the work.
Receive the result.
Define the task, connect the permitted evidence and set the acceptance rules. The agent takes incoming work through analysis, checks, correction and delivery. It keeps results current as the evidence changes.
Routine cases finish without an employee carrying out each step. Your team handles exceptions, quality audits and decisions outside the agent’s remit. The goal is to remove the need for people to execute this routine workload and reduce the human hours needed to deliver it.
Run locally, with control over your data, models, access and updates. Live industrial changes follow your authorized operating process.
Read our missionMeasure the work removed.
Agree the workload and completion criteria, then compare accepted results with your current process.
Human effort
Count preparation, exceptions, audits, corrections and fallback work alongside the hours the agent takes over.
Completion and quality
Track accepted jobs against all eligible work, including blocked cases and failures. Record errors and reopened cases with turnaround time.
Operating value
Measure changes in downtime, rework or release delay separately. Value released capacity and realized cost savings separately, after deployment and operating costs.
Which workload should
your agent take over first?
Bring us a recurring task, the evidence it uses and the people-hours it takes today. We’ll define what your agent should complete, when your team should step in and how to measure the work removed.