Fla.—IFSat itsUnleashedconference here last weekannouncedthe company’sindustrial AI Harness, whichisdesigned to help enterprisesimplementAI within the policies, controlsand operationsthat govern their business
AI Harnessextends its existingsecurity, safety,governanceand trust controls.The platform provides context, permissions, governance,and controls that allowits agentic“digital workers”to execute work within established business rules
AIHarnessalso serves as the operational foundation to IFS Intelligence, whichthe company said can collate data from all types of industrial assets, systems, and processes all around an operation and turn that information into actionable tasks that flows through one conversational interface.
According tonew research from IFS, 43% of frontline
According tonew research from IFS, 43% of frontline teams have trained and introduced agentic digital workers into their day-to-day operations over the past 12 months. However, only 11% have validated AI outputs for safety, quality, or mission-critical processes, and 11% haveestablishedcontrol mechanisms for AIusewith sensitive or export-controlled data.
As research fromFuturumalso found that while 66% of enterprises plan to invest in digital workers within the next 12 months, just 5.7% trust AI to act fully autonomously
Tohelp companies address these controlgaps,IFS designed theHarnesssothatAIoperatesthrough the customer’s existing controls. It inherits permissions and access controls from connected systems, usingyetanother IFS product,IFS Cloud,as the foundation
The harness has six key components, according to IFS:
-
Planning and orchestration break goals into steps and coordinate agents and tools.
-
Skills and connectors define andvalidatethe systems agents can use.
-
Memory and context carry progress forward and assemble only the information relevant to each task.
-
Guardrails and permissions enforce identity, approvals, andlimits onrisky actions.
-
Verification and escalation check work for correctness and policy compliance, escalating when needed.
-
Observability and auditabilitylogsevery decision and action for review, so nothing happens that cannot be traced back after the fact.
The harness is also designed to work across AI models andservices,so customers are not locked into a single provider. It also allows customer requirements, like where data can be processed, to remain part of how AI is deployed, IFS said.
Podcast:Do manufacturers dream of ‘digital workers’?
Other features, according to the company, include:
- Sovereignty:All data stays within the system of record; no raw datasentto external AI providers.
-
Staged autonomy:Workers start with co-pilotassistance, progress to recommendations, then to autonomous action, with escalation on uncertainty.
-
Industrial context:Domainexpertiseand curated tooling that prevents agents from being paralyzed by 70,000 available APIs.
-
Multi-layer governance:Security at the cloud level, the harness level, and the model level; not a single control, but aggregated assurance.
