See It Work
See It Work
SYSTEM: OPERATIONAL OT/IT CONNECTORS: 150+ AUTONOMOUS OPERATION: 15+ DAYS GOVERNED AUTONOMY: ENFORCED AUDIT TRAIL: IMMUTABLE INDUSTRIES: ASSET-INTENSIVE & MISSION-CRITICAL DEPLOYMENT: 3-6 MONTHS VIA APEX CONTROL LOOPS: 3,400+ SYSTEM: OPERATIONAL OT/IT CONNECTORS: 150+ AUTONOMOUS OPERATION: 15+ DAYS GOVERNED AUTONOMY: ENFORCED AUDIT TRAIL: IMMUTABLE INDUSTRIES: ASSET-INTENSIVE & MISSION-CRITICAL DEPLOYMENT: 3-6 MONTHS VIA APEX CONTROL LOOPS: 3,400+

RECOMMENDATION MANAGER · INSIGHT TO ACTION

Manage recommendations from insight to action.

Prioritise the right response. Connect recommendations to workflows and approvals. Capture the outcomes.

WHERE IT FITS

Your team is drowning in alerts. The signal is buried in the noise.

Recommendation Manager is the decision layer between insight and action.

It manages operational recommendations end-to-end — from prioritisation to approval to outcome — so the signal that actually matters lands in front of the right person, with the context and authority to act.

Primarily supports

  • Advise & Coordinate — the operating phase between Monitor & Predict and Operate Autonomously.
  • Human-Controlled & Human-Approved decision paths — with audit trail attached.
  • Operational prioritisation — which recommendations matter most, right now, for which team.
  • Next-best-action workflows — routing each recommendation to the right person and the right system.

RECOMMENDATIONS FROM EVERY TIER

One inbox. Recommendations from every level of intelligence.

Recommendation Manager isn't tied to a single source. It's the operator-facing surface for recommendations produced anywhere in the platform — deterministic rules, reasoned AI, or autonomous cognitive agents. Whatever's generating the recommendation, the human sees one consistent surface to triage, approve, and act.

TIER 1

Deterministic

Rules-based recommendations

Threshold breaches, time-based triggers, and deterministic logic composed directly on the Stream Designer canvas. Same recommendation pipeline you've always had — just routed and surfaced consistently.

Explore Stream Designer →

TIER 2

Reasoned

Reasoned recommendations

AI Workflow Harness adds governed LLM reasoning to the same canvas — classifying signals, prioritising response, and explaining the why. Advisor-pattern outputs land in Recommendation Manager with the structured evidence operators need to trust them.

Explore AI Workflow Harness →

TIER 3

Cognitive

Cognitive recommendations

Cognitive Agents (MAGS) plan across decisions, learn from outcomes, and coordinate as a team. Their recommendations carry deeper context — observed patterns, retrieved knowledge, multi-agent reasoning — routed into the same inbox under governed control modes.

Explore Cognitive Agents →

HOW IT WORKS

The lifecycle of a recommendation.

From anomaly detection to resolution — follow a single recommendation as it flows through the system.

RECOMMENDATION LIFECYCLE LIVE
PUMP P-301 — BEARING VIBRATION ALERTAUDIT TRAIL
09:14:32
Anomaly Detected
Vibration spike on Pump P-301 bearing assembly exceeds threshold. Data stream triggers recommendation rule.
StreamDesigner
09:14:33
Rule Evaluated
Dynamic threshold rule fires: vibration > 4.2mm/s for 3 consecutive readings. Confidence score: 94%.
Rule Engine
09:14:34
Triage Protocol Loaded
SME-authored response protocol for bearing vibration loaded. Priority: High. Escalation path defined.
Triage Engine
09:14:35
Context Assembled
Maintenance history, OIM context, open work orders from SAP, equipment specifications — all surfaced to operator.
Context Provider
09:14:48
Operator Acts
Work order WO-4821 created in SAP. Bearing replacement scheduled for next shift. Parts pre-ordered.
Operator
09:15:01
Resolution Logged
Full decision provenance recorded. Recommendation effectiveness tracked. Rule refined for next occurrence.
Audit Trail

CORE CAPABILITIES

What Recommendation Manager does,
end-to-end.

From the moment a recommendation fires to the moment its outcome is captured — six jobs Recommendation Manager handles inside one operator experience.

Take a tour
  • Manage operational recommendations

    Every recommendation gets a unique ID, status, and lifecycle — visible in one inbox across teams and shifts.

  • Prioritise response

    Severity, confidence score and time decide what reaches the operator first — the right recommendation, to the right team, at the right moment.

  • Track status & ownership

    Who's working on what, what's open, what's closed — with full handover continuity across shifts.

  • Link to evidence & context

    Event data, asset history, open work orders, SME-authored triage protocols and discussion threads — attached to every recommendation.

  • Route into workflows

    From the recommendation straight into SAP, EAM, ServiceNow or your own back-of-house systems — work order created, parts ordered, action initiated.

  • Capture feedback & outcomes

    Did the recommendation solve the problem? Every outcome feeds back into the rule that fired — so the next one is smarter.

RULES ENGINE

Granular, Logic-Based Rule Building

Set up thresholds using static and dynamic data to trigger specific recommendations before an important event occurs. No coding — visual rule configuration.

Static and dynamic threshold combinations
Multi-condition logic with AND/OR operators
Time-window analysis and trend detection
Confidence scoring on every recommendation

INTERACTIVE TOUR

Take a Tour of Recommendation Manager

RECOMMENDATION MANAGER TOUR INTERACTIVE

PRODUCTION PROVEN

Trusted by Industrial Operators

VERIFIED RESULT — OIL & GAS
$16M Saved every year
18% Reduction in field service trips
95% Reduction in maintenance planning

Customer Case Study

Using XMPro, a global oil and gas supermajor rapidly composed and deployed an intelligent oil well maintenance solution in just three months -- achieving over $8 million in calculated value within the first six months.

VERIFIED RESULT — MINING
$10M Saved every year
30% Reduction in conveyor downtime
9,000t Saved every month

Customer Case Study

Using XMPro, the world's largest potash mining company rapidly composed and deployed a predictive maintenance solution for over 50 miles of underground conveyors in just 30 days, achieving $10 million in savings every year by reducing unplanned downtime by over 30%.

VERIFIED RESULT — ENTERPRISE SCALE
6 Sites with in-house adoption
1,000+ Assets monitored
35+ Operational, tactical and strategic use cases

Customer Case Study

XMPro enabled the in-house engineering team at a major North American miner to independently compose 35 operational, tactical and strategic solutions across six sites, scaling to monitor and manage over 1,000 diverse critical assets.

"XMPro successfully triggered a real predictive maintenance alert for a Haul Truck that appears to have a Strut issue - This was particularly impressive, considering we have only deployed the development environment a few weeks ago"

-- Advanced Predictive Maintenance Lead, major global mining company

Turn alerts into action.

See how Recommendation Manager gives your team the prescriptive intelligence to act before critical events happen.