What defines an exception event for the alert pipeline?

Configured based on SLA risk thresholds, delay windows, customs hold flags, and telematics events.

How were dispatchers prepared for reduced call volume?

Managed through structured briefings and transition monitoring, redirecting capacity to carrier relationship calls.

Does the platform handle multilingual customer communication?

Operates natively in English and Arabic with automatic language detection.

What is the ownership arrangement after engagement ends?

Full code, DB credentials, API configs, and docs transferred to client on go-live with zero platform lock-in.

Production Case Study · Logistics🔒 NDA Protected

AI Freight Dispatch and Shipment Platform

A regional freight forwarder managing 400 daily shipments across 8 depots was wasting 3.2 dispatcher hours per day on status queries the TMS already had the answer to. Mirlo Systems deployed an AI shipment status agent and exception alert pipeline, cutting dispatcher call volume by 68% within 30 days.

Schedule a Consultation

✦Enterprise-Grade Security✦AES-256 Encrypted Pipelines✦Zero-Downtime Migrations✦Sub-500ms Response Latency✦Agile Delivery Sprints✦CI/CD Infrastructure✦HIPAA & SOC2 Ready✦NDA-Protected Engagements✦Enterprise-Grade Security✦AES-256 Encrypted Pipelines✦Zero-Downtime Migrations✦Sub-500ms Response Latency✦Agile Delivery Sprints✦CI/CD Infrastructure✦HIPAA & SOC2 Ready✦NDA-Protected Engagements✦Enterprise-Grade Security✦AES-256 Encrypted Pipelines✦Zero-Downtime Migrations✦Sub-500ms Response Latency✦Agile Delivery Sprints✦CI/CD Infrastructure✦HIPAA & SOC2 Ready✦NDA-Protected Engagements

68%Dispatcher Call Volume Reduction

8 minException Alert Time

1,728 hrsDispatcher Hours Recovered Monthly

AI Freight Dispatch and Shipment Automation Platform — Mirlo Systems

TL;DR

Executive Summary

01 · Business & Technical Challenge

The Challenge

Operational Friction

The dispatch team of 18 across 8 depots spent 3.2 hours per day answering inbound status calls from customers and brokers (1,728 hours/month). Exception notification lag ran 4 to 6 hours after TMS event registration, causing customer complaints and contract penalty exposures.

Business Risks at Stake

Risk of adverse selection in freight capacity as dispatchers spend time on status calls
Risk of exception penalty clauses being triggered repeatedly due to late customer notification
Risk of leadership making routing decisions on data 4-5 days behind live operational state

02 · Solution Architecture & Technical Execution

The Solution

Deployed a bilingual AI Shipment Status Agent across voice, SMS, and WhatsApp pulling real-time Cargowise TMS data via API. Automated Exception Detection Pipeline triggered customer notifications within 8 minutes of TMS delay events.

Technology Stack

Cargowise TMSAnthropic ClaudeTwilion8n Workflow AutomationSupabaseSamsara Fleet

Engineering Capabilities Delivered

AI status agent handling voice, SMS, and WhatsApp queries in English and Arabic with live TMS integration
Exception detection pipeline monitoring TMS event stream and firing stakeholder alerts within 8 minutes
Automated customer exception notifications drafted and sent within 8 minutes of TMS event trigger
Fleet performance dashboard connecting TMS and fleet management system with 15-minute refresh cycle
KPI anomaly alerts firing when any depot metric deviates beyond 10% from 4-week average

Execution Approach

Discovery Across 3 DepotsTMS Integration BuildPhased 8-Depot CutoverDispatcher Transition BriefingSLA-Backed Support Tier

03 · Business Value & Tangible Results

Measurable Outcomes

Verified Performance Results

Inbound dispatcher call volume: Reduced by 68% within 30 days — Telephony platform CDR data
Exception alert time: Reduced from 4-6 hours to 8 minutes average — TMS event log audit
Dispatcher person-hours recovered: 1,728 hours per month returned to capacity planning — Time allocation audit
Fleet performance reporting cycle: Replaced manual 8-hr weekly process with real-time dashboard — Operations process audit
Customer satisfaction complaints: Reduced by 44% in 3 months — Customer service complaint log

Before vs. After

Daily dispatcher status calls

Before~320 per day

After~102 per day

-68%

Average exception alert time

Before4-6 hours

After8 minutes

-97%

Fleet performance reporting

BeforeManual 6-8 hrs weekly

AfterReal-time live dashboard

Eliminated manual process

Customer exception complaints

BeforeBaseline Q1

After44% reduction Q2

Quarterly comparison

Dispatcher hours on status queries

Before1,728 hrs/month

AfterUnder 550 hrs/month

1,178 hrs recovered monthly

Qualitative Gains

Zero manual administrative friction in routine processing pipelines.
Enhanced staff operational capacity redirected to high-value client interactions.
Full compliance and security audit trail maintained across all automated pipelines.

Stage 01
"We haven't started with AI yet"
Not sure where AI actually fits in your operation. We run a focused audit, show you exactly where it pays off, and build a prioritized roadmap - before you spend on anything.
AI Strategy & AdvisoryAuditRoadmap
Explore Advisory & Audit
Stage 02
"We tried AI and it didn't stick"
A chatbot or off-the-shelf tool didn't hold up in real operations. We rebuild it properly - integrated with your actual systems and tested against real workload, not a controlled test.
Custom AI DevelopmentIntegrationRebuild
Explore Custom AI Build
Stage 03
"AI is working, we want more of it"
One system is proving out. Now scale it - more coverage, more automation, better reporting - without breaking what's already working.
Workflow AutomationAI Reporting & AnalyticsScale
Explore Scaling & Automation

Connects directly to Cargowise TMS via API, pulling live shipment location, ETA, and documentation status per query.