SAIE for transport is an AI environment with document agents that read orders and transport documents, prepare responses to complaints and scale from one branch to the whole company. Documents that read themselves, complaints with a draft reply, and a pilot that scales across branches
Why now
The first job for AI in transport and logistics is to cut everyday time drains: transport documents are retyped by hand, complaints take too long, and monthly summaries for clients and carriers are compiled by hand. Branches work in local mail and Teams, knowledge does not reach headquarters, and a successful pilot in one branch does not spread to the rest of the company. From 9 July 2027, authorities must accept electronic freight transport information (eFTI), and entities in the transport sector must implement the security measures under the amended KSC Act (Poland’s NIS2 implementation) by 3 April 2027. KSeF (Poland’s National e-Invoicing System) has been mandatory since 1 February 2026 for the largest taxpayers and since 1 April 2026 for others, while the smallest have until the end of 2026
Automotive: dealers and service centres work with technical documentation, manufacturer bulletins, warranty terms and repair histories. In TWIN:DESK a service advisor gets answers from these documents with the source cited, and an agent prepares a warranty claim or a complaint response for a human to approve
Business scenarios
Automatic reading of transport documents
Process automation
TWIN:DESKProblem: Transport and billing documents are retyped by hand
How it works: OCR reads data from documents, and n8n flows pass it to operational systems
What you gain: Data from CMR and billing documents reaches the system without retyping - the forwarder checks rather than enters
Assistant for complaints and requests
Process automation
TWIN:DESKNEW · SAIE PANTERAProblem: Handling client complaints and requests takes too long
How it works: The assistant analyses the request history in the RAG knowledge base and prepares a draft reply for review; the Decision Learning Layer proposes automating repetitive decisions. In the agentic loop the agent proposes a plan for approval, and the run history shows every step
What you gain: The client gets an answer faster, and over time repetitive complaints are handled according to approved rules
Automatic reports for clients and carriers
Analytics and reporting
TWIN:DESKNEW · SAIE PANTERAProblem: Summaries for clients and carriers are compiled by hand every month
How it works: Scheduled prompt runs (RRULE) that generate periodic reports. The consolidated report follows a published plan (DAG) and runs again when the data changes
What you gain: Monthly summaries generate themselves, in the same format, on time - no month-end in spreadsheets
An assistant that uses the knowledge of dispersed branches
Knowledge and documents
TWIN:DESKNEW · SAIE PANTERAProblem: Dispersed branches work in local mail and Teams, and knowledge does not reach headquarters
How it works: A local agent reads Outlook, Teams and folders without loading them into the central base; integration with Microsoft 365. The local agent moves Outlook meetings into Asana tasks, with no duplicates
What you gain: A branch’s knowledge is available to the assistant where it is created - without a project to migrate data to headquarters
Controlled automation of multi-step processes
Process automation
TWIN:DESK + PROXY:AIProblem: Operational processes require multi-step automation while keeping control
How it works: If/then rules in natural language; A2A delegation with approvals and limits; stateful orchestration of multi-step agent processes
What you gain: The process runs step by step through agents, with approvals where needed - and with the full state between stages
Scaling a successful pilot across the organisation
Adoption and skills
CDFProblem: An AI pilot in one branch does not spread to the rest of the company
How it works: A “scale or stop” gate with a Cognitive SLA (F4); scaling in waves and an AI system catalogue (F5); AI Champions in every branch (F3)
What you gain: A successful pilot has a ready path to the next branches: in waves, with local leaders and a catalogue of proven use cases
Secure AI for drivers’ and clients’ data
Security and sovereignty
PROXY:AIProblem: Drivers’ and clients’ data must not reach an external model
How it works: Personal data detection and masking; routing by data sensitivity
What you gain: Drivers’ and clients’ data is masked automatically, and sensitive queries go only to a local model
Questions decision-makers ask
How do you transfer data from orders and CMR documents to the TMS?
Document agents in TWIN:DESK read data from documents and prepare it for the system, and a human approves the result before it is saved
How do you keep drivers’ and customers’ data secure?
Through a single gateway to models with personal data masking (PROXY:AI) and permissions by branch
Where should the decision be left to a human?
Wherever the outcome affects a customer or a driver: accepting a complaint, contractual penalties, carrier evaluation
How does AI help car dealers and service centres?
TWIN:DESK answers advisors’ questions from technical documentation, bulletins and warranty terms with the source cited, and agents prepare warranty claims and complaint responses. A human decides whether to accept a warranty claim
Which AI tools can be used in logistics and freight forwarding?
In SAIE, logistics and freight forwarding are supported by, among others, three tools in TWIN:DESK: an AI agent for freight forwarding that reads orders and CMR documents and prepares the data for the TMS, a complaints assistant that prepares a draft reply, and reports for clients and carriers generated on a schedule. PROXY:AI masks drivers’ and clients’ data, and a human approves order data before it is saved in the TMS
Does NIS2 cover railways and transport companies?
Railways, yes: rail infrastructure managers and railway undertakings belong to the transport sector in Annex I of the NIS2 Directive, alongside air and water transport. In road transport the directive covers road authorities responsible for traffic management and operators of intelligent transport systems, not every haulage company; courier companies are in Annex II. As a rule, it applies to medium-sized and large enterprises. In Poland NIS2 is implemented by the amended KSC Act, and entities in the transport sector must implement the security measures by 3 April 2027. The PROXY:AI query log helps show oversight of AI tools
All questions