Artificial intelligence for logistics and freight
The SOP, the claim, and the customer's standing instructions — answered for the desk that is on the phone now.
Request a consult for your operation.
How logistics companies use generative AI
Routing and forecasting are already software problems. The gap Convex fills is the written operation: what this customer requires, and what we do when a shipment fails.
Customer standing instructions
The desk asks how this account wants exceptions handled and gets the current instruction, not last year's email.
Claims and exceptions
A damage or delay file is drafted from the POD, the photos, and the clause in the conditions of carriage.
SOPs across sites
A new warehouse follows the same procedure as the one that wrote it, because the assistant cites that procedure.
Carrier and customs documents
Bills, permits, and the checklist for a lane are searchable before the cutoff, in Persian or English.
The same answer twice
Two agents no longer give two answers. The assistant is the procedure, and a person still sends the message.
Sites with their own network
A yard or a bonded warehouse can run the same product on its own infrastructure.
What logistics surveys show
Generative AI is already in transportation work. The mature, fully automated operation is not.
of large shippers and logistics providers had already implemented at least two generative-AI use cases
McKinsey logistics survey, more than 260 respondents, reported 2024–2025
of shippers and logistics providers in a 2025 transportation survey said they use generative AI. Top uses: data entry, route and load planning, forecasting
Descartes and SAPIO Research, Ninth Annual Global Transportation Benchmark Survey, July 2025, n=616
of those respondents said transportation management was fully automated. 37% had only partial or minimal automation
Descartes Transportation Benchmark Survey, 2025
of North American supply-chain leaders expect their supply chain to rely more on AI by 2030
DHL Supply Chain, Insight 2030 survey, 350 leaders, February–March 2025
Figures come from the published surveys and case reports named on each card. They describe those samples, not a promise of the same result.
What Convex puts in front of the team
The transport system keeps planning the freight. Convex answers the questions the system does not: the customer's rule, the claim, the SOP.
Several models
Pick the model for the task from several leading models, in one place.
Specialized assistants
Assistants for exceptions, claims, and the standing instructions of each account.
A personal assistant
Each person has an assistant tuned to how they work.
Workspace assistants
Shared assistants that keep the company's context for the whole team.
Search over your documents
Answers come from your own procedures, contracts, and records, with the source attached.
Documents out
Word files and images today. CSV export is planned.
A cap per person
Token use is visible per person, and the spend can be exported.
Adoption dashboard
See where AI is actually being used, and where it is not.
Cloud, or entirely on your own infrastructure
The same product. The difference is where the data sits.
Cloud
What is available today, hosted.
- Access to several leading models
- Specialized, personal, and workspace assistants
- Search over the company's documents
- Word documents and images
- Token-use tracking and reports
- Adoption dashboard
On-premise
Full control inside your environment, including a network with no outbound connection.
Everything in Cloud, plus:
- Your own model endpoints
- Offline licensing and payment for a disconnected site
- Assistants and workflows built for your process
Start with one account's file
The standing instructions and the last ten exceptions. If those answer cleanly, the desk can use it.