AI for logistics and distribution, from the order to the delivery
Where a shipment is, why it is late and whether the customer has been told are answers spread over the warehouse database, the ERP, the order source, the support desk and the phone system. Memtro connects to them and answers across them, running database queries inside read-only transactions with the SQL shown, and citing every figure to the row, order or ticket it came from.
7-day free trial · card on file, nothing charged until it ends · cancel any time
Shipments, orders, the support desk and the ledger in one answer, with every figure cited to its record.
The systems these questions draw on, connected to one memory. Every connector reads by default; the tools that change something are granted by name, per team.
What it looks like today
- 01A customer asks where their order is and the answer needs the warehouse system, the carrier and the ticket.
- 02Late shipments are counted at month end rather than caught on the day.
- 03Operations questions become tickets for the data team.
- 04What was promised to a customer about a redelivery is in a call recording.
- 05The carrier's exception report and the warehouse's own data disagree, and the customer is told whichever arrives first.
- 06The person who knows which table holds the real despatch time is on holiday.
What Memtro does about it
One memory in front of the systems you already pay for, reading by default and acting only where an administrator has granted the tool by name.
- Connect the warehouse database on Postgres, MySQL or SQL Server, NetSuite, Shopify, Zendesk, Aircall, Twilio, Slack and Google Drive, reading by default and acting where you grant it.
- Ask about an order and the answer joins the order, the shipment rows and the customer's tickets and calls, each fact cited.
- Database questions run as bounded SQL in read-only transactions with a row cap and a timeout; the query is part of the answer, so the next person can rerun it.
- Memory keeps which tables answer which questions, so the second question about shipments is faster than the first.
- Schedule jobs: shipments past their promised date each morning, carriers with rising exception rates, customers with an open ticket and a late order.
System by system
What Memtro reads in each part of the stack, and what it may change there once the tool has been granted.
Carriers and delivery
ShipEngine or EasyPost in front of Royal Mail, Parcelforce, DPD, Evri, InPost and Yodel, or Royal Mail Click & Drop and UPS directly on your own accounts: what a parcel costs before the postage is bought, where it is afterwards, which ones have stopped moving, and the lockers and ParcelShops nearest a customer. Buying a label, voiding one and booking a collection are each granted by name, and a price is always quoted before anything is spent.
Warehouse and transport databases
Postgres, MySQL, SQL Server or MongoDB: consignments, despatch times, exceptions and stock. Schema first, then a bounded read-only query with a row cap and a timeout, and the SQL shown in the answer.
The ERP and the order source
NetSuite or Dynamics 365 Business Central with Shopify or WooCommerce: the order, the customer and the date that was actually promised.
The support desk
Zendesk, Freshdesk, Intercom, Front or Gorgias: what the customer has already asked and been told, with a reply or a status change on the desks that offer it, once granted.
Calls and messages
Aircall and Twilio: the call record and its transcript or summary where there is one, and the texts a customer was actually sent.
Agreements and the team
Google Drive or SharePoint for carrier agreements and rate cards, Slack or Microsoft Teams for where the morning list lands.
Money
Stripe, PayPal or the ledger in Xero, QuickBooks Online or NetSuite: what was charged for a delivery and what a claim or a credit cost.
There are 144 connectors in all, each with its own tools, its own permissions and a page of its own. Browse every connector →
Who asks what
Customer service
Answers where an order is, why it is late and what the customer has already been told, in one answer with the sources named.
Transport manager
Sees the exceptions by carrier and by lane each morning, rather than counting them at the end of the month.
Account manager
Walks into a review with on-time performance, the claims and the tickets for that customer, every figure traced to a row.
Analyst
Stops being the queue: the question is asked in English, the SQL comes back with the answer, and the right table is remembered for the next person.
The day in despatch
- 01
Before the shift
A seven o'clock job lists everything past its promised date by carrier, with the customer's last contact attached, so the calls that matter are known before the phones start.
- 02
Through the day
An order question is answered from the warehouse rows, the ticket and the call record at once, which is three tabs fewer and one version of events.
- 03
Exceptions
Carrier exception rates are compared each Monday against their own four-week average, so a carrier getting worse is a conversation rather than a surprise.
- 04
Over the month
Memory keeps which tables answer which questions and what each status code actually means, so the second analyst does not rediscover it.
Ask it like this
Plain English, from chat, your editor, a scheduled job or your own agent. In agent mode each question also checks the other systems that know about the same people, companies and references, and the answer ends with a line per system consulted.
- ShipEngine
- Royal Mail Click & Drop
- UPS
- FedEx
- DHL Location Finder
Every figure in the answer cites the record it came from, and the run ends with a line per system consulted.
- ›How many shipments went out late last week, by carrier, with the query you used?
- ›Which customers have an open Zendesk ticket and an order past its promised date?
- ›What did we promise the caller from BigCo about the redelivery on Tuesday?
- ›Which consignments missed their promised time yesterday, and what reason did the carrier give?
- ›What has this customer been told about their delayed order, by phone and by email?
- ›Which postcodes had the worst on-time rate last month, and with which carrier?
- ›What does the rate card say we should have been charged for this consignment?
- ›Which consignments have stopped moving, and where did each last scan?
- ›What would this pallet cost across every carrier we have an account with?
- ›Which collections are booked for tomorrow, and for which carrier?
Work that runs itself
A job is a prompt the agent runs on a cron schedule as its owner, with their tools and connections. Say any of these in chat and the job exists; every run's report is kept in a chat you can question.
- schedule:Every day 07:00: shipments past their promised delivery date, by carrier, with the customer's last contact
- schedule:Every Monday 08:00: exception rate by carrier, last week against the four-week average
- schedule:Every hour: new tickets from customers whose order is late, routed to the operations channel
- schedule:Every day 18:00: consignments despatched today with no tracking event recorded, by carrier
- schedule:Every Monday 09:00: claims and credits raised last week, with the carrier and the cause
- schedule:Every day 17:00: collections booked for tomorrow against the labels generated today
Questions people ask
Can it write to the warehouse database?+
No. Database connectors read inside read-only transactions with a timeout and a row cap, schema first, and the SQL is shown in every answer.
Does it work with our carriers?+
Carrier data reaches Memtro through the warehouse database or the ERP that records it. Shipments, statuses and exceptions are read from there, and the carrier is named on every figure.
Can it tell the customer?+
Where you grant it: Slack can post and Zendesk can reply on the ticket, each granted by name per team and used only when a person asks. Until granted, a connector only reads.
How does it learn our schema?+
It reads it. The agent lists tables and columns before writing anything, and memory keeps which tables answered which questions, so the next person gets the right one without asking a colleague.
Can it reach a database on a private network?+
Yes. Postgres, MySQL and SQL Server connections take an optional SSH tunnel: give Memtro a bastion host and a key or password and each query is forwarded through it, so the database never needs a public address.
Can the whole team use it, or only analysts?+
The whole team. A question in plain English gets the query written, run and explained, and the SQL comes back with the answer so the data team can check or correct it rather than field the request.
The same work, by team
The same connectors and the same memory, described through the job somebody does rather than the business they do it in.
- OperationsMonitors and digests that run themselvesJobs are prompts the agent runs on a schedule with the same tools as their owner. Create them in plain language, get the report in a chat, pause or change them in a sentence.Memtro for operations
- SupportAnswer tickets with the whole company behind youSupport teams spend their day switching tabs: the ticket in Help Scout, the customer in the CRM, the order in the warehouse, the invoice in Xero. Memtro reads the ticket and does the switching for them.Memtro for support
- Data and analyticsQuestions answered from the warehouse, with the SQL shownPoint Memtro at a read-only replica and anyone can ask the warehouse a question in plain English. The agent reads the schema, writes the query, runs it inside a read-only transaction, and shows its work.Memtro for data and analytics
Ask it about your own business
Connect the first two systems, ask the question you opened this page with, and see where the answer comes from. About five minutes.
7-day free trial · card on file, nothing charged until it ends · cancel any time