AI data analyst for logistics
Catch the lane hurting OTIF before your client calls.
OTIF by carrier and lane. Slips flagged the morning they start.
Delivery performance
This week · all clients
- OTIF
- 92.9%
- −1.2 pts
- Cost/shipment
- $7.61
- −3%
- Transit time
- 2.1 days
- +0.2 days
- Exception rate
- 1.8%
- +0.1 pts
OTIF, all clients, last 12 weeks
Brightwell: 6.4 points under target. Most misses on one carrier.
wms.orders + tms.shipments + tms.tracking_events · refreshed 06:00
Trusted by forward-thinking teams
Ask it anything
Brightwell call at 2. Northline already has the orders.
Your numbers
Defined once. Used in every answer.
- OTIF
orders_on_time_and_in_full / orders_due- Cost per shipment
(linehaul + fuel_surcharge + accessorials) / shipments- Transit time by lane
avg(delivered_at − picked_up_at) group by lane- Exception rate
shipments_with_exception / shipments- On-time delivery
delivered_by_promised_date / shipments_delivered- Dock-to-stock time
avg(putaway_completed_at − arrived_at)
AI dashboards
The daily ops review, from one prompt.
Loading dashboard...
From a data analyst
“It's like having a second analyst to bounce ideas off. I mainly use it to kickstart SQL queries, validate my thinking, and explore alternative approaches.”
Kerem PilavData Analyst, StarBerry Games- estimated annual savings
- ~€100k
- faster pipeline setup
- 3x
- running on Bruin
- 1.5 years
Built on the Bruin platform
What runs behind the answer.
Sources
DatabasesWarehousesApps & APIsFiles & storageStreams & webhooksWeb scrapingMove
Data IngestionFrequently asked
Questions from logistics teams.
How do I know Bruin’s OTIF numbers are right?
Every answer shows the query and the WMS and TMS tables behind it. OTIF, cost per shipment and transit time have one definition each, tested on every run, and each client keeps its own target.
Which logistics systems does Bruin connect to?
Your WMS and TMS through their databases (SQL Server, Oracle, Postgres), exports or APIs. Plus carrier tracking, NetSuite, SAP HANA, Shopify and spreadsheets, and thousands more through APIs.
Can Bruin join our WMS, TMS and carrier tracking data?
Yes. Orders, shipments and tracking events sit in one model, so a late order traces back to the carrier, the lane and the hub where it stalled.
Can Bruin flag a shipping lane the morning it starts to slip?
Yes. Set a rule, like any lane under 90% OTIF, and Bruin checks each morning, posts the orders to the client’s channel and can email the carrier.
Can Bruin show cost per shipment by carrier and lane?
Yes. Linehaul, fuel surcharges and accessorials from the TMS or carrier invoices join to each shipment, so cost is counted the same way for every carrier, lane and client.
Can Bruin build the weekly report for each of our clients?
Yes. Schedule a PDF per client with OTIF, transit time and exceptions, or build the daily ops dashboard from one prompt.
Do we need a data team or data expertise to use Bruin?
No. Connect your WMS and TMS databases and ask in Slack. If you have a data team, Bruin runs on their models and checks.
Can our ops and account managers use Bruin in Microsoft Teams?
Yes. Bruin answers in Slack, Microsoft Teams, Google Chat, WhatsApp, Discord, Telegram, email or the browser. Nobody has to learn a new tool.
Does Bruin need access to our live WMS or TMS?
No. It loads from read replicas, exports or incremental loads, so nothing touches the live systems. Bruin can also run in your own VPC.
How is Bruin different from asking ChatGPT about our shipment data?
A chat assistant only sees what you paste in. Bruin answers from your connected WMS, TMS and carrier data, runs the query itself and shows its sources.
How much does Bruin cost, and is it per seat?
Bruin Cloud is free to start: $100 in credits and 50 AI tasks, no credit card. After that, compute is billed per second (about $2.50 an hour for SQL, $10 on a standard instance) and AI tasks cost $1 to $3 each, depending on complexity. Committed-use discounts lower the rate as usage grows. No seats.
Is our data, and our clients’ data, safe with Bruin?
Bruin is SOC 2 Type 2 attested and ISO/IEC 27001:2022 certified. Your data, your clients’ included, is never used to train AI models.
Call the client before they call you.
$100 in credits and 50 AI tasks. No credit card.
A demo walks through your own data.