Logistics and supply chain

What happens when an agent gets it wrong at 2am?

Shipments, carriers and warehouses run around the clock, and so do your agents. LeafCraft makes failures stop safely and sends work to a backup when a person does not act in time.

One teamYour rulesYour memoryYour budget
Product screen · example dataLeafCraft console
Trusted by
MiVi
mediamint
Bhashini
Neurasix
Wyra

What's changing in logistics and supply chain

01

Exceptions happen at 2am

A delayed shipment, a rejected freight invoice, a reroute. Agents handle them when nobody is awake.

02

Freight invoices are a leak

An agent that approves a freight invoice with no checker is a cost you find at audit.

03

Carriers and 3PLs bring their own agents

Your operation now includes agents from partners you do not control.

Two risks the layer removes

The agents you can't see, and the model that gets retired.

Agents you don't know about

In logistics and supply chain, agents arrive through vendor updates and team pilots. LeafCraft finds all of them, gives each an owner, and brings it under your rules or removes it.

How discovery works

A model that gets retired

An agent built straight on one model has to be rebuilt and re-approved when that model is retired or repriced. On LeafCraft you switch the model for that agent in config and keep everything else. Months and a budget, saved.

Agent tied to one model
  • The model is retired or repriced
  • Prompts, tests and sign-offs rebuilt
  • Months of work, a new approval cycle
  • The history stays with the old tool
MonthsA rebuild budget
Agent on LeafCraft
  • Pick another model for that agent
  • Switching is a config change
  • Test it against your own record first
  • Rules, limits, owner and memory stay
HoursNo rebuild
TimeHours to switch, not months to rebuild
CostNo rebuild budget, no new approval cycle
MemoryThe record carries over to the new model
Your choice of model

Why it matters now

In logistics and supply chain, the agents arrived before the rules did.

Logistics never stops, and the agents that keep it moving make decisions while your people sleep. The layer defines what an agent may do alone at night, what must wait for a named person, and what happens when nobody replies. It records every exception and every reroute, so the morning starts with a record, not a surprise.

What the record answers hereEvery exception, every reroute and every freight decision, with the reason, day and night.
How the layer works

AI and people, one team

Your logistics and supply chain team, with AI on the org chart.

Does the work
Decides
Checks
AI drafts. A person decides. Another agent checks.

The agent prepares the case. Your person makes the call and writes why. A separate audit agent checks the decision against your rules.

Same rules for every seatNo one checks their own workOne named ownerCost set before it runsBoth reasons recorded
No one checks their own workAgent or person. Maker and checker are never the same.
One named owner per decisionNever "the system".
Authority earned from the recordWidens with clean work. Narrows after mistakes.
People stay where they workSlack, Teams, WhatsApp (coming) or email. Their reply moves the work on.

What changes for you

Today
With LeafCraft
Night exceptions handled with no trail
Every night decision has an owner, a rule and a record
Freight invoices approved by the agent that matched them
Maker and checker are never the same
Partner agents acting on your orders
Partner agents fenced in and recorded like your own
Reroute costs discovered at month end
Cost per exception known before it runs
Silence is never a yesEstimated before it runsNothing erased after it's written
Product screen · example dataLeafCraft console
LeafCraft sells no agents, no models and no compute.
NeutralGains nothing from your choice of agent or modelYoursRuns in your cloud, VPC or on-premOpenAny model, any cloud, MCP and A2AEqualBought, built and people, same rules
Why that matters

Questions teams ask

What if something goes badly wrong overnight?

A step that keeps failing is stopped and handed to a person, not retried all night. One switch pauses the whole operation across every server, work in progress included, until you resume.

Can our ops team approve from their phones?

Yes. Requests reach the people you name on Slack, Microsoft Teams, WhatsApp (coming soon), Telegram or email, and their reply moves the work on. Replies over email or Teams are checked to come from the right sender.

Can agents react to events from our TMS and WMS?

Yes. Work can start from webhooks, Kafka, Amazon SQS, MQTT, Redis Streams, an email inbox or a schedule you set.

Bring one logistics and supply chain process.

We'll map it with you: which roles are AI and which are people, who decides, who checks, what it costs and what gets recorded.