Auto components

If an agent accepts an OEM schedule change, who answers for it?

Schedules, PO changes and quality calls move fast between you, your OEMs and your suppliers. LeafCraft puts agents and people on those calls under your approval levels, with every decision recorded.

One teamYour rulesYour memoryYour budget

Book a demo Experience now

LeafCraftto Arjun Mehta, Plant planning head · 10:42

OEM schedule change above the agent's limit

ItemOEM-2 · Week 46 · +18% on part 7731-BWhy youAbove the agent's limitAgent saysAccept. Material and line capacity are available.WaitingMoves to Sunita Rao, Supply chain head, in 2 hours

Your reason (required): "Overtime approved for week 46."

ApproveSend backReject

Your reason is saved in the record, next to the agent's reason.

Decision request in Microsoft Teams · example dataLeafCraft console

Trusted by

What's changing in auto components

OEM schedules change weekly

An agent that accepts a schedule change commits your plant. Someone must answer for it.

Quality claims cut both ways

Supplier claims and OEM rejections both need a decision with a reason, not a reflex.

Tier 2 and 3 suppliers run their own agents

Your supply chain now includes agents you did not build and cannot see.

Two risks the layer removes

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

Agents you don't know about

In auto components, 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.

Inside software you buySwitched on by vendor updates

CRMERPHR systemService deskOffice suite

Built by your teamsPilots, scripts and side projects

LangGraphCrewAINotebooksAutomationsCopilot studios

LeafCraft connects to your ecosystem and finds every agent

One registerexample counts

23found

9no owner yet

11governed

3retired

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 auto components, the agents arrived before the rules did.

Auto components live between OEM demands and supplier limits. The agents that read schedules, raise purchase orders and answer quality claims make commitments on your behalf. The layer makes sure each commitment has a named owner, stays inside a limit the agent earned, and lands on a record you can show the OEM.

What the record answers hereEvery schedule accepted, every PO raised, every claim answered, with the reason.

How the layer works

OEM portal connectors

ERP planning agents

Quality system plug-ins

Plant engineer laptops

No shared owner · no shared limit · no shared record

LeafCraftone layer, on your side

One ownerper decision, AI or person

Your ruleson every run

Your memoryboth reasons, your database

Your budgetset before work runs

The core infrastructure

What LeafCraft runs for auto components.

One team

Schedule, PO and quality calls go by impact to named people: the purchase manager, the plant head, then senior leaders.

How it works 02

Your rules

You decide what planning, procurement and maintenance agents may change alone, what needs a person, and what they may never touch, such as a released drawing.

How it works 03

Your memory

Every PO change, schedule call and quality claim is kept with the reasons of the agent and the person, on your side for OEM and audit reviews.

How it works 04

Your budget

Every task, agent and agent type has a cost limit set before the work runs, charged to the plant or the programme.

How it works

Build and control a smart ecosystem

A connected ecosystem for your parts, under your rules.

Your components now report from the vehicle, and agents act on what they report: flagging wear, opening quality cases, triggering service, feeding the OEM. LeafCraft lets you build that ecosystem across OEMs, fleets and service networks and keep control of it. Each agent acts within a rule, each action has a named owner, and the record follows the part from the line to the end of its life.

Parts on the roadTelematics, wear, faults

OEM and fleet systemsSchedules, claims, recalls

Service networkReplacements, repairs

Plant and suppliersTraceability, quality

LeafCraftyour rules · your memory · your budget

MQTTKafkaREST APIsWebhooks

Govern actions across OEM, fleet and service

What an agent may change on a schedule, open as a claim or trigger in service, and where a named person decides.

Traceability as memory

Every part's quality checks, field reports, claims and service actions, with the reason, kept for as long as liability runs.

Audit for recalls and OEM reviews

Show which batches, which vehicles, what was decided and by whom. Export it in open formats on demand.

OEMs and tier suppliers inside it

Their agents and people join under your rules, with their own logins and limits, and leave the same record.

Devices, events and platforms LeafCraft connects to

AI and people, one team

Your auto components 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

Schedule changes accepted by an agent, owner unclear

Every accepted change has a named owner and a reason

POs raised at night, discovered in the morning

Above the limit, the agent waits for a person. Silence is never a yes.

Quality claims decided from a thread

One record across the claim, the test and the decision

Planning agent cost unknown

Estimated before each run, capped per agent

Silence is never a yesEstimated before it runsNothing erased after it's written

BudgetEvery model call is checked against these limits before it is made

This month

Per task · schedule checkEstimated before it runs

2.10 / 5.00

Per agent · Planning agentMonthly limit

4,600 / 8,000

Per agent type · PO agentsShared by 3 agents

7,700 / 10,000

Per decision · quality claimsEstimated before it runs

5.30 / 15.00

Before the next task runs

Estimate1.90 on the current modelModelChosen by you per agent. Switching is a config change.If over limitStops and asks the owner. It never runs on silence.

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

How it helps your people

Who it helps in auto components.

Leaders who ask first

COOs and supply chain headsWhat happens when an agent changes a PO or a supplier order at 2am?Read CFOs and finance leadersWhat does each AI decision cost, and can I show my auditor who approved it?Read CIOs, CTOs and IT headsVendors shipped agents and my teams built others. How do I govern all of them from one place?Read AI implementation teams and forward deployed engineersHow do I get an agent from demo to production without building the control layer myself?Read

Functions where it runs

Supply chain and procurementWhat stops an agent from changing a supplier order it should not?Read FinanceCan I show my auditor who approved each payment, and why?Read IT operationsAgents can now grant access and change cloud settings. Who checks them?Read

Questions teams ask

Our ERP vendor is adding its own agents. Why do we need another layer?

Your ERP vendor governs the agents on its own stack. LeafCraft holds one set of rules and one record for every agent, bought or built, and for your people, on your side.

Can we start with one process?

Yes. Pick one process, mark each role as an AI agent or a person, and give each a checker and an escalation path. Ready-made templates for production planning, procurement, quality and maintenance give you a starting team.

Can it run inside our plant network?

Yes. LeafCraft runs in your cloud account, your VPC or on-prem, with run records in your own Redis or Postgres.

Bring one auto components 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.

Book a demo Experience now