# Pitlane — Agentic Optimisation Accelerator

An agentic orchestration layer over an operational workflow. Decomposes job cards into tasks, runs the day's timesheet through a proprietary scheduling optimiser, auto-assigns work, and pushes status to customers.

## Key facts

- **Domain:** OPERATIONAL OPTIMISATION
- **Status:** PoC delivered to a global automotive OEM (abstracted)
- **Use when:** Automotive OEMs or large dealership networks want to retire manual dispatch boards.
- **Reference engagement:** A global automotive OEM operating service centres across MENA

## The problem

After-sales service centres on MENA dealership networks run the same play every day. Receive job cards, decompose them into tasks, assign tasks to bays under capacity and skill constraints, push status updates to customers. Manual dispatch boards make every step lossy.

## The approach

An orchestrator agent ingests each job card, decomposes it into tasks, and routes the request to a proprietary scheduling optimisation engine. The optimiser returns the day's timesheet under the full constraint set; the agent assigns tasks back to the operational system and triggers customer notifications.

## The architecture

FastAPI hosts the orchestrator. The scheduling optimiser is packaged as a containerised service on Google Cloud Run. The agent runtime calls the optimiser as a tool, keeping orchestration thin and the optimisation logic isolated and independently versionable.

## The outcome

A working PoC that closes the loop from job card receipt to assigned timesheet to customer status, with no manual board work. A reusable pattern for any after-sales workflow with similar shape.

## ATI shape

- Predictive intelligence — Capacity-aware scheduling under real-world constraints
- Agentic execution — Orchestrator agent over a proprietary optimiser tool
- Secure data — Customer perimeter respected end to end
- Actionable outcomes — Day-of timesheets and customer status broadcasts

## Tech stack

- FastAPI
- Python
- Google Cloud Run
- Docker
- Scheduling optimiser

## Impact

- Real-time — Day-of timesheet generation
- Multi-bay — Capacity-aware assignment
- Auto — Customer status broadcasts

## Related

- [All accelerators](https://levent.ai/accelerators/)
- [Next: TerrAVia](https://levent.ai/accelerators/terravia/)

Metrics on this page are estimated and expected improvements describing the design intent of the accelerator. Real-client delivered metrics stay in private decks; see https://levent.ai/ai-content-policy/ for the abstraction policy.

---

**Canonical URL:** https://levent.ai/accelerators/pitlane/