A guided technical learning path
Autonomous Post-Training: Build a 1B In-Car Agent
Build RoutePilot, a 1B-class route-aware agent that extracts constraints, calls a maps or POI tool, ranks returned candidates, and proposes a safe next action. The course starts with a deterministic behavioral contract, then moves through licensed synthetic data, baselines, post-training, failure-driven iteration, structural pruning with recovery training, quantization, and publication.
Your Learning Path
Each module builds on the last. Open any published lesson or lab and continue at your own pace.
Built for
Who this course helps
- Learners who meet the course prerequisites
- Independent developers building practical depth
- Teams creating a shared technical vocabulary
What you leave with
A practical body of work from Autonomous Post-Training: Build a 1B In-Car Agent
- Define a testable product contract for a tool-using route assistant
- Generate licensed training scenarios whose labels follow explicit constraints
- Post-train and compare a 1B-class student against teacher and base-model baselines
Move from explanation to worked examples and practice in one coherent learning path.
About This Course
A useful in-car language model should not memorize restaurants, opening hours, traffic, or charger availability. Those facts change. RoutePilot learns the stable part of the job: understand the request, convert it into explicit constraints, select a tool, reason over current results, and explain a proposed action.
The course treats post-training as an experimental system. Every model iteration is evaluated against deterministic hard constraints and ranking utilities. Failures become categorized evidence for the next data pass. No accuracy, latency, or deployment claim is made until a reproducible run is committed.
Course design and benchmark are original to SciMigo. Product and model claims are paraphrased from linked primary sources fetched 2026-09-21. Google, Cerence, Quadrillion, Qwen, and Hugging Face are trademarks of their respective owners; this independent course is not endorsed by them.
Prerequisites
- Comfortable Python and JSON
- Basic familiarity with language-model prompting and supervised fine-tuning
- No prior automotive or edge-ML experience required
What You Will Learn
- Define a testable product contract for a tool-using route assistant
- Generate licensed training scenarios whose labels follow explicit constraints
- Post-train and compare a 1B-class student against teacher and base-model baselines
- Diagnose hard-constraint, tool-call, ranking, and clarification failures separately
- Compare an adapted student with structurally pruned, recovered, and quantized variants on named edge hardware
- Publish a model card, data card, benchmark, and integration boundary without overstating results
Terminology Mapping
How classic concepts map to the terminology used in this course.
| Classic | This Course (Routepilot) |
|---|---|
| Dynamic world knowledge | facts returned at request time by maps, POI, traffic, or charger tools |
| Hard constraint | a condition that disqualifies a candidate, such as closed, wrong connector, or too much detour |
| Soft preference | a weighted signal that orders feasible candidates, such as rating or lower detour |
| Oracle | deterministic code that applies the declared constraints and utility weights |
| Agent action | a proposal that still requires application policy and, when appropriate, driver confirmation |
Start now
Module 1: The Contract Before the Model
Freeze what the agent may know, what it must call, and how a wrong answer fails. About 90 minutes.
Start module 1 — freeHelp shape what we build next
Tell us what you want to learn. This records your interest; it does not enroll you or promise a launch email.