Skip to main content

Forward Deployed
Engineering

We mine the automotive gold
that no search engine will ever reach.

Even the most capable model is only the drilling rig. The gold is extracted on site — where confidential design assets and the tacit knowledge of field engineers lie buried — by domain specialists led by an AI Champion.

SEARCHABLE Above the line · public data (crawlable) WATERLINE TACIT · CONFIDENTIAL Below · tacit knowledge · NDA = the gold (unsearchable) BMS · code → spec recovery NL → CAPL scenarios NL → ARXML generation E-Drive thermal prediction Simulink ↔ C conversion & diagnosis Thermal Mgmt · HITL verified SAD·SDD auto-generated · 100% traceable SecOC secure comms
BELOW THE SURFACE

Even the most advanced AI needs a partner in automotive

The AI industry has already converged on one answer: go direct where outputs can be verified, and partner with domain specialists where the gold lies unverifiable. Automotive is that gold.

STEP 01

Where it can be verified, they go direct

Coding, law, biology — domains where inputs and outputs are unambiguously verifiable. Builders of powerful AI enter these directly, without partners, because the model can check its own answers and learn without limit.

RLVR · Verifiable Reward
STEP 02

But the real value sits below the surface

The knowledge that makes verification possible exists only in public data. What actually runs an industry lives in the tacit knowledge inside expert minds and in client confidential assets — gold that no search will surface.

Tacit Knowledge
STEP 03

In automotive, almost everything is confidential

Design documents, requirements and control logic are almost entirely proprietary, beyond the reach of any crawler. The more powerful the model in hand, the more urgently one needs a domain specialist who knows where the gold is buried.

Domain Gap

The drilling rig (the foundation model) already exists.
The gold is extracted by the specialists who go on site. — Those specialists are PopcornSAR.

THE SPECIALIST

The rig exists. The mining is ours.

Holding a foundation model and knowing the automotive domain are two different capabilities. PopcornSAR holds both — eleven years of embedded and AUTOSAR engineering, and PARVIS, our own AI toolchain.

The Rig · Equipment

Foundation Model

World-class foundation models. Powerful — yet blind to the automotive domain and to the confidential floor where the work happens.

provides
the rig
The Specialist · PopcornSAR

A domain team led by an AI Champion

Eleven years of automotive embedded and AUTOSAR engineering, plus PARVIS. An AI Champion fluent in both domain and AI leads on site, holding the verification tooling and extracting the gold.

deployed
on site
The Gold Mine

The client floor

Confidential design assets and the tacit knowledge of field engineers. Real value emerges only here, where nothing is searchable.

THE MISSING VERIFIER

Every domain has a grader.
Every domain but automotive — until now.

One criterion decides which domains AI enters directly: whether correctness can be graded mechanically. PopcornSAR exists to install that grader in automotive.

CodingSoftware
Who decides whether generated code is correct?
=
The compiler and test suite grade it instantly
LegalJurisprudence
Who decides whether the generated reasoning holds?
=
Case law and statutory databases settle it
BioLife Sciences
Who decides whether the generated design works?
=
Experiment and simulation verify it physically
AutomotiveSafety-Critical
Who decides whether generated specs, code and tests are right?
=
PopcornSAR's deterministic toolchain grades it
GATE ARXML schema & interface validation GATE Requirement–design–test traceability validator GATE Artifact integrity verification GATE MISRA & coding-rule auto-compliance GATE In-vehicle bus (CANoe) measurement cross-check GATE Domain expert & client HITL sign-off
HOW WE DELIVER

How Forward Deployed Engineering works

Nothing leaves the client boundary. Every AI artifact must pass a human verification gate.

01
Led by an AI Champion

On site, led by an AI Champion

An AI Champion fluent in both domain and AI embeds inside the client network and leads the team. One person owns the work from problem definition through verification, and confidential material never leaves the room.

02
On-prem / Local LLM

Deployment without exposure

Three on-premise configurations matched to the client environment — private cloud, lightweight Mac Studio, and NVIDIA server room. Local LLMs supported.

03
Tool-in-the-Loop · HITL

The verification gate

AI-generated artifacts must clear deterministic tool validation and expert-plus-client review (HITL). Safety and real-time code always requires final expert approval.

04
Tacit → Explicit

Tacit made explicit

Scattered design assets and field knowledge are consolidated into Automotive SPICE-conformant documentation — including reverse engineering back up the V-cycle.

IN THE FIELD

On these unsearchable floors,
PopcornSAR is already forward deployed

Battery Management · BMS
Sample analysis → artifact recovery

Recovering requirement specifications and test cases from production control source code

Task
Production BMS code with upstream documentation lost; the rationale survived only in one engineer's head
Team
Source sample received under NDA; on-premise analysis pipeline stood up
Result
Draft requirement specification and test cases within one week; technical validation passed
On-premNDAReverse
Model-Based Development · MBD
Bidirectional conversion & diagnosis

Automating MATLAB/Simulink ↔ C code conversion and diagnosis

Task
An organisation mid-transition to MBD; models and legacy C coexist, with consistency checked by hand
Team
Simulink and Stateflow environments built in-house; conversion and diagnosis workflow designed
Result
Model-to-code cross-diagnosis automated; migration risk surfaced early
SimulinkCDiagnosis
Bus Verification · CAPL·CANoe
From natural language to executable code

Translating natural-language intent into CAPL test scenarios

Task
A verification team dependent on CANoe and CAPL, with scripting bottlenecked on a few experts
Team
Intent-to-CAPL translation pipeline with a measurement cross-check gate
Result
Non-specialists can now express scenarios; experts concentrate on review
NL→CAPLCANoe
AUTOSAR Architecture
Multiple AUTOSAR releases & languages

Generating ARXML from natural language, validated against schema and custom rules

Task
ARXML conventions differing by release and internal rule — undocumented tacit knowledge
Team
NL-to-architecture and SW-component generation, double-validated by schema and custom rules
Result
Multi-release design automation; artifacts passing interface validation
ARXMLSchema checkMulti-release
E-Drive · Integrated Thermal
Air-gapped premise · embedded on site

Generating supplementary domain data as co-input, verified through client HITL

Task
Source requirements alone were insufficient as AI input; domain knowledge scattered across teams
Team
Domain engineers hand-authored supplementary data as co-input, with a client review loop
Result
Verification automation established under air-gapped conditions; client approval gate institutionalised
Air-gappedHITL
Wireless Charging Controller
Requirement–design–test traceability

Auto-generating an SAD and 29 SDD documents while preserving full traceability

Task
A full English design document set for an overseas client — unachievable by hand within schedule and consistency limits
Team
SAD + 29-SDD generation pipeline with a traceability validator and anti-hallucination gate
Result
Full English artifact set generated; 100% traceability validation passed
SAD/SDDTraceabilityEnglish output
— Premium OEM change-request workflows, rotor–stator thermal prediction, and more, currently in progress —
WHY POPCORNSAR

Not generic FDE. Automotive FDE.

Few companies can transplant the verifiability AI depends on into a domain where the documents themselves are confidential.

Verifiability, transplanted

Tool-in-the-Loop deterministic gates make quality reproducible in automotive.

Confidentiality preserved

On-premise and local LLM deployment keeps data inside the client boundary.

Standards-conformant

Delivered on processes aligned to Automotive SPICE, ISO 26262 / 21434 and ASIL.

Led by an AI Champion

People fluent in both domain and AI lead the floor. Tools do not own outcomes; people do.

Domain & language coverage

Eleven years in automotive, operating across Korean, Japanese, Chinese and English.