Skip to main content

Agentic coding workshop for automotive and manufacturing

Vehicle and machine software is developed under process models, safety standards and supplier contracts that leave little room for experiments. Our workshop shows engineering teams where AI coding agents add value in this world and where human engineering judgment must stay in charge.

ISO 9001 & ISO/IEC 27001Certified quality and information securitySince 2014, made in GermanyDiese Seite auf Deutsch

AI agents meet safety-critical engineering

Automotive and industrial software teams rarely work on a single web app. They maintain embedded C and C++ under MISRA rules, AUTOSAR configurations, test automation for hardware-in-the-loop benches, MES integrations and a growing amount of cloud tooling for connected vehicles or machines. Requirements are traced from specification to test, and Automotive SPICE assessments check that the process is followed. An AI coding agent that writes code fast but cannot explain where a change came from creates more work than it saves.

That is why neooutput, the AI education unit of jocapps GmbH, separates the workshop into two zones. In tooling, test automation, data pipelines and internal applications, Claude Code, OpenAI Codex or Cursor can take on large parts of the work under review. In safety-relevant embedded code, the focus moves to explanation, test generation, static analysis findings and documentation, while qualified engineers keep the decisions. Sessions run on-site at your plant or development center or remote, in English or German.

What to watch out for

  • Under ISO 26262, tools that can introduce errors into safety-related work products may need tool qualification. Clarify early how your safety manager classifies AI coding agents before they touch such code.
  • MISRA and internal coding guidelines apply to every line, whoever wrote it. Run your static analysis on agent output as strictly as on manual code and feed the findings back into the agent's instructions.
  • OEM and supplier contracts often restrict where source code may be processed. Check confidentiality clauses and TISAX requirements before connecting repositories to a hosted AI service.
  • Export control and intellectual property matter in industrial code. Some algorithms or calibration data must not leave defined environments, which limits the use of external models.
  • In manufacturing, a change to PLC or MES integration code can stop a production line. Test on simulations or staging cells first and keep commissioning decisions with qualified automation engineers.

What your engineering teams gain

Clear zones for AI use

Teams leave with an agreed map of which repositories and tasks are suitable for agents. That avoids both blanket bans and uncontrolled use in safety-relevant code.

Faster test automation

Agents are well suited to writing test scripts, bench automation and test data generators. Test engineers practise this on examples close to their daily work.

Traceability preserved

We show how to link agent-assisted changes to requirement IDs, tickets and review records. Your ASPICE work products stay complete and consistent.

Legacy and tooling knowledge

Agents can explain undocumented build scripts, code generators and old tool chains. That helps when experienced engineers retire or move to new platforms.

How the workshop runs

  1. Scoping call

    We discuss your product domain, safety level, languages, tool chain and current AI policy.

  2. Zone mapping

    Together with your leads we classify repositories and tasks into suitable, restricted and excluded areas.

  3. Hands-on labs

    Engineers work with the agent on tooling, test automation and code explanation tasks using sample or approved code.

  4. Process integration

    We document how agent use fits your review, traceability and qualification processes for a pilot.

Matching products

neooutput

Agentic coding workshops and AI services. Hands-on agentic coding workshops for teams on Claude Code, OpenAI Codex and Cursor, remote or on-site, in English or German. Plus AI Code Engineers on demand who deploy, secure and scale AI-built apps.

Explore neooutput workshops

Frequently asked questions

Can AI agents write safety-critical embedded code?

They can produce drafts, but in safety-relevant code we recommend using them mainly for explanation, review support and test generation. Final implementation decisions and verification stay with qualified engineers under your safety process.

Does the workshop cover PLC programming?

We can include IEC 61131-3 code and automation interfaces if your teams work with them. Agent support for these languages varies, so we focus on documentation, test cases and code review rather than unsupervised generation.

Can the workshop take place at our plant?

Yes. On-site sessions are possible, which helps when code may not leave your network or when teams want to work directly with their own environments.

Which tool fits engineering teams best?

It depends on your IDEs, operating systems and security policy. We compare Claude Code, OpenAI Codex and Cursor against your setup during the scoping call.

Let's talk about your project.

15 minutes with an AI Code Engineer, free and without obligation. Or call our team around the clock.