All courses
Track G
Coming soonSafety-critical and AI-assisted design
Two directions hardware design is going: regulated markets that need evidence for every check, and AI agents that run the tools. The agent labs follow the loop shown on lumeeslab.com: the agent compiles, runs CDC, reads the finding, fixes the RTL and runs again until clean, and you review every change, because a human signs off.
- Duration
- 6–8 weeks
- Level
- Advanced
- Before you start
- The four core levels; Python helps.
What you'll learn
- Follow DO-254 and ISO 26262 processes on a hardware project
- Use fault injection and requirements traceability as evidence
- Drive Lumina from an agent with JSON and SARIF results
- Review and sign off agent-made RTL changes
Syllabus
6 topics
- 01
DO-254 and ISO 26262 processes
Safety rule pack · Planned - 02
Fault injection
- 03
Requirements traceability
- 04
Driving Lumina from an MCP agent
MCP server · Planned - 05
JSON and SARIF results for agents
- 06
Agent-in-the-loop RTL repair, with human review
Coming soon
Be the first to know when the courses open.
Write to us to hear when the first courses open, or to talk about a university course or training for your team.
Training
hello@lumeeslab.comHelpful to include
- Who you are, and whether you're learning yourself, teaching, or training a team
- The courses or tracks you're most interested in
- English or Turkish