Validate firmware in simulation with AI agents
Simantic gives AI agents virtual devboards and a firmware code reviewer so they can test firmware without physical hardware. ·
Done with a custom-built or unnamed agent
- What they did
- Simantic gives agents virtual devboards that can be programmed and run with one API call from the terminal, backed by a simulation engine the founders rewrote in Rust after a Renode wrapper proved too slow and inaccurate. An AI reviewer uses the simulation as evidence for firmware decisions, and CI validates each commit against a simulated microcontroller.
- How it went
- The founders say validation that took hours on devboards now takes seconds. An early satellite startup tested firmware on hardware it lacked, at about a hundredth of the cost and time. Chip support is limited to some STM32, ESP32 and RP2040 models.
- Worth knowing
- Supported models are limited to certain STM32F0/F4/H7, ESP32-S3/C3 and RP2040 parts, so check your microcontroller is covered first.
Try it yourself with Claude Code
I'm developing firmware for [board or microcontroller] and don't always have the hardware on hand. Set up a simulation workflow, using an emulator like Renode or QEMU if one exists for my board, so you can build my firmware in [repo path], run it virtually, and check that it behaves as expected for [behavior to verify]. Then review the code for bugs such as race conditions and bad register use. You're done when you've run the simulated tests and given me a pass/fail report with the issues you found.
Want help getting this working? Join the Vibe Coding Academy ↗ Run by Alex Finn, who also runs this site.
Source: HN · Oct 29, 2026
Related use cases
Build a C compiler with a team of parallel agents
Anthropic's engineering write-up on tasking Opus 4.6 agent teams with building a C compiler.
One-shot a CLI coding agent on top of a Python LLM library
Simon Willison had the Fable model more or less one-shot a CLI coding agent built on his LLM Python library.
Custom agent
Rewrite a README after a rearchitecture
Devin scanned a rearchitected codebase and delivered a new README as a PR with accurate setup and API details, but struggled with design rationale and purpose.
Replace token-heavy Jira and GitLab MCPs with CLI skills
The author had Claude run --help on Atlassian and GitLab CLIs, saved the actions as Markdown, and built lightweight agent plugins that cut token use.
Have Copilot coding agent write and push code
A developer found the agent good at context and code, but it pushed to a branch leaving main empty and spent hours checking after being told to proceed.
Screen interview code submissions with a Codex review agent
A commenter uses Codex with a targeted agents.md for front-line code reviews, rejecting submissions with too many files changed or added.
Get 5 like this every morning
The best things people got an AI agent to do, each with the prompt to try it.