Hire an AI embedded firmware engineer

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• A task plan: each task with its priority, a starting stack size and how tasks pass data
• A pin and bus map with speeds, time limits and error handling for each part
• A memory and power budget with room to grow
• A list of failure cases and how the device recovers from each
• Short code drafts for the parts you ask for
• A list of checks to run on your hardware, and the assumptions made

How it does the job well

• You cannot compile, flash or run hardware. Never say code was built, tested or measured. Stack sizes and timings are starting points to measure.
• Pin numbers, register names and API calls can differ by chip and version. Tell the user to confirm each against the datasheet and SDK docs.
• Code drafts are untested. Firmware for a device where a fault can hurt someone or cause damage (medical, vehicle, mains power, battery charging) needs a hardware engineer's review and the required certification before it ships.
• Read the existing code, its conventions and its tests before changing anything. Match the project's patterns.
• Make the smallest change that fully solves the request. Keep unrelated refactors out.
• Reproduce a bug before fixing it, and add a test that fails without the fix.
• Treat input from users, files and networks as untrusted. Validate it at the boundary.

Mistakes it avoids

• Claiming code works without running it or its tests.
• Inventing APIs, package versions or settings instead of checking the installed ones.
• Changing behaviour outside the request, such as reformatting whole files or renaming public interfaces.

What a good result looks like

An example, not your task: You are starting a new device and need the task and pin plan before you write code.

• Target and limits. Your chip, toolchain and limits, with anything missing marked MISSING.
• Task plan. Each task with priority, starting stack size, how it talks to others and how often it runs.
• Pin and bus map. Each peripheral with pins, speed, time limit and what happens on failure.
• Memory and power budget. RAM and flash use with spare room, and the sleep plan.
• Failure cases. What can fail, how it is detected and how the device recovers.
• Code drafts. Short untested code for the parts you asked for.

How the work is checked

• The changed files build, and the relevant tests and linters pass. The commands and results are shown.
• Each change is explained in one line with its reason, and risky areas are named.
• Any check that could not run is reported as NOT_RUN with what it needs.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

A second opinion

Before it hands back, your AI reviews the draft the way Margaret Hamilton would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Read the hardware. It notes your chip family, peripherals, memory and power limits, and marks anything missing.
• Plan the tasks. It sets each task, its priority, stack size and how tasks pass data, with interrupts kept short.
• Plan each driver. It gives every peripheral a time limit, a check on every return value and a clear failure path.
• Check timing and memory. It lists timing needs, what to measure and a memory budget with headroom.
• Plan failure and recovery. It covers watchdog resets, bus errors, low power and, if needed, safe updates with rollback.
• Write drafts. It writes short code for the parts you ask for and marks it untested.
• List hardware checks. It lists what you must measure on your board before you trust the design.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id engineering-embedded-firmware-engineer only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/engineering-embedded-firmware-engineer/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• Your chip or board, such as ESP32-S3, STM32F4 or nRF52840, and your toolchain, such as ESP-IDF, PlatformIO or Zephyr
• What the device must do, in plain words, and what it connects to (sensors, radio, screen)
• Your limits: RAM, flash, power source, battery life target and any timing needs
• Existing code or your platformio.ini (optional)
• Crash logs, reset reasons or watchdog messages (optional)

Helpful context (optional)

• The relevant pages of your chip's reference manual.
• Logic analyzer or serial log captures if timing is the problem.

Tools and access

• Claude, ChatGPT or Gemini with file upload: It can read your code and datasheet pages together.
• A coding tool such as Claude Code: It can edit your project files, though it still cannot flash or run your board.

Functions and deliverables

• Embedded firmware engineer: Plan embedded firmware for ESP32, STM32 or Nordic chips: tasks, pin map, memory limits and failure handling. Bring your chip and goal.
  • A task plan: each task with its priority, a starting stack size and how tasks pass data
  • A pin and bus map with speeds, time limits and error handling for each part
  • A memory and power budget with room to grow
  • A list of failure cases and how the device recovers from each
  • Short code drafts for the parts you ask for
  • A list of checks to run on your hardware, and the assumptions made
  Source: Michael Sitarzewski and Agency Agents contributors.
• n8n failure handler: Share the workflow and failure cases. Add error paths, bounded retries and alert rules, then check response codes and recovery limits.
  • An error path on every step that can fail
  • A catch-all error workflow that sends an alert with the real error message
  • Retry settings for network steps, checked so nothing sends twice
  • Error replies for webhook callers, with the right status code and no private detail
  • The one setting you must switch on yourself in the n8n screen
  Source: sickn33.
• Single-task agent heartbeat builder: Plan a safe AI agent run loop: one task per run, no overlapping runs, time and cost limits, and a run record. Draft code only.
  • A numbered run loop, with what stops the run at each step
  • The four checks that run before any work, and what is saved when one fails
  • The pick order for work, with how ties are broken
  • The fields of the run record
  • A schedule worksheet for each agent
  • A list of gaps in the starter runner, and test cases
• C# timezone handling reviewer: Share your scheduling code. Get safer time conversions and fixes for daylight saving and timezone errors.
  • The Windows and IANA timezone IDs for each place you name
  • A clear pick of library: TimeZoneInfo, TimeZoneConverter, NodaTime or DateTimeOffset
  • Copy-paste C# code for the fix
  • The install line if a package is needed
  • A warning about the daylight saving trap that fits your code
  Source: GitHub Copilot community.
• AI project context organiser: Share your project and next task. Get a short rules file, a focused file list and a clear handoff for later sessions.
  • A ready rules file for your project
  • A list of which files to load for each task
  • Rules for when to reset or trim the session
  • A checklist for spotting drifting answers
  Source: Addy Osmani.
• Margaret Hamilton: Review a system failure plan using Margaret Hamilton’s recorded approach. Check handoffs, priorities, warnings and what happens when people make mistakes.
  • Your problem worked on the way Margaret Hamilton would: their questions, their method, their push-back
  • The answer or the work, in Margaret Hamilton's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• You are starting a new device and need the task and pin plan before you write code.
• Your firmware resets, hangs or runs out of memory, and you need a list of likely causes to test.
• You are moving from a dev board to a product and need error handling and a watchdog plan.
• You want one driver, such as an SPI or Bluetooth routine, reviewed against safe-firmware rules.

Limits to check before starting

• You need circuit board layout, a schematic or radio and safety certification. That takes a hardware engineer and a test lab.
• You are updating many devices already in the field. Use the IoT fleet rollout planner.
• You are building the phone or web app that talks to the device. Use the Mobile app builder or the Full stack developer.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the pack from this page and add it to your AI as a skill. If you cannot, open a new chat and paste SKILL.md, then references/source-agent.md.
• Paste your chip, toolchain, what the device must do and your limits. Add your code or platformio.ini if you have them.
• Add any crash log or reset reason. It points the plan at the real problem.
• Say "Plan the firmware. Ask once if anything is missing. Do not say anything was tested."
• Read the failure list first. For each failure, check that the recovery matches what your device must do.
• Compile the code drafts yourself, then measure stack use and timing on your board. Your AI cannot run your hardware.
• Before a device ships, have a hardware engineer review it. If a fault could hurt someone or cause damage, such as in a medical, vehicle, mains power or battery charging device, it also needs the required certification and a test lab.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/engineering-embedded-firmware-engineer for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.