How to use ESP Agent

You describe the task in plain words — the agent writes the code, compiles it, fixes the errors and flashes your board. Below is everything worth knowing on day one. Five minutes of reading saves you a few dollars and a couple of hours.

1. How to brief the agent

The main rule: the agent does exactly what you asked for. It doesn't guess what you meant — it picks the most likely option. The more detail in the brief, the fewer fixes later.

Worth specifying: the pin, timings and speeds, whether you need Serial and at what baud rate, how many files, which library to use (if you have a favourite), and what to do on failure (e.g. "if the sensor doesn't respond, blink the LED").

If the agent asks a question in the chat, just answer with your next message. It asks on purpose instead of guessing when the choice really matters.

2. Why the same request gives different code

This is not a bug, and the agent is not having a bad day. It is how AI models work: they pick words by probability, so two identical answers are impossible in principle. A few more things add to it:

• the agent sees the state: which board is selected, which port, what is already in the project folder, what you discussed earlier;
• the model decides on its own how deeply to think about the task;
• compiler errors get fixed a little differently every time.

Modern models have no "always do it the same way" knob (temperature).

Hence the practical takeaway: refine as you go, in the same chat ("make it 200 ms", "drop the Serial") instead of "rewrite it". In the same chat the agent already sees the finished sketch and changes a couple of lines — that is faster and noticeably cheaper than writing everything from scratch.

3. Four buttons not to mix up

4. If a turn gets cut off

Power lost, app closed halfway, or the reply hit its ceiling — the app starts a new conversation itself and tells you so in the chat.

Your files and sketches are safe. Just write "continue, the code is in the project" — the agent will read the sketch and finish the job. Nothing is lost and nothing needs rewriting.

5. Start vs Pro: what it means in practice

Every model has a reply ceiling — how much it can write in a single turn. That is not the same as how much it can read: reading capacity is huge.

The Start model's reply ceiling is several times lower, and it silently truncates long code — the turn breaks mid-sentence. Pro has plenty of headroom, so it finishes large sketches.

This is an honest difference between the plans, not a setting — no limit can fix it. Simple tasks: Start. Complex projects: Pro.

6. The board

• Don't switch boards mid-task — the agent is already writing code for the selected one.
• If the board in the header doesn't match the chip on the port, the app highlights it in the status bar and refuses to flash. That is a safeguard: over USB an ESP8266 and an ESP32 look identical, and flashing the wrong one never ends well.
• "⚡ Flash anyway" is there for when you know the boards are compatible.

7. Where the money goes

You pay for the model's work, and its reply costs several times more than your question. Everything else follows from that:

• A targeted fix is cheaper than a rewrite. "Change the period" is a few lines. "Rewrite the file" is the whole file again, at full price.
• The real spend is the long "edit → compile" loop. Every round trip through a compiler error costs money.
• A detailed brief saves money. It costs almost nothing as input, but it cuts out those rounds of fixes.

Your balance is visible right in the app, in the status bar.