Usage, Energy, and Privacy

How ProtoBot energy (Wh) works, tips for getting more out of it, and what happens to your data when you use AI features.

Energy (Wh)

ProtoBot usage is measured in Energy, using Watt-hours (Wh) as a themed credit unit. Wh is a product credit unit within Protoboard; it does not represent literal electrical power.

Every plan includes a daily energy allowance that refreshes every 24 hours from your first message. The battery icon in the ProtoBot panel shows your current balance. When energy runs out, ProtoBot pauses until your allowance refreshes; the rest of Protoboard (canvas, parts library, DRC, BOM, sharing) keeps working.

Your current allowance and remaining balance are always visible in the app. Allowance amounts are not listed here because they change as the product evolves.

What consumes energy

Three things drive cost:

1. Model choice. More capable models cost more per interaction: gpt-5.4 (the default) is the efficient option, and gpt-5.5 costs more. The model selector shows relative pricing.

2. Reasoning effort. The reasoning-effort control next to the model selector sets how much the model thinks before acting. Higher effort handles hard problems better but uses more energy; Medium is the default, and Low or Off keep routine work cheap.

3. Task size. A short question ("What's on my board?") costs little; a multi-step workflow ("find a regulator, place it, wire it, run DRC") chains many tool calls and costs more.

Getting more out of your energy

• Stay on the default model for routine tasks; switch up only for genuinely complex workflows, and switch back after.

• Combine related actions into one message: "Create a harness, auto-link interfaces, and run DRC" costs less than three separate exchanges.

• Be specific. One well-constrained prompt replaces several vague back-and-forths. See prompt patterns.

• Use auto-link and auto-allocate instead of wiring connections one at a time.

• Start a fresh session when switching topics. Long sessions accumulate context that must be processed with every message.

---

Data and Privacy

Using ProtoBot means your design data flows through an AI provider. Here is exactly what that involves.

What gets sent

When you message ProtoBot, the request to the model includes your board data (parts, interfaces, harnesses, allocations, BOM, name, notes, requirements, tasks) and your conversation (messages, responses, tool inputs and outputs). There is no way to use ProtoBot without sending board data to the AI provider.

Where it goes

ProtoBot runs on OpenAI models, so requests are processed by OpenAI's API servers. Sessions and messages are also stored by Protoboard so your history persists. For provider-side handling, see OpenAI's API data usage policies.

What not to include

Never paste credentials, API keys, or passwords into the chat. They would be sent to the AI provider and stored in your session history.

Also avoid: personally identifiable information about end users, trade secrets, regulated data (HIPAA, ITAR, EAR), and financial details. Technical content (constraints, part numbers, protocols, pin mappings, BOM data) is what ProtoBot is designed for.

Sensitive projects

• Typical prototypes: component specs and connection topology are not inherently sensitive; focus your review on correctness rather than exposure.

• Proprietary designs: use ProtoBot for the standard portions (power supplies, common sensor interfaces) and handle trade-secret subsystems manually. Check your organization's policy on third-party AI tools.

• Regulated industries: designs under HIPAA, ITAR, ISO 13485, DO-178C, or similar frameworks may restrict third-party AI processing. Consult your compliance team first.

The Privacy Policy and Terms of Service are the definitive documents governing data use.