Newsletter

Stay in the loop

Get new posts and product notes—occasionally, not daily.

  • Practical insights you can use.
  • New posts delivered to your inbox.
  • No spam, unsubscribe anytime.

We’ll only use this to send blog updates.

Why Ideavo uses E2B sandboxes

Insights
· 5 min read

If AI can generate code, it also needs a place to run that code.

That is exactly why we are writing this blog.

A lot of builders see “sandbox” in Ideavo and understand that it is part of the product, but not necessarily why it exists, why we ask for an E2B key, or why we chose this setup in the first place.

The short answer is simple: generated code needs a real execution environment, and we believe that environment should stay transparent, affordable, and under your control. That is why Ideavo integrates with E2B instead of hiding code execution behind our own servers.

What is a sandbox?

A sandbox is an isolated runtime environment where code can run safely without affecting the rest of your system.

Think of it as a separate computer created just for the task at hand. Code can run there, dependencies can be installed, files can be created, and commands can be executed, all inside an isolated environment instead of directly on your machine or inside shared platform infrastructure.

That isolation matters a lot when AI is involved, because generated code is only useful if it can actually be executed, tested, and refined in a real environment.

Why is a sandbox required?

AI-generated code is not finished the moment it is written.

It usually needs to be:

  • executed

  • tested

  • debugged

  • iterated on

  • connected to files, packages, or terminal commands

Without a sandbox, an AI product can generate code, but it cannot meaningfully run that code in a secure and controlled way.

That makes the sandbox essential. It is the execution layer that turns generated code into a working development loop.

If you want an app builder to do more than just output code snippets, it needs a real runtime behind it.

What is E2B?

E2B is an open-source runtime for executing AI-generated code in secure cloud sandboxes. E2B describes its sandbox as a fast, secure Linux VM created on demand for an agent, with support for running code, commands, filesystems, and more.

In simple terms, E2B gives AI products a dedicated isolated computer in the cloud where generated code can actually run.

That makes it a strong fit for products like Ideavo, where code execution is part of the product experience, not just an optional extra.

Why Ideavo asks you to bring your own E2B account

Because we want sandbox execution to stay transparent, affordable, and under your control.

1. Cost: Ideavo gives cost-to-cost API usage

Ideavo is built around transparent usage. The same principle applies to sandbox execution.

Running our own managed sandbox layer for every user would mean adding another infrastructure cost on top of the platform. That would either introduce markup or force sandbox usage into a more opaque bundled pricing model.

We do not want that.

By asking you to connect your own E2B account, sandbox billing stays direct. You pay E2B for sandbox compute, and that compute remains outside a hidden platform markup layer.

That keeps the model simple:Ideavo handles the product experience.E2B handles the sandbox runtime.You keep visibility into where compute costs come from.

E2B also publicly states that new users receive $100 in free credits, which is enough to get started and can cover multiple projects depending on usage.

2. Ownership and security: your code runs in your sandbox

The second reason is control.

When you connect your own E2B account, the code runs in a sandbox attached to your runtime provider account, not inside a hidden Ideavo-owned execution layer.

That matters because code execution is a sensitive part of the stack. Builders should know where code is running and who controls that environment.

Using your own E2B key keeps the sandbox layer closer to you. It gives you clearer ownership of the runtime, clearer billing, and a cleaner separation between the product interface and the execution environment.

That is a better model than asking users to blindly trust a black-box runtime they cannot see or control.

Sandbox Compute Selection

Not every project needs the same sandbox setup.

Some projects only need a lightweight environment for everyday coding tasks. Others become heavier over time more dependencies, larger builds, more background processes, or workflows that simply need more resources to run smoothly.

That is why Ideavo lets you choose the compute tier for your sandbox directly from project settings.

You can select between:

  • Default - 4 vCPU / 4 GB RAM - a balanced setup for everyday coding tasks

  • Pro - 8 vCPU / 8 GB RAM - more compute for heavier, more resource-intensive workflows

This becomes useful when your project gets more complex or when your sandbox starts feeling slower than usual. If your app is installing more packages, running larger builds, or handling more demanding workflows, moving to a higher compute tier gives the sandbox more room to work with.