all posts
blog · topic

AI agent sandboxes

An agent that runs code, installs packages, or drives a browser needs somewhere to do it that is not your laptop or your production cluster. These posts cover how agent sandboxes work, what coding and browser agents actually need from one, how to scope tool permissions, and how to run many agents in parallel with a hardware-isolated microVM per session.

AI agent sandboxes on PandaStack

206 posts

·8 min read

How to add human approval to agent code execution

The gate that asks about everything gets clicked through by Thursday. The useful design asks about almost nothing, because isolation earns you the right not to ask.

ai-agentshuman-in-the-loopsandbox
Ajay Kumar
·9 min read

The best AI agent guardrail tools in 2026, by layer

Most teams buy one guardrail product and think they're covered. The layers solve disjoint problems, and only one of them is deterministic.

ai-agentssecurityguardrails
Ajay Kumar
·8 min read

How to run SWE-agent in a sandbox

SWE-agent hands a language model a shell over your repository. On a laptop, that shell also reaches your SSH keys. Here is the isolated version.

swe-agentcoding-agentsai-agents
Ajay Kumar
·8 min read

How to sandbox code from Cline and Continue

The approval prompts work — for about a day. Then you turn on auto-approve, and a model has an unattended shell next to your cloud credentials.

clinecontinuecoding-agents
Ajay Kumar
·8 min read

How many sandboxes should a multi-agent system have?

Most teams pick their multi-agent isolation topology by accident and find out which one they picked when it breaks. There are three, and the choice is decidable.

multi-agentai-agentsarchitecture
Ajay Kumar
·9 min read

What is a deep research agent?

Every provider now ships something called deep research. Underneath the label they are the same shape: a loop that keeps searching until it decides it knows enough.

ai-agentsdeep-researchexplainer
Ajay Kumar
·9 min read

How to give a Haystack agent a code execution tool

Haystack thinks in pipelines and components, so the first question is not how to write the tool. It is whether code execution should be a tool at all.

haystackai-agentshow-to
Ajay Kumar
·8 min read

Agent tool permissions, explained

Your agent has six tools and the whole authorization story is "the model decides". Here is where the decision should actually live.

ai-agentssecuritytool-calling
Ajay Kumar
·8 min read

How to hand off work between AI agents

A handoff summary is a lossy channel, and most chains use it as the only channel. Here is what to send instead, and how to hand over the environment rather than a description of it.

ai-agentsmulti-agenthow-to
Ajay Kumar

More posts in this topic