> ## Documentation Index
> Fetch the complete documentation index at: https://docs-staging.poolside.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Poolside overview

> Poolside provides agentic coding models, APIs, and agent workflows for secure software engineering.

## What Poolside is

Poolside provides agentic coding model weights, APIs, and agent workflows for governments and other organizations that need sovereign AI infrastructure, control over their intelligence layer, and predictable inference costs.

Poolside runs entirely within your infrastructure. You deploy models, inference, and APIs in your virtual private cloud (VPC) or on-premises in your data center, so your code, prompts, and data never leave your environment. This enables AI to operate on production software workflows while you maintain full ownership, data control, and security.

Poolside supports software engineering workflows through:

* **Poolside Agent CLI**: Use `pool` for interactive terminal sessions and `pool exec` for scripts, CI jobs, and other non-interactive workflows.
* **OpenAI-compatible API**: Send model requests from your own tools and automation through the `/openai/v1` API.
* **Self-managed deployment paths**: Deploy Poolside model inference and supporting services within your infrastructure.

## Key capabilities

Poolside provides core capabilities built around models, agents, and controlled execution to accelerate software engineering workflows.

* **Foundation models for software engineering**: Models trained using reinforcement learning from code execution feedback across hundreds of millions of real-world tasks.

* **Agentic workflows**: Agents and multi-agent systems that plan, implement, and iterate on complex tasks such as legacy code refactoring, incident analysis, and security reviews.

* **Knowledge-grounded generation**: Poolside generates code and recommendations grounded in your private documentation, tickets, and internal standards.

* **Controlled execution**: Approval prompts, tool permissions, and sandbox options help you control what agents can do in your environment.

## Common use cases

Teams use Poolside for tasks such as:

* Generating and completing code with awareness of local context
* Explaining unfamiliar or legacy code
* Writing and maintaining code documentation
* Refactoring and modernizing existing systems
* Generating and running tests
* Translating and migrating legacy code
* Automating multi-step engineering tasks using agents
* Investigating incidents and proposing fixes
* Enforcing internal standards using private documentation and policies