Skip to main content

​
What Poolside is

Poolside is a secure, full-stack AI platform for software engineering. It provides foundation models and agentic systems that help teams write, understand, test, refactor, and operate complex codebases in production. 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 is available wherever your software work happens:
  • In the IDE: Poolside Assistant brings agent-based workflows and code assistance into VS Code, Visual Studio, or any IDE that supports Agent Client Protocol (ACP).
  • In the browser: Poolside Web Assistant provides chat-based interactions outside the IDE.
  • In CI/CD pipelines and headless environments: Poolside Agent CLI (pool) runs and manages agents in automated workflows.
  • In the Poolside Console: A browser-based administrative interface for metrics, governance, and system management.
  • Across your stack: APIs let you integrate Poolside into your own data, tools, and automation.

​
Key capabilities

Poolside provides core capabilities built around models, agents, and embedded expertise 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.
  • Enterprise-grade governance: Built-in access controls, auditability, and policy enforcement ensure every action taken by a model or agent is traceable and accountable.
  • Embedded research engineering: Forward Deployed Research Engineers embed with your teams to help design, build, and operate AI systems directly within 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