What is Laguna by Poolside?

Laguna is a foundation model from Poolside, a frontier AI lab focused on building the most capable Foundation Models, agents, and enterprise systems. Designed specifically for long-horizon work, Laguna powers software agents that can plan, reason, and execute complex tasks across enterprise environments. It represents Poolside's strategic beachhead toward artificial general intelligence, starting with the hardest problems in high-consequence software development.

Who it's for

• Enterprise engineering teams that need AI capable of handling multi-step reasoning and long-horizon objectives inside strict security boundaries
• CISOs and compliance officers who require on-premise or VPC deployment with data never leaving organizational control and executive-grade governance
• Forward Deployed Research Engineers who embed with customer teams to design, build, and operate intelligence where software work actually happens

Key features

Foundation Models deployed in your environment

Laguna runs inside your own infrastructure—on-prem, in your VPC, or on workstations for defense applications. Models are measured against evaluations created together with you, ensuring relevance to your specific use cases.

Agents and Multi-Agent Orchestration

Single and multi-agent systems that can plan, use tools, and execute in sandboxed environments. All agent activity is governed by policies and captured in end-to-end traces for full auditability.

Developer Surfaces

Laguna integrates across your development ecosystem through agents, terminal user interfaces, IDE extensions, binaries, and workflows that move with your engineers. Intelligence reaches everywhere work gets done.

Data and Knowledge connectors

Secure connectors to repositories, databases, data warehouses, and private corpora operate within strict boundaries, allowing Laguna to access and reason over your proprietary knowledge without exposing it.