# Poolside

> Official documentation for Poolside, including setup, CLI workflows, API usage, model deployment, and reference material.

## Docs

- [AGENTS.md instructions](https://docs-staging.poolside.ai/agent-instructions.md): Set up instructions for Poolside across personal, project, and directory scopes.
- [Authentication](https://docs-staging.poolside.ai/api/authentication.md): Use API keys to authenticate Poolside API requests and CLI automation.
- [OpenAI API examples](https://docs-staging.poolside.ai/api/openai-api-examples.md): Make OpenAI-compatible API requests to Poolside models.
- [API overview](https://docs-staging.poolside.ai/api/overview.md): Get started with the Poolside OpenAI-compatible API and CLI automation authentication.
- [Automated mode](https://docs-staging.poolside.ai/cli/automated-mode.md): Use `pool exec` to send a one-shot prompt and exit.
- [CLI reference](https://docs-staging.poolside.ai/cli/cli-reference.md): Reference for current Poolside Agent CLI shell commands, slash commands, and flags.
- [Editor integration (ACP)](https://docs-staging.poolside.ai/cli/editor-integration.md): Use Poolside in Zed, JetBrains, Neovim, and other ACP-compatible editors with `pool acp`.
- [Install Poolside Agent CLI](https://docs-staging.poolside.ai/cli/install.md): Install pool and authenticate.
- [Interactive mode](https://docs-staging.poolside.ai/cli/interactive-mode.md): Use `pool` to work with a Poolside agent over multiple turns in the terminal.
- [Poolside Agent CLI](https://docs-staging.poolside.ai/cli/pool.md): Work with Poolside agents from your terminal, scripts, or editor.
- [Troubleshoot Poolside Agent CLI](https://docs-staging.poolside.ai/cli/troubleshooting.md): Diagnose common Poolside Agent CLI authentication, configuration, and ACP issues.
- [Install on Amazon EKS](https://docs-staging.poolside.ai/deployment/cloud/aws-eks/install.md): Deploy Poolside model inference on Amazon EKS with Helm, using IRSA for S3 access and an Application Load Balancer for ingress.
- [Manage models on Amazon EKS](https://docs-staging.poolside.ai/deployment/cloud/aws-eks/manage-models.md): Add, update, or remove inference models in an existing inference deployment on Amazon EKS.
- [Amazon EKS deployment](https://docs-staging.poolside.ai/deployment/cloud/aws-eks/overview.md): Overview of deploying Poolside model inference on Amazon EKS by using Helm, with IRSA for object storage and an ALB for ingress.
- [Reference architecture](https://docs-staging.poolside.ai/deployment/cloud/aws-eks/reference-architecture.md): AWS reference architecture for a Poolside model inference deployment on Amazon EKS, including the architecture diagram, the AWS layers the inference chart depends on, and the key design decisions.
- [Remove from Amazon EKS](https://docs-staging.poolside.ai/deployment/cloud/aws-eks/remove.md): Instructions for removing a model inference deployment from an Amazon EKS cluster.
- [Upgrade on Amazon EKS](https://docs-staging.poolside.ai/deployment/cloud/aws-eks/upgrade.md): Upgrade an existing model inference deployment on Amazon EKS to a new bundle.
- [Install on OpenShift](https://docs-staging.poolside.ai/deployment/cloud/openshift/install.md): Deploy Poolside model inference on OpenShift and serve models through an OpenAI-compatible API.
- [Manage models on OpenShift](https://docs-staging.poolside.ai/deployment/cloud/openshift/manage-models.md): Add, update, or remove inference models in an existing inference deployment on OpenShift.
- [OpenShift deployment](https://docs-staging.poolside.ai/deployment/cloud/openshift/overview.md): Overview of deploying Poolside model inference on Red Hat OpenShift by using Helm.
- [Remove from OpenShift](https://docs-staging.poolside.ai/deployment/cloud/openshift/remove.md): Instructions for removing a model inference deployment from Red Hat OpenShift.
- [Upgrade on OpenShift](https://docs-staging.poolside.ai/deployment/cloud/openshift/upgrade.md): Upgrade an existing model inference deployment on OpenShift to a new bundle.
- [Cloud deployment](https://docs-staging.poolside.ai/deployment/cloud/overview.md): Deploy Poolside model inference in a supported GPU-backed cloud Kubernetes environment.
- [Set up offline documentation](https://docs-staging.poolside.ai/deployment/cloud/set-up-offline-documentation.md): Deploy the Poolside documentation site in-cluster for offline access as part of a cloud inference deployment.
- [Install on Kubernetes](https://docs-staging.poolside.ai/deployment/cloud/upstream-kubernetes/install.md): Deploy Poolside model inference on a self-managed Kubernetes cluster and serve models through an OpenAI-compatible API.
- [Manage models on Kubernetes](https://docs-staging.poolside.ai/deployment/cloud/upstream-kubernetes/manage-models.md): Add, update, or remove inference models in an existing inference deployment on upstream Kubernetes.
- [Upstream Kubernetes deployment](https://docs-staging.poolside.ai/deployment/cloud/upstream-kubernetes/overview.md): Overview of deploying Poolside model inference on a self-managed Kubernetes cluster by using Helm.
- [Remove from upstream Kubernetes](https://docs-staging.poolside.ai/deployment/cloud/upstream-kubernetes/remove.md): Instructions for removing a model inference deployment from an upstream Kubernetes cluster.
- [Upgrade on Kubernetes](https://docs-staging.poolside.ai/deployment/cloud/upstream-kubernetes/upgrade.md): Upgrade an existing model inference deployment on upstream Kubernetes to a new bundle.
- [Admin toolkit](https://docs-staging.poolside.ai/deployment/on-prem/admin.md): Common commands and checks for operating a Poolside on-premises model inference deployment.
- [Certified stacks](https://docs-staging.poolside.ai/deployment/on-prem/certified-stacks/overview.md): Certified software stacks for supported Poolside on-premises model inference deployments.
- [On-premises deployment FAQ](https://docs-staging.poolside.ai/deployment/on-prem/faq.md): Answers to common questions about Poolside on-premises model inference deployments.
- [Install on-premises](https://docs-staging.poolside.ai/deployment/on-prem/install.md): Install Poolside model inference on a single on-premises GPU host by using the Terraform installation bundle.
- [On-premises deployment](https://docs-staging.poolside.ai/deployment/on-prem/overview.md): Overview of Poolside on-premises model inference deployments, including hardware options, architecture, installation approach, and operational considerations.
- [Relocate an on-premises server](https://docs-staging.poolside.ai/deployment/on-prem/relocation.md): Relocate a Poolside on-premises model inference server to a different physical network.
- [Server and service maintenance](https://docs-staging.poolside.ai/deployment/on-prem/server-maintenance.md): Stop, start, reboot, or fully shut down a Poolside on-premises model inference node.
- [STIG hardening considerations](https://docs-staging.poolside.ai/deployment/on-prem/stig.md): Considerations for deploying Poolside on-premises model inference on STIG-hardened systems, including known compatibility issues and recommended configurations.
- [Storage requirements](https://docs-staging.poolside.ai/deployment/on-prem/storage.md): Storage guidance for Poolside on-premises model deployments, including partitioning recommendations and model checkpoint storage.
- [Upgrade on-premises](https://docs-staging.poolside.ai/deployment/on-prem/upgrade.md): Upgrade an on-premises Poolside model inference deployment to a new installation bundle.
- [Supported configurations](https://docs-staging.poolside.ai/deployment/supported-configurations.md): Review supported environments and minimum requirements for Poolside model inference.
- [Poolside overview](https://docs-staging.poolside.ai/get-started/overview.md): Poolside provides agentic coding models, APIs, and agent workflows for secure software engineering.
- [Quickstart](https://docs-staging.poolside.ai/get-started/quickstart.md): Install Poolside Agent CLI, authenticate, and run your first agent task.
- [Supported models](https://docs-staging.poolside.ai/get-started/supported-models.md): An overview of Poolside models, including modes and context windows.
- [](https://docs-staging.poolside.ai/index.md)
- [Acceptable Use Policy](https://docs-staging.poolside.ai/legal/acceptable-use-policy.md)
- [Data Processing Agreement](https://docs-staging.poolside.ai/legal/data-processing-agreement.md)
- [End User License Agreement](https://docs-staging.poolside.ai/legal/end-user-license-agreement.md)
- [Privacy Policy](https://docs-staging.poolside.ai/legal/privacy-policy.md)
- [Trust Center](https://docs-staging.poolside.ai/legal/trust-center.md): Security, compliance, and privacy information is available in the Poolside Trust Center.
- [MCP servers](https://docs-staging.poolside.ai/mcp-servers.md): Configure personal MCP servers that Poolside agents can invoke from the CLI.
- [Inference metrics](https://docs-staging.poolside.ai/metrics/inference-metrics.md): Reference for the Prometheus metrics the Poolside vLLM model server exposes, and how to scrape them.
- [Create chat completion](https://docs-staging.poolside.ai/openai-api/chat/create-chat-completion.md): Generates a response based on a list of messages sent by the user to the model. The list of messages may include system messages, user messages, and assistant messages.<br/><br/>This endpoint allows other tools in the developer ecosystem to leverage poolside as a drop-in replacement for other models…
- [Create completion](https://docs-staging.poolside.ai/openai-api/chat/create-completion.md): Get a completion along with the probabilities of alternative tokens at each position. This endpoint is not recommended for new use cases and is maintained for legacy compatibility only.<br/><br/>Use <i>/chat/completions</i> instead for the best and newest models.
- [List models](https://docs-staging.poolside.ai/openai-api/models/list-models.md)
- [Laguna M.1 release notes](https://docs-staging.poolside.ai/release-notes/laguna-m1.md): Release notes for the Laguna M.1 model.
- [Laguna XS.2 release notes](https://docs-staging.poolside.ai/release-notes/laguna-xs2.md): Release notes for the Laguna XS.2 model.
- [Malibu 2.1 release notes](https://docs-staging.poolside.ai/release-notes/malibu-2-1.md): Release notes for the Malibu 2.1 model.
- [Malibu 2.2 release notes](https://docs-staging.poolside.ai/release-notes/malibu-2-2.md): Release notes for the Malibu 2.2 model.
- [Release notes](https://docs-staging.poolside.ai/release-notes/overview.md): Recent Poolside inference deployment and model releases.
- [Example prompts](https://docs-staging.poolside.ai/resources/example-prompts.md): Common development tasks and example prompts you can use with Poolside.
- [Example workflows](https://docs-staging.poolside.ai/resources/example-workflows.md): Common tasks you can accomplish with Poolside Agent CLI.
- [How agents work](https://docs-staging.poolside.ai/resources/how-agents-work.md): A conceptual overview of agents powered by large language models, including their core components, behavior, and common use cases.
- [Prompting best practices](https://docs-staging.poolside.ai/resources/prompting-best-practices.md): Learn how to write effective prompts to get the most out of Poolside.
- [Documenting code](https://docs-staging.poolside.ai/resources/use-cases/documenting-code.md): This use case demonstrates how to use Poolside to generate, improve, and maintain code documentation. This can be especially useful when interacting with legacy codebases and understanding how existing codebases work.
- [Refactoring code](https://docs-staging.poolside.ai/resources/use-cases/refactoring-code.md): This use case demonstrates how to use Poolside to refactor code by understanding existing implementations and suggesting improvements while maintaining functionality.
- [Visualizing data flows](https://docs-staging.poolside.ai/resources/use-cases/visualizing-data-flows.md): This use case demonstrates how to use Poolside to generate visual representations of code structures, workflows, and architectures using Mermaid diagrams.
- [Sandboxes](https://docs-staging.poolside.ai/sandboxes.md): Run Poolside agents in local sandbox environments with file system and network controls.
- [Secrets](https://docs-staging.poolside.ai/secrets.md): Store sensitive values like API keys and tokens that agents can use without exposing the raw value.
- [Settings file reference](https://docs-staging.poolside.ai/settings-file-reference.md): Reference for settings you can define in Poolside `settings.yaml` files.
- [Skills](https://docs-staging.poolside.ai/skills.md): Use local skills to give agents reusable, task-specific instructions and resources.
- [Support Overview](https://docs-staging.poolside.ai/support/overview.md): Overview of Poolside support offerings, eligibility requirements, and options for non-standard deployments
- [Premium Support](https://docs-staging.poolside.ai/support/premium-support.md): Learn about Poolside Premium Support, response times, and scope.
- [Standard Support](https://docs-staging.poolside.ai/support/standard-support.md): Learn about Poolside Standard Support, response times, and more.
- [Submit a Support Request](https://docs-staging.poolside.ai/support/submit-a-support-request.md): How to open a support request through the Poolside support portal, set the right metadata, and write requests that get resolved faster.
- [Support Portal](https://docs-staging.poolside.ai/support/support-portal.md)
- [Tool permissions](https://docs-staging.poolside.ai/tool-permissions.md): Control what Poolside agents can read, write, and run by using settings.yaml.