> ## Documentation Index > Fetch the complete documentation index at: https://docs.os.meetluno.ai/llms.txt > Use this file to discover all available pages before exploring further. # Explore features > Find the right feature for your use case. Luno OS gives teams everything they need to build internal agents and AI systems in a single platform, with every project backed by TypeScript they own. Not sure where to start? Use the sections below to find the features that best match what you're trying to do. ## Build a specialized agent An [agent](https://docs.os.meetluno.ai/learn/agents/overview.md) is an LLM you give a job, a model, and a set of tools. It reasons about a request, calls the tools you expose, and works toward a result. Reach for an agent when the steps aren't fixed and you want the model to figure out the path. Define agents in TypeScript, give them [tools](https://docs.os.meetluno.ai/learn/actions/agent-tools.md) built from your actions, choose a [model](https://docs.os.meetluno.ai/learn/agents/build-agents.md#models), and add [memory](https://docs.os.meetluno.ai/learn/agents/build-agents.md#memory), [subagents](https://docs.os.meetluno.ai/learn/agents/build-agents.md#subagents-as-tools), or [sandboxes](https://docs.os.meetluno.ai/learn/agents/build-agents.md#sandboxes) as your use case grows. See [Agents](https://docs.os.meetluno.ai/learn/agents/overview.md) and [Build agents](https://docs.os.meetluno.ai/learn/agents/build-agents.md). ## Keep agents safe and reliable * **Human approval** — mark an action `needsApproval` and the agent pauses before every call until someone approves or denies it, from the web app, Slack or Teams. See [human approval](https://docs.os.meetluno.ai/learn/agents/build-agents.md#human-approval). * **Memory per person** — an agent remembers each user it talks to (and recalls their earlier conversations) without mixing people up; you can read or clear it per user. See [memory](https://docs.os.meetluno.ai/learn/agents/build-agents.md#memory). * **Guardrails and fallbacks** — block prompt injection, redact personal data, moderate content, and fall back to another model when a provider is down. See [guardrails](https://docs.os.meetluno.ai/learn/agents/build-agents.md#guardrails). * **Evals** — score real replies against your cases with `luno evals run` before you ship a prompt or model change. See [evals](https://docs.os.meetluno.ai/learn/agents/test-agents.md#evals). ## Ground agents in company knowledge [Company Brains](https://docs.os.meetluno.ai/learn/settings/company-brain.md) are shared knowledge bases that agents can search and read on demand. Use a Brain when several agents or projects need trusted context from product documentation, policies, research, customer knowledge, or other organization sources. ## Automate multi-step work with workflows A [workflow](https://docs.os.meetluno.ai/learn/workflows/overview.md) chains [actions](https://docs.os.meetluno.ai/learn/actions/overview.md) and [agents](https://docs.os.meetluno.ai/learn/agents/overview.md) into a durable, multi-step automation. Reach for a workflow when the steps are known and you want them to run reliably and predictably, the opposite end of the spectrum from letting an agent decide. Workflows orchestrate the deterministic parts of your automation and can call agents for the parts that need reasoning. Branch, loop, run steps in parallel, wait for a human, sleep for days, and when something fails, [restart the run](https://docs.os.meetluno.ai/learn/workflows/run-workflows.md#restart-a-run) from the failed step, or from any step with new input. See [Workflows](https://docs.os.meetluno.ai/learn/workflows/overview.md), [Build workflows](https://docs.os.meetluno.ai/learn/workflows/build-workflows.md), and [Best practices](https://docs.os.meetluno.ai/learn/workflows/authoring-best-practices.md) for keeping them durable and legible on the canvas. ## Connect the tools your team already uses Your [agents](https://docs.os.meetluno.ai/learn/agents/overview.md) and [workflows](https://docs.os.meetluno.ai/learn/workflows/overview.md) can call any HTTP API (including private internal APIs) and MCP server, with OAuth and API keys managed in one place. A curated catalog of managed integrations is coming soon. See [Integrations](https://docs.os.meetluno.ai/integrations.md) and [Credentials](https://docs.os.meetluno.ai/learn/credentials/overview.md). ## Run automatically on a schedule or event A [trigger](https://docs.os.meetluno.ai/learn/triggers/overview.md) kicks off a [workflow](https://docs.os.meetluno.ai/learn/workflows/overview.md) without anyone pressing a button. Run automations on a [schedule](https://docs.os.meetluno.ai/learn/triggers/schedules.md) with cron, in response to a [webhook](https://docs.os.meetluno.ai/learn/triggers/webhooks.md), by [polling](https://docs.os.meetluno.ai/learn/triggers/polling.md) an external system (with persisted cursor state) so a run starts only when there's work, or from [app events](https://docs.os.meetluno.ai/learn/triggers/app-events.md) like a Google Meet call ending or a new Linear issue. Triggers attach to [workflows](https://docs.os.meetluno.ai/learn/workflows/overview.md) and filter on the source, so each automation runs exactly when it should. See [Triggers](https://docs.os.meetluno.ai/learn/triggers/overview.md). ## Talk to your agents in Slack and Teams Wire an [agent](https://docs.os.meetluno.ai/learn/agents/overview.md) to Slack and other chat surfaces so your team can interact with it where they already work. Ask questions, kick off tasks, and get results back in a thread, with no separate UI to learn. See [External channels](https://docs.os.meetluno.ai/learn/agents/external-channels.md). ## Build it all with AI Because everything is TypeScript in a real project, an AI agent can build and maintain it for you. Use the built-in [Luno Builder](https://docs.os.meetluno.ai/build-with-ai/platform-agent.md) directly in the web app — describe what you want in chat and it builds, tests, and deploys. Or use your own coding agent (Cursor, Claude Code, Codex, etc): it reads `AGENTS.md` and the bundled [skills](https://docs.os.meetluno.ai/learn/skills/overview.md) to learn how Luno OS works, then writes [agents](https://docs.os.meetluno.ai/learn/agents/overview.md), [workflows](https://docs.os.meetluno.ai/learn/workflows/overview.md), and [triggers](https://docs.os.meetluno.ai/learn/triggers/overview.md) on your behalf. See [Luno Builder](https://docs.os.meetluno.ai/build-with-ai/platform-agent.md), [AI onboarding](https://docs.os.meetluno.ai/build-with-ai/onboarding.md), and [llms.txt](https://docs.os.meetluno.ai/build-with-ai/llms-txt.md). ## Deploy and operate on the platform The Luno OS platform is a managed place for your team to run what you build. [Deploy](https://docs.os.meetluno.ai/learn/projects/deploy-a-project.md) your project from TypeScript, then inspect [run history](https://docs.os.meetluno.ai/learn/logs/overview.md), manage [credentials](https://docs.os.meetluno.ai/learn/credentials/overview.md), invite [members](https://docs.os.meetluno.ai/learn/settings/members.md), and set access controls, all from one shared workspace. ## Learn more > **[Quickstart](https://docs.os.meetluno.ai/quickstart.md)** > > Install the CLI, scaffold a project, and deploy your first agent. > **[Agents](https://docs.os.meetluno.ai/learn/agents/overview.md)** > > Define LLM agents with tools, models, memory, and sandboxes. > **[Workflows](https://docs.os.meetluno.ai/learn/workflows/overview.md)** > > Chain actions and agents into durable, multi-step automations. > **[Integrations](https://docs.os.meetluno.ai/integrations.md)** > > Connect Slack, any HTTP API, and MCP servers. This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.