> ## Documentation Index > Fetch the complete documentation index at: https://app.keystroke.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # Explore features > Find the right feature for your use case. Keystroke gives you a code-first toolkit for building AI agents and workflow automations, and a managed platform to run them. 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](/learn/agents/overview) 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](/learn/actions/agent-tools) built from your actions, choose a [model](/learn/agents/build-agents#models), and add [memory](/learn/agents/build-agents#memory), [subagents](/learn/agents/build-agents#subagents-as-tools), or [sandboxes](/learn/agents/build-agents#sandboxes) as your use case grows. See [Agents](/learn/agents/overview) and [Build agents](/learn/agents/build-agents). ## Automate multi-step work with workflows A [workflow](/learn/workflows/overview) chains [actions](/learn/actions/overview) and [agents](/learn/agents/overview) 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. See [Workflows](/learn/workflows/overview) and [Build workflows](/learn/workflows/build-workflows). ## Connect the tools your team already uses Keystroke ships with over [1,000 built-in integrations](/integrations), so your [agents](/learn/agents/overview) and [workflows](/learn/workflows/overview) can interact with the tools your team relies on. You can also connect to any HTTP API (including private internal APIs), wire up MCP servers, and manage OAuth and API keys in one place. See [Integrations](/integrations) and [Credentials](/learn/credentials/overview). ## Run automatically on a schedule or event A [trigger](/learn/triggers/overview) kicks off a [workflow](/learn/workflows/overview) without anyone pressing a button. Run automations on a [schedule](/learn/triggers/schedules) with cron, in response to a [webhook](/learn/triggers/webhooks), or from [app events](/learn/triggers/app-events) like a Google Meet call ending or a new Linear issue. Triggers attach to [workflows](/learn/workflows/overview) and filter on the source, so each automation runs exactly when it should. See [Triggers](/learn/triggers/overview). ## Talk to your agents in Slack Wire an [agent](/learn/agents/overview) 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](/learn/agents/external-channels). ## Build it all with your coding agent Because everything is TypeScript in your repo, your coding agent (Cursor, Claude Code, Codex, etc) can build and maintain your project for you. It reads `AGENTS.md` and the bundled [skills](/learn/skills/overview) to learn how Keystroke works, then writes [agents](/learn/agents/overview), [workflows](/learn/workflows/overview), and [triggers](/learn/triggers/overview) on your behalf. See [AI onboarding](/build-with-ai/onboarding) and [llms.txt](/build-with-ai/llms-txt). ## Deploy and operate on the platform The Keystroke platform is a managed place for your team to run what you build. [Deploy](/learn/projects/deploy-a-project) your project from TypeScript, then inspect [run history](/learn/logs/overview), manage [credentials](/learn/credentials/overview), invite [members](/learn/settings/members), and set access controls, all from one shared workspace. ## Learn more Install the CLI, scaffold a project, and deploy your first agent. Define LLM agents with tools, models, memory, and sandboxes. Chain actions and agents into durable, multi-step automations. Connect Slack, Google, Linear, and 1,000+ other tools.