# Lodol Docs

> Lodol is a workflow automation platform. A workflow starts when something happens in one of your apps, on a schedule or on demand, and runs the same steps every time. These docs explain how workflows work, how to build them yourself or with an AI tool, every app and built-in step a workflow can use, and the developer API.

Every page is also available as Markdown: add `.md` to its address. For Lodol's product, pricing and company, see https://www.lodol.com/llms.txt.

## Documentation

- [What is Lodol?](https://docs.lodol.com/docs.md): Lodol runs your automations for you. Say what should happen and when, and Lodol does it every time, with your keys kept safe and every run on the record.
- [Build with your AI tool](https://docs.lodol.com/docs/build-with-ai.md): Connect Claude, ChatGPT, Cursor or any tool that supports MCP, then describe the automation you want. Your AI builds the workflow in Lodol, and Lodol runs it.
- [Workflows](https://docs.lodol.com/docs/concepts/workflows.md): A workflow is a trigger followed by steps, read top to bottom. Lodol keeps every version of it, runs it when it should, and records what each run did.
- [Triggers and schedules](https://docs.lodol.com/docs/concepts/triggers.md): A workflow starts when something happens in an app, at the times you schedule, or when you start it. Each start is one run.
- [Steps and data](https://docs.lodol.com/docs/concepts/steps-and-data.md): Steps are what a workflow does, in order. Each one hands its result to the steps after it, which read it with @ references.
- [Inputs and outputs](https://docs.lodol.com/docs/concepts/inputs-and-outputs.md): Inputs let one workflow run for many cases, such as a report for any client. Outputs are what it hands back to a workflow that runs it.
- [Runs](https://docs.lodol.com/docs/concepts/runs.md): A run is one pass through a workflow. Lodol records every run step by step, emails you when one fails, and counts each run once however many steps it takes.
- [Connections and secrets](https://docs.lodol.com/docs/concepts/connections.md): Workflows use your app accounts through connections, and your own API keys as secrets. Both are encrypted, used by name, and never shown in a workflow or to your AI.
- [Make decisions](https://docs.lodol.com/docs/guides/conditions.md): Use If to run steps only when something is true, Otherwise for when it isn't, and a chain of Ifs for three or more cases.
- [Repeat steps](https://docs.lodol.com/docs/guides/loops.md): Use Repeat to run steps once for each item in a list, a set number of times, or while something is true, and avoid the mistakes that make loops quietly wrong.
- [Ask for approval](https://docs.lodol.com/docs/guides/approvals.md): Pause a run until someone approves or rejects it, or answers a question in writing, then carry on with their answer. People outside your workspace can answer too.
- [Use an AI agent](https://docs.lodol.com/docs/guides/ai-agents.md): Give an AI a task, files to read and tools to use, and get back an answer or the exact fields you ask for. Use it where the work has no fixed recipe.
- [Remember values between runs](https://docs.lodol.com/docs/guides/stored-values.md): Stored values let a workflow pick up where it left off, keep a count, or share a value with other workflows, from one run to the next.
- [Run a workflow from another](https://docs.lodol.com/docs/guides/sub-workflows.md): Build a procedure once, such as "look up a customer", and use it as a step in any workflow. It takes inputs, hands back outputs, and doesn't count as an extra run.
- [Handle failures](https://docs.lodol.com/docs/guides/failures.md): When a step fails, the run stops and Lodol tells you. Here's how to find out why, fix it, and keep a run going when a failure shouldn't end it.
- [Call an API or run code](https://docs.lodol.com/docs/guides/http-and-code.md): Reach any service with a REST or GraphQL API, or compute something no built-in step covers. Use them when nothing else fits.

## API

- [Developer API](https://docs.lodol.com/docs/api.md): Start workflows from your own code, pass them inputs, and read what each run did. A small REST API with JSON bodies and API-key authentication.
- [Quickstart](https://docs.lodol.com/docs/api/quickstart.md): Create an API key, start a workflow run from your code, and read its result. About five minutes.
- [Authentication](https://docs.lodol.com/docs/api/authentication.md): Every request carries an API key. A key belongs to one workspace, its scopes say what it may do, and it can never do more than the member who created it.
- [Errors and retries](https://docs.lodol.com/docs/api/errors.md): The error codes the API returns and what to do about each, the request ID to quote to support, which requests are safe to retry, and how idempotency keys stop a retry from starting a run twice.
- [Limits](https://docs.lodol.com/docs/api/limits.md): How many requests a workspace can make each minute, the other limits your plan sets, and how to tell when you're close to them.
- [Workflows](https://docs.lodol.com/docs/api/workflows.md): List the workspace's workflows, read one with its steps, or delete one for good.
- [Runs](https://docs.lodol.com/docs/api/runs.md): Start a workflow run with inputs, follow it to what it hands back, list past runs, stop a run in progress, and delete one.
- [Workflow format](https://docs.lodol.com/docs/api/workflow-format.md): How a workflow's trigger and steps are written as JSON, for reading the program that Get a workflow returns.

## Integrations

- [Integrations](https://docs.lodol.com/docs/integrations.md): The 1165 apps and the built-in steps a workflow can use, one line each, linking to a page with each one's triggers and actions and their inputs and outputs.

## Optional

- [Full documentation](https://docs.lodol.com/llms-full.txt): Every page under Documentation and API above, in one file.