Prefect llms.txt · AI Docs Browser · mdream

[llms.txt Tools](https://mdream.dev/llms-txt/prefect/llms-txt)

# Prefect llms.txt

docs.prefect.io/llms.txt

[Raw llms.txt](https://docs.prefect.io/llms.txt) [Raw llms-full.txt](https://docs.prefect.io/llms-full.txt)

Copy Markdown [](https://docs.prefect.io/llms.txt)

llms.txt

Docs

Code of conduct

Contribute to integrations

Develop on Prefect

Contribute to documentation

Contribute

Code and development style guide

Integrations

assume_role_parameters

batch

execute

upload

client_parameters

client_waiter

credentials

decorators

steps

glue_job

lambda_function

plugins

s3

secrets_manager

settings

init

ecs

utilities

ecs_worker

Get to know the ECS worker

How to manually deploy an ECS worker to an ECS cluster

prefect-aws

Azure Container Instances Worker Guide

blob_storage

execute

upload

container_instance

cosmos_db

credentials

decorators

steps

ml_datastore

plugins

repository

settings

init

container_instance

prefect-azure

credentials

repository

prefect-bitbucket

client

task_runners

utils

prefect-dask

credentials

flows

jobs

rest

prefect-databricks

commands

base

bigquery

postgres

snowflake

credentials

clients

credentials

exceptions

jobs

models

runs

utils

runner

settings

utilities

dbt Cloud

prefect-dbt

Installation

Legacy

PrefectDbtOrchestrator

PrefectDbtRunner

containers

credentials

decorators

steps

host

images

types

worker

prefect-docker

credentials

message

prefect-email

bigquery

execute

upload

cloud_storage

credentials

decorators

steps

cloud_run_v2

secret_manager

settings

utilities

cloud_run

cloud_run_v2

vertex

Google Cloud Run Worker Guide

prefect-gcp

credentials

exceptions

graphql

mutations

organization

repository

repository_owner

graphql_schema

user

utils

viewer

prefect-github

credentials

repositories

prefect-gitlab

credentials

custom_objects

decorators

deployments

diagnostics

exceptions

flows

jobs

observer

pods

services

settings

utilities

worker

prefect-kubernetes

context

task_runners

prefect-ray

blocks

cleanup_queue

client

lease_storage

locking

messaging

ordering

tasks

prefect-redis

commands

prefect-shell

credentials

messages

prefect-slack

credentials

database

prefect-snowflake

credentials

database

prefect-sqlalchemy

Use integrations

How to use and configure the API client

How to customize asset metadata

How to deploy a web application powered by background tasks

How to customize caching behavior

How to cancel running workflows

How to configure network access for restricted environments

How to create custom blocks

Customizing Base Job Templates

How to daemonize worker processes

How to maintain your Prefect database

How to debounce events

How to build deployments via CI/CD

How to detect and respond to zombie flows

How to develop a custom worker

Configure UI forms for validating workflow inputs

How to generate a custom SDK for your deployments

Advanced

How to manage Prefect resources using Infrastructure as Code

How to write interactive workflows

How to customize Prefect's logging configuration

How to write a Prefect plugin

How to persist and retrieve workflow results

How to secure a self-hosted Prefect server

How to scale self-hosted Prefect

How to self-host the Prefect Server with Helm

How to submit flows directly to dynamic infrastructure

How to write transactional workflows

How to emit and use custom events

How to configure worker healthchecks

Artifact and asset events

Automation events

Prefect Cloud events

Concurrency events

Deployment events

Flow run events

Events reference

Infrastructure events

Task run events

Work pool and work queue events

Worker and runner events

API & SDK References

artifacts

core

materialize

automations

abstract

core

notifications

redis

system

webhook

init

execute

cache_policies

api

artifact

automation

block

init

asset

ip_allowlist

webhook

concurrency_limit

config

dashboard

init

deployment

dev

events

experimental

flow

flow_run

flow_runs_watching

global_concurrency_limit

plugins

profile

result_storage

sdk

server

shell

task

task_run

init

variable

version

work_pool

work_queue

worker

init

attribution

base

cloud

collections

init

base

actions

events

filters

objects

responses

schedules

sorting

worker_channel

subscriptions

utilities

asyncio

context

services

sync

asyncio

context

services

sync

context

base

flow_runs

runner

schedules

core

pull

utility

docker_image

engine

actions

clients

filters

related

automations

deployment_triggers

events

labelling

subscribers

utilities

worker

exceptions

filesystems

flow_engine

flow_runs

flows

futures

init

base

init

cloud_run

coiled

container_instance

ecs

modal

actions

run_input

filesystem

memory

protocol

clients

configuration

filters

formatters

handlers

highlighters

loggers

plugins

results

runner

server

storage

init

deployment

flow_run

task_run

schedules

serializers

admin

artifacts

automations

background_workers

block_capabilities

block_documents

block_schemas

block_types

clients

collections

concurrency_limits

concurrency_limits_v2

csrf_token

dependencies

deployments

events

flow_run_states

flow_runs

flows

logs

middleware

root

run_history

saved_searches

server

task_run_states

task_runs

task_workers

templates

init

flow_runs

flows

schemas

task_runs

validation

variables

work_queues

workers

alembic_commands

configurations

dependencies

interface

orm_models

query_components

actions

clients

counting

filters

jinja_filters

messaging

automations

composite_trigger_child_firing

init

db

memory

pipeline

automations

events

labelling

lifecycle

actions

event_logger

event_persister

triggers

init

database

stream

triggers

exceptions

messaging

stream

artifacts

block_documents

block_registration

block_schemas

block_types

concurrency_limits

concurrency_limits_v2

configuration

csrf_token

deployments

events

flow_run_input

flow_run_states

flow_runs

flows

logs

saved_searches

storage_defaults

task_run_states

task_runs

task_workers

variables

work_queues

workers

core_policy

dependencies

global_policy

instrumentation_policies

policies

rules

actions

core

filters

graph

internal

responses

schedules

sorting

states

statuses

ui

base

cancellation_cleanup

cleanup_reconciler

db_vacuum

foreman

late_runs

pause_expirations

perpetual_services

repossessor

scheduler

task_run_recorder

telemetry

task_queue

database

encryption

http

leasing

init

memory

names

postgres_listener

bases

serializers

server

subscriptions

text_search_parser

user_templates

worker_channel

worker_channel_cleanup

init

init

memory

init

base

context

legacy

api

cli

client

cloud

deployments

events

experiments

flows

internal

logging

plugins

results

root

runner

api

concurrency

database

deployments

docket

ephemeral

events

flow_run_graph

logs

root

services

tasks

ui

worker_channel

tasks

telemetry

testing

worker

profiles

sources

states

task_engine

task_runners

task_runs

task_worker

tasks

run_telemetry

cli

docker

fixtures

utilities

transactions

init

entrypoint

names

annotations

asyncutils

callables

collections

compat

context

dispatch

dockerutils

engine

filesystem

generics

hashing

importtools

math

names

processutils

pydantic

render_swagger

hydration

validation

services

templating

text

timeout

urls

visualization

variables

base

block

cloud

process

server

utilities

Cloud API Overview

REST API overview

Clear Server Default Result Storage

Read Server Default Result Storage

Read Settings

Read Version

Update Server Default Result Storage

Count Artifacts

Count Latest Artifacts

Create Artifact

Delete Artifact

Read Artifact

Read Artifacts

Read Latest Artifact

Read Latest Artifacts

Update Artifact

Count Automations

Create Automation

Delete Automation

Delete Automations Owned By Resource

Patch Automation

Read Automation

Read Automations

Read Automations Related To Resource

Update Automation

Validate Template

Validate Template

Read Available Block Capabilities

Count Block Documents

Create Block Document

Delete Block Document

Read Block Document By Id

Read Block Documents

Update Block Document Data

Create Block Schema

Delete Block Schema

Read Block Schema By Checksum

Read Block Schema By Id

Read Block Schemas

Create Block Type

Delete Block Type

Install System Block Types

Read Block Document By Name For Block Type

Read Block Documents For Block Type

Read Block Type By Id

Read Block Type By Slug

Read Block Types

Update Block Type

Read View Content

Bulk Decrement Active Slots

Bulk Decrement Active Slots With Lease

Bulk Increment Active Slots

Bulk Increment Active Slots With Lease

Create Concurrency Limit V2

Delete Concurrency Limit V2

Read All Concurrency Limits V2

Read Concurrency Limit V2

Renew Concurrency Lease

Update Concurrency Limit V2

Create Concurrency Limit

Decrement Concurrency Limits V1

Delete Concurrency Limit

Delete Concurrency Limit By Tag

Increment Concurrency Limits V1

Read Concurrency Limit

Read Concurrency Limit By Tag

Read Concurrency Limits

Reset Concurrency Limit By Tag

Create Csrf Token

Bulk Create Flow Runs From Deployment

Bulk Delete Deployments

Count Deployments

Create Deployment

Create Deployment Schedules

Create Flow Run From Deployment

Delete Deployment

Delete Deployment Schedule

Get Scheduled Flow Runs For Deployments

Paginate Deployments

Pause Deployment

Read Deployment

Read Deployment By Name

Read Deployment Schedules

Read Deployments

Resume Deployment

Schedule Deployment

Update Deployment

Update Deployment Schedule

Work Queue Check For Deployment

Count Account Events

Create Events

Read Account Events Page

Read Events

Read Flow Run State

Read Flow Run States

Average Flow Run Lateness

Bulk Delete Flow Runs

Bulk Set Flow Run State

Count Flow Runs

Create Flow Run

Create Flow Run Input

Delete Flow Run

Delete Flow Run Input

Download Logs

Filter Flow Run Input

Flow Run History

Read Flow Runs

Read Flow Run

Read Flow Run Graph V1

Read Flow Run Graph V2

Read Flow Run Input

Read Flow Runs

Resume Flow Run

Set Flow Run State

Update Flow Run

Update Flow Run Labels

Bulk Delete Flows

Count Flows

Create Flow

Delete Flow

Paginate Flows

Read Flow

Read Flow By Name

Read Flows

Update Flow

Server API Overview

Create Logs

Read Logs

Health Check

Hello

Perform Readiness Check

Server Version

Create Saved Search

Delete Saved Search

Read Saved Search

Read Saved Searches

Read Task Run State

Read Task Run States

Count Task Runs

Create Task Run

Delete Task Run

Paginate Task Runs

Read Task Run

Read Task Runs

Set Task Run State

Task Run History

Update Task Run

Read Task Workers

Count Variables

Create Variable

Delete Variable

Delete Variable By Name

Read Variable

Read Variable By Name

Read Variables

Update Variable

Update Variable By Name

Count Work Pools

Create Work Pool

Create Work Queue

Delete Work Pool

Delete Work Queue

Delete Worker

Get Scheduled Flow Runs

Read Work Pool

Read Work Pool Concurrency Status

Read Work Pools

Read Work Queue

Read Work Queues

Read Workers

Update Work Pool

Update Work Queue

Worker Heartbeat

Create Work Queue

Delete Work Queue

Read Work Queue

Read Work Queue By Name

Read Work Queue Concurrency Status

Read Work Queue Runs

Read Work Queue Status

Read Work Queues

Update Work Queue

Settings reference

Artifacts

Assets

Automations

Blocks

Caching

Deployments

Define event triggers

Events

Flows

Global concurrency limits

Concepts

Rate limits and data retention

Runtime context

Schedule flow runs

Prefect server

Settings and profiles

Measure reliability with Service Level Agreements

States

Tag-based concurrency limits

Task runners

Tasks

Telemetry

Variables

Webhooks

Work pools

Workers

AI-Powered Data Analyst

Database Cleanup with Human or AI Approval

Social Analytics Dashboard

Hello, world!

Overview

Per-worker task concurrency

Resume Flow Run on PR Merge

API-sourced ETL

dbt Model Orchestration

Simple web scraper

Introduction

Install Prefect

Quickstart

AI log summaries

AI assistants with Prefect MCP

How to use the Prefect MCP server

How to access deployment and flow run parameters

How to chain deployments with events

How to create automations

How to create deployment triggers

Custom notifications

How to pass event payloads to flows

How to connect to Prefect Cloud

How to create a webhook

How to manage API keys

How to audit Cloud activity

How to configure single sign-on

How to manage user accounts

How to manage account roles

How to manage teams

How to manage Access Control Lists (ACLs)

How to secure access by IP address

How to secure access over PrivateLink

How to manage service accounts

How to troubleshoot Prefect Cloud

How to manage workspaces

How to manage settings

How to store secrets

How to share configuration between workflows

How to run flows on Coiled

How to run flows in Docker containers

How to run flows on Kubernetes

How to manage work pools

How to run flows on Prefect Managed infrastructure

Using cloud workload identity with Prefect Managed work pools

How to run flows on Modal

How to run flows in local processes

How to run flows in a long-lived Docker container

How to run flows on serverless compute

How to create deployments

How to create schedules

How to override job variables

How to deploy flows with Python

Manage Deployment schedules

How to define deployments with YAML

Trigger ad-hoc deployment runs

How to retrieve code from storage

How to version deployments

How-to Guides

How to Migrate from Airflow

How to transfer resources between Prefect environments

How to upgrade from agents to workers

How to upgrade to Prefect 3.0

How to run the Prefect Server via Docker Compose

How to run a local Prefect server

How to run the Prefect server in Docker

How to run Prefect on Windows

How to access runtime information

How to add logging to a workflow

How to produce workflow artifacts

How to use assets to track workflow outputs

How to cache workflow step outputs

How to customize a workflow's metadata

How to apply global concurrency and rate limits

How to pass inputs to a workflow

How to automatically rerun your workflow when it fails

How to manually retry a flow run

How to run tasks background tasks

How to run work concurrently

How to respond to state changes

How to limit concurrent task runs with tags

How to test workflows

How to write and run a workflow

Release Notes

3.0

3.1

3.2

3.3

3.4

3.5

3.6

3.7

Versioning and compatibility

OpenAPI Specs

schema

meta

Will

We

Units

Spelling

Spacing

Slang

Semicolons

Ranges

Quotes

Periods

Passive

Parens

OxfordComma

Ordinal

OptionalPlurals

LyHyphens

Latin

Headings

HeadingPunctuation

GenderBias

Gender

Exclamation

EmDash

Ellipses

DateFormat

Contractions

Colons

Acronyms

AMPM

WordList

FirstPerson

openapi

## What is Prefect's llms.txt?

Prefect publishes an `/llms.txt` file that provides AI systems with a structured index of its documentation. It follows the [llms.txt specification](https://llmstxt.org), organizing links to guides, API references, and tutorials under section headings so that LLMs like ChatGPT, Claude, and Gemini can quickly understand what Prefect offers and where to find details.

Pass

Spec

2

Sections

923

Links

97.8 KB

Size

~25.0k

Tokens

Sections: Docs · OpenAPI Specs

## Add Prefect Docs to Your AI Assistant

Select your tool to see how to add Prefect's llms.txt as a documentation source.

Cursor

 Windsurf

 Claude Code

 ChatGPT

 Zed

 Copilot

1. 1

   Open any chat or composer panel
2. 2

   Type @Docs and select "Add new doc"
3. 3

   Paste the URL: https://docs.prefect.io/llms.txt
4. 4

   Wait for the green dot (indexing complete)
5. 5

   Reference @Docs in chat when asking about Prefect

Cursor crawls the URL and indexes all subpages. Add a trailing slash to index child pages too.

## Spec Compliance 5 notes

## Frequently Asked Questions

Where is Prefect's llms.txt file?

Prefect publishes its llms.txt at https://docs.prefect.io/llms.txt. This file provides a structured, markdown-formatted index of Prefect's documentation that AI systems can consume to understand the project's APIs, guides, and references.

How do I use Prefect's llms.txt with AI coding assistants?

Copy the llms.txt content and paste it into your AI assistant (Cursor, Windsurf, Claude, ChatGPT) as context. This gives the AI an accurate map of Prefect's documentation so it can provide better code suggestions and answers about Prefect.

What does Prefect's llms.txt contain?

Prefect's llms.txt contains 2 sections and 923 documentation links in 97.8 KB (~25.0k tokens). Key sections include Docs, OpenAPI Specs.

How many tokens does Prefect's llms.txt use?

The concise llms.txt index is approximately 25.0k tokens (97.8 KB). Most AI assistants can fit this within their context window. For the full expanded documentation, look for an llms-full.txt variant which embeds all content inline.

Can I generate an llms.txt for my own project?

Yes. Use the free llms.txt generator at mdream.dev/tools/llms-txt/generator to crawl your site and produce a spec-compliant llms.txt file. You can also validate existing files with the llms.txt validator.

## Browse More llms.txt Files

[GitBook Documentation](https://mdream.dev/llms-txt/prefect/llms-txt/gitbook) [Add a New Provider In above example, we have given our provider name as example-provider for simplicity. If provider you want to add have name as twilio, don't use twilio-provider as name, instead use twilio only. If one provider supports multiple channels like infobip supports both sms and email channels, use infobip-email or infobip-sms to differentiate these providers.](https://mdream.dev/llms-txt/prefect/llms-txt/novu) [The JavaScript Oxidation Compiler The JavaScript Oxidation Compiler](https://mdream.dev/llms-txt/prefect/llms-txt/oxc) [Apify Documentation The entire content of Apify documentation is available in a single Markdown file at https://docs.apify.com/llms-full.txt](https://mdream.dev/llms-txt/prefect/llms-txt/apify) [Nx Nx is an AI-first monorepo platform that connects your editor to CI. It helps you deliver fast without breaking things by optimizing builds, scaling CI, and fixing failed PRs.](https://mdream.dev/llms-txt/prefect/llms-txt/nx) [Kilo Code Documentation**Note:** Skip labels and required labels are also excluded from the set of labels the AI can apply. This keeps gating labels strictly under your control.](https://mdream.dev/llms-txt/prefect/llms-txt/kilocode) [EventCatalog EventCatalog is an Open Source project that helps you document your messages, services and domains.](https://mdream.dev/llms-txt/prefect/llms-txt/eventcatalog) [Documentation Automated auditing, performance metrics, and best practices for the web.](https://mdream.dev/llms-txt/prefect/llms-txt/lighthouse)

[View all 99 projects ](https://mdream.dev/llms-txt/prefect/llms-txt)

## Related Tools

[<h3>llms.txt Generator</h3>Generate an llms.txt for your own project.](https://mdream.dev/llms-txt/prefect/tools/llms-txt/generator) [<h3>llms.txt Validator</h3>Validate your llms.txt against the official spec.](https://mdream.dev/llms-txt/prefect/tools/llms-txt/validator)

© 2026 [Harlan Wilton](https://github.com/harlan-zw) · [MIT](https://github.com/harlan-zw/mdream/blob/main/license)

[GitHub](https://github.com/harlan-zw/mdream) [Discord](https://discord.com/invite/275MBUBvgP)