Automation library · Data collection

Send daily AI YouTube news digests to Telegram with Firecrawl

Started by a clock, and works across Telegram. It hands the judgement calls to Claude and OpenAI. 11 steps, 1 branch, 1 loop or waits: a working afternoon to understand properly.

MediumCalls a model: Claude, OpenAI

11 stepsMedium: a working afternoon
1Branch: places the flow splits
1Loop or waits
1Service it connects to

The flow

Starts it 1Model 3Logic 4Service 3

The steps in the order they run, from what starts it.

  1. 1DeepSeek via Fireworks (fallback)Lm Chat Open AiModel
  2. 2Claude Haiku 4.5 (primary)Lm Chat AnthropicModel
  3. 3Every day at 10:00Schedule triggerStarts it
  4. 4Summarize AI newsAgentModel
  5. 5SettingsSetLogic
  6. 6Send digest to TelegramTelegramService
  7. 7Start Firecrawl scrape jobFirecrawlService
  8. 8Wait 7 minutesWaitLogic
  9. 9Check scrape job statusFirecrawlService
  10. 10Scrape finished?IfLogic
  11. 11Build transcript blockCodeLogic

How it's built

Starts on
A clock
Steps
11, with 1 branch, 1 loop or waits
Size
Medium: a working afternoon
Connects to
Telegram
Model
Claude, OpenAI

Questions

What does it need to run?

An n8n account, plus your own Telegram account, and a key for Claude and OpenAI. You connect your own accounts after importing it; none are included.

What starts it?

It starts on a clock.

Does it use AI?

Yes. It calls Claude and OpenAI. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Plan an afternoon. 11 steps is enough that you should read each one before running it.

How do I import it?

Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts.

Before you run it

Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 11 steps before you point it at anything that matters.