# Create and optimize B2B LinkedIn AI posts with Groq: n8n workflow

> Started by a clock, and works across LinkedIn and Telegram. It puts Groq behind a retrieval step, so answers are drawn from documents you supply rather than...

Source: https://millionrounds.com/workflow/create-and-optimize-b2b-linkedin-ai-posts-with-groq (Millionrounds; every figure on the page links to its filing or article)

[Automation library](https://millionrounds.com/workflows) · [Alerts and monitoring](https://millionrounds.com/workflows?category=Alerts+and+monitoring#library)

# Create and optimize B2B LinkedIn AI posts with Groq

Started by a clock, and works across LinkedIn and Telegram. It puts Groq behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 34 steps, 2 branches, 1 loop or waits: large, and worth reading before you trust it with anything live.

Large Calls a model: Groq Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fcreate-and-optimize-b2b-linkedin-ai-posts-with-groq)

**34 steps** Large: read it before trusting it with anything live

**2** Branches: places the flow splits

**1** Loop or waits

**2** Services it connects to

## The flow

Starts it 3 Model 17 Logic 10 Service 4

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

- 1 **Schedule Trigger** Schedule trigger *Starts it*
- 2 **Démarrer** Manual trigger *Starts it*
- 3 **Groq Model1** Lm Chat Groq *Model*
- 4 **Simple Memory2** Memory Buffer Window *Model*
- 5 **Simple Memory3** Memory Buffer Window *Model*
- 6 **Groq Chat Model4** Lm Chat Groq *Model*
- 7 **Groq Chat Model2** Lm Chat Groq *Model*
- 8 **Error Trigger** Error trigger *Starts it*
- 9 **Groq Chat Model3** Lm Chat Groq *Model*
- 10 **Groq Model2** Lm Chat Groq *Model*
- 11 **Groq Chat Model5** Lm Chat Groq *Model*
- 12 **Groq Chat Model6** Lm Chat Groq *Model*
- 13 **Générer Contenu LinkedIn2** Agent *Model*
- 14 **Générer Contenu LinkedIn1** Agent *Model*
- 15 **verificateur1** Agent *Model*
- 16 **marketing1** Agent *Model*
- 17 **optimiser la version final1** Agent *Model*
- 18 **message erreur** Telegram *Service*
- 19 **verificateur2** Agent *Model*
- 20 **optimiser la version final2** Agent *Model*
- 21 **marketing2** Agent *Model*
- 22 **Verification finale1** Code *Logic*
- 23 **Parser Vérificateur** Code *Logic*
- 24 **Verification finale2** Code *Logic*
- 25 **IF Validation finale1** If *Logic*
- 26 **IF Validation finale2** If *Logic*
- 27 **Succes publication1** Set *Logic*
- 28 **Message erreur1** Set *Logic*
- 29 **Succes publication2** Set *Logic*
- 30 **Message erreur2** Set *Logic*
- 31 **Create a post1** Linked In *Service*
- 32 **vrai et pret a verifier1** Telegram *Service*
- 33 **Create a post2** Linked In *Service*
- 34 **attrendre 1 minute** Wait *Logic*

## How it's built

- **Starts on:** A clock
- **Steps:** 34, with 2 branches, 1 loop or waits
- **Size:** Large: read it before trusting it with anything live
- **Connects to:** LinkedIn, Telegram
- **Model:** Groq
- **Retrieval:** Answers are drawn from documents you supply, not from the model alone

## Questions

What does it need to run?

An n8n account, plus your own LinkedIn and Telegram accounts, and a key for Groq. 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 Groq. Its answers draw on documents you give it, not on the model alone. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Take your time. At 34 steps it is large: read it before trusting it with anything live.

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 34 steps before you point it at anything that matters.

## Run it in n8n

- **Create your n8n account** Free to start. n8n is where the workflow runs. [Create an n8n account ↗](https://millionrounds.com/n8n)
- **Download the workflow** Free with a Millionrounds account. [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fcreate-and-optimize-b2b-linkedin-ai-posts-with-groq)
- **Paste it into n8n** Open a new workflow in n8n and paste. Then connect your own accounts.

Stored with the author's traces removed: canvas notes, instance identifiers, saved credential names and any live document they had left behind.

## Connects to

Each opens the other workflows that use it.

[LinkedIn](https://millionrounds.com/workflows?service=LinkedIn#library)[Telegram](https://millionrounds.com/workflows?service=Telegram#library)

## Workflows like it

Also alerts and monitoring, with the same services where possible, closest in size first.

- [**Manage Supabase database records with Telegram** 34 steps · Supabase, Telegram](https://millionrounds.com/workflow/manage-supabase-database-records-with-telegram)
- [**Automate PPOB business operations with Telegram Bot** 33 steps · Telegram](https://millionrounds.com/workflow/automate-ppob-business-operations-with-telegram-bot)
- [**Manage on-campus event attendance with Google Sheets** 35 steps · Gmail, Google Sheets](https://millionrounds.com/workflow/manage-on-campus-event-attendance-with-google-sheets)
- [**Onboard frontline workers with Telegram and DeepSeek** 35 steps · Notion, Telegram](https://millionrounds.com/workflow/onboard-frontline-workers-with-telegram-and-deepseek)
- [**Automate delivery confirmation with Telegram Bot** 32 steps · Gmail, Google Drive](https://millionrounds.com/workflow/automate-delivery-confirmation-with-telegram-bot)
- [**Reply to Instagram comments with Groq and Telegram** 32 steps · Google Sheets, Telegram](https://millionrounds.com/workflow/reply-to-instagram-comments-with-groq-and-telegram)