---
title: "A solo founder says moving Formula Bot's backend to n8n cut new connector builds from a week to about a day and a half"
person: "David Bressler (Formula Bot)"
tools:
  - "n8n"
  - "Bubble"
  - "AWS S3"
country: "Country unknown"
category: "Get tasks done"
category_slug: get-tasks-done
proof:
  - label: "Read the Formula Bot story on n8n"
    url: "https://n8n.io/case-studies/formula-bot/"
date: 2026-11-01
as_claimed: "The result is shown as claimed in the public source linked here. It has not been checked and is not a typical outcome."
url: "https://agentstories.org/stories/david-bressler-formula-bot-n8n-connectors.html"
markdown_url: "https://agentstories.org/stories/david-bressler-formula-bot-n8n-connectors.md"
site: "Agent Stories by Solopreneur Code"
---

# A solo founder says moving Formula Bot's backend to n8n cut new connector builds from a week to about a day and a half

David Bressler (Formula Bot) · Country unknown · n8n, Bubble, AWS S3

## What the agent did

David Bressler runs Formula Bot, an AI data analysis app, with Bubble for the front end and n8n for the backend. One orchestration agent in n8n takes each user request and decides which connector workflow to call, such as BigQuery, Snowflake or Google Analytics. About 90% of each connector workflow is a reusable template.

## Result, as claimed

Adding a new data connector went from about a week to around a day and a half. David estimates 20 to 30 hours saved per month, and hundreds of hours overall, by building workflows in n8n instead of maintaining custom Lambda functions and API code.

> The result is shown as claimed in the public source linked here. It has not been checked and is not a typical outcome.

## Proof

- [Read the Formula Bot story on n8n](https://n8n.io/case-studies/formula-bot/)

## Try it yourself

Build one router workflow that reads each request and hands it to the right sub-workflow, so each new integration reuses the same template.

Prompt:

```text
Help me design an n8n setup for [your app or business]. Requests come in from [source, such as a form or webhook] and need to go to one of these jobs: [list jobs, such as query Google Analytics, convert a PDF to a spreadsheet, scrape a page]. Design: 1. A router step that picks the right job from the request. 2. One template sub-workflow that every job can reuse, with only the data source swapped. 3. Where to put long jobs so the caller gets an instant reply. List the nodes for each part and what could fail.
```

Tools:

- [n8n](https://n8n.partnerlinks.io/t51hrijhextl): Named in the story. Runs the orchestration agent and connector workflows
- [Bubble](https://bubble.io): Named in the story. Front end and database layer

Steps:

1. List the jobs your app or business repeats.
2. Run the prompt and build the router and one template sub-workflow first.
3. Add a second job by copying the template and swapping only the data source.
4. Move any slow job behind a webhook that replies straight away.

Watch out: A router agent can send a request to the wrong workflow, so log every routing decision and test with real requests before customers use it.

## More

- [This story as a web page](https://agentstories.org/stories/david-bressler-formula-bot-n8n-connectors.html)
- [More stories: Get tasks done](https://agentstories.org/categories/get-tasks-done.html)
- [More stories that use n8n](https://agentstories.org/tools/n8n.html)
- [Every story, indexed for AI assistants](https://agentstories.org/llms.txt)
