n8n & Python automation

Stop re-keying the same data into three tools.

When systems don’t talk, people become the integration. I build n8n and Python workflows that do that part, and check what they produce against data you already trust.

workflow · new enquiry → CRMIllustration
FormNew enquiry
CleanDeduplicate
CheckRules, then AI
CRMQualified lead
09:12  24 enquiries in
09:12  22 qualified → CRM
09:12  1 duplicate merged
09:12  1 stopped: missing email, sent back for review
Illustration. A made-up run: every step says what it did, and bad input stops instead of passing on.

Recent automation work

Where I’ve done this.

Ten Lives · Portugal

Supplier scraping and enrichment

Portuguese directories, deduplicated and filterable by region, certification and category.

PythonGoogle Places API
Ten Lives · Portugal

Volunteer onboarding

For the same festival. Still being built.

In progress
Rapidos.ai · 2025–26

Lead qualification and knowledge bases

n8n workflows and internal AI agents.

n8nAI agents
Galene Pathways · co-founder

Environmental data pipelines

Internal data workflows and scripts.

Python

All recent work →

Example: Ten Lives supplier pipeline

From scattered listings to one usable list.

  1. CollectPortuguese directories and the Google Places API.
  2. CleanThe same business in several places becomes one record.
  3. EnrichTagged by region, certification and category.
  4. UseOne list, filtered to what’s needed.

What I build

n8n and Python workflows that fail loudly.

Data copied every week

Integrations

Between the tools you already use, over their APIs.

Lists out of date

Data pipelines

Collect, clean, deduplicate and load, on a schedule.

Requests sorted by hand

Triage and qualification

Rules first, an AI step only where it earns its place.

Automations nobody watches

Guardrails

Each step logs what it did and stops on bad input.

How it runs

One workflow first, on real data.

First step, free

A 20-minute call about one manual step.

One workflow, one fixed price

Quoted after a call, checked on real data before the next.

On your accounts, documented

Your credentials, and a note on how to switch it off.

Describe one manual step.

What gets copied, from where, to where, and how often. I’ll tell you whether it’s worth automating, and what that would involve.