Skip to content

LLM ready

/en/services/ai-data-automation.md

Title:
AI, data and automation

Less manual work. More routines that run on their own.

I map today’s repetitive work, help choose the first routine worth automating, and deliver it running with real data, tests and instructions.

Tools I use: Python, Polars, pandas, FastAPI, PostgreSQL, Google Cloud.

Manual routines don’t scale

While someone copies and checks by hand, errors and delays come along.

Manual routine

  • Someone copies data from one tool to another
  • Every file arrives in a different format
  • Checks depend on whoever is on duty
  • The report goes out when it can
  • An error only shows up when someone complains

Automated routine

  • The tools exchange data on their own
  • Input is standardised before it moves on
  • Validation rules stop bad data
  • The report goes out on schedule
  • An alert arrives when the routine fails

Where an automation usually goes wrong

This is what I check before the routine runs on its own.

  • Input data (Critical): Files with swapped columns, broken accents and dates in different formats.
  • Validation (Critical): Without checks, the automation spreads the error faster.
  • Duplicates (High): The same row processed twice turns into a wrong charge or wrong stock.
  • Silent failures (High): The routine stops and nobody notices until the report fails to arrive.
  • Tool access (Medium): Integration passwords and keys stored carelessly.
  • Regression tests (Medium): A change in the input format breaks what used to work.

From manual work to an automatic routine

The same task, before and after. Every automated step has its own check.

Today, by hand

  1. Download the files
  2. Copy into the spreadsheet
  3. Fix the formats
  4. Check row by row
  5. Build the report

Then, automatic

  1. Receive the files
  2. Standardise the data
  3. Validate the rules
  4. Write to the destination
  5. Send the report

From mapping to a routine that runs on its own

Three phases. The first routine goes live before anything grows.

  1. Mapping: We record inputs, outputs and checks.
    • Current workflow
    • Scope of the first routine
  2. First routine: I integrate the tools and verify the data.
    • Integrations
    • Routine tests
  3. Follow-up: You get instructions and know when to act.
    • Operating instructions
    • Routine failure alerts

How it starts

You know which routine will be automated, and how it will be checked, before you approve.

  1. First conversation: Show me the routine that takes the most time.
    • 30 minutes, at no cost.
  2. Mapping: We review the workflow and its data sources.
    • Current workflow
    • Scope of the first routine
  3. First routine: We verify the result with a controlled sample of real data.
    • Integrations
    • Routine tests
  4. Delivery and follow-up: I deliver the routine with instructions and failure alerts.
    • Operating instructions
    • Routine failure alerts

What you get

  • Integration between tools
  • Data processing and normalization
  • Automated reports
  • Fewer manual errors
  • Routine tests
  • Instructions for automatic and manual steps
  • Routine failure alerts

See the potential before you invest

Mapping helps you choose the first routine worth automating.

  • Free first conversation: Show me where work gets stuck.
  • Automation by routine: Mapping helps you choose where to start.
  • Data validation: Tests help find failures in the routine.

What the automation excludes

  • Full data history: Cleaning the entire history at once is outside the scope.
  • Licenses: You handle tool licenses.
  • Decisions without review: AI decisions need human review.

Who handles the work

I follow the workflow from data sources to operating instructions. I verify inputs and outputs with tests.

Agents in my workflow: Claude Code, Codex, Grok, Agy, Cursor.

If one of these sounds familiar, it is time to automate

  • “I spend the morning copying data from one spreadsheet to another.”
  • “Every client sends the file in a different format.”
  • “Monday’s report is only ready on Wednesday.”
  • “We have already paid dearly for a typo.”
  • “Only one person knows how to run this process.”

Frequently asked questions

Will I need to replace my tools?

I start by mapping the tools you already use.

Can we start with one routine?

Yes. Mapping helps define that scope.

Which details get set during mapping?

We map the data, the tools involved and the first routine to automate.

How will I find out about failures?

The handover includes alerts if the routine fails and instructions for responding.

---
title: AI, data and automation
url: https://nandomoreira.dev/en/services/ai-data-automation
---

# Less manual work. More routines that run on their own.

I map today’s repetitive work, help choose the first routine worth automating, and deliver it running with real data, tests and instructions.

Tools I use: Python, Polars, pandas, FastAPI, PostgreSQL, Google Cloud.

## Manual routines don’t scale

While someone copies and checks by hand, errors and delays come along.

### Manual routine

- Someone copies data from one tool to another
- Every file arrives in a different format
- Checks depend on whoever is on duty
- The report goes out when it can
- An error only shows up when someone complains

### Automated routine

- The tools exchange data on their own
- Input is standardised before it moves on
- Validation rules stop bad data
- The report goes out on schedule
- An alert arrives when the routine fails

## Where an automation usually goes wrong

This is what I check before the routine runs on its own.

- **Input data** (Critical): Files with swapped columns, broken accents and dates in different formats.
- **Validation** (Critical): Without checks, the automation spreads the error faster.
- **Duplicates** (High): The same row processed twice turns into a wrong charge or wrong stock.
- **Silent failures** (High): The routine stops and nobody notices until the report fails to arrive.
- **Tool access** (Medium): Integration passwords and keys stored carelessly.
- **Regression tests** (Medium): A change in the input format breaks what used to work.

## From manual work to an automatic routine

The same task, before and after. Every automated step has its own check.

### Today, by hand

1. Download the files
2. Copy into the spreadsheet
3. Fix the formats
4. Check row by row
5. Build the report

### Then, automatic

1. Receive the files
2. Standardise the data
3. Validate the rules
4. Write to the destination
5. Send the report

## From mapping to a routine that runs on its own

Three phases. The first routine goes live before anything grows.

1. **Mapping:** We record inputs, outputs and checks.
   - Current workflow
   - Scope of the first routine
2. **First routine:** I integrate the tools and verify the data.
   - Integrations
   - Routine tests
3. **Follow-up:** You get instructions and know when to act.
   - Operating instructions
   - Routine failure alerts

## How it starts

You know which routine will be automated, and how it will be checked, before you approve.

1. **First conversation:** Show me the routine that takes the most time.
   - 30 minutes, at no cost.
2. **Mapping:** We review the workflow and its data sources.
   - Current workflow
   - Scope of the first routine
3. **First routine:** We verify the result with a controlled sample of real data.
   - Integrations
   - Routine tests
4. **Delivery and follow-up:** I deliver the routine with instructions and failure alerts.
   - Operating instructions
   - Routine failure alerts

## What you get

- Integration between tools
- Data processing and normalization
- Automated reports
- Fewer manual errors
- Routine tests
- Instructions for automatic and manual steps
- Routine failure alerts

## See the potential before you invest

Mapping helps you choose the first routine worth automating.

- **Free first conversation:** Show me where work gets stuck.
- **Automation by routine:** Mapping helps you choose where to start.
- **Data validation:** Tests help find failures in the routine.

## What the automation excludes

- **Full data history:** Cleaning the entire history at once is outside the scope.
- **Licenses:** You handle tool licenses.
- **Decisions without review:** AI decisions need human review.

## Who handles the work

I follow the workflow from data sources to operating instructions. I verify inputs and outputs with tests.

Agents in my workflow: Claude Code, Codex, Grok, Agy, Cursor.

## If one of these sounds familiar, it is time to automate

- “I spend the morning copying data from one spreadsheet to another.”
- “Every client sends the file in a different format.”
- “Monday’s report is only ready on Wednesday.”
- “We have already paid dearly for a typo.”
- “Only one person knows how to run this process.”

## Frequently asked questions

### Will I need to replace my tools?

I start by mapping the tools you already use.

### Can we start with one routine?

Yes. Mapping helps define that scope.

### Which details get set during mapping?

We map the data, the tools involved and the first routine to automate.

### How will I find out about failures?

The handover includes alerts if the routine fails and instructions for responding.

Ready to share.