---
title: "A Netherlands AI agency founder says Claude Code agents let him do about 4.2x the work of a 2023 week, including 250 company reports in two minutes"
person: "Jonas Braadbaart"
profile: "https://metacircuits.substack.com/about"
tools:
  - "Claude Code"
  - "Make"
  - "Perplexity"
  - "Apollo"
  - "Obsidian"
  - "Figma"
country: "Netherlands"
category: "Get tasks done"
category_slug: get-tasks-done
proof:
  - label: "Read his post on Substack"
    url: "https://metacircuits.substack.com/p/last-week-i-worked-28-hours-my-ais"
date: 2026-11-06
date_posted: 2026-03-09
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/jonas-braadbaart-claude-agents-4x-week.html"
markdown_url: "https://agentstories.org/stories/jonas-braadbaart-claude-agents-4x-week.md"
site: "Agent Stories by Solopreneur Code"
---

# A Netherlands AI agency founder says Claude Code agents let him do about 4.2x the work of a 2023 week, including 250 company reports in two minutes

Jonas Braadbaart · Netherlands · Claude Code, Make, Perplexity, Apollo, Obsidian, Figma

## What the agent did

Jonas runs three Claude Code workspaces for content, his AI agency and research, plus Make.com automations for a voice second brain, Substack tagging and a daily AI news roundup. In the week he tracked, agents helped pre-screen thousands of companies, research hundreds of them and draft personalised company reports for outreach, while he kept final emails and strategy in his own hands.

## Result, as claimed

In one tracked week he worked 28 hours while his agents put in about 90. He says he got about 4.2x as much done as in 2023. Agents pre-screened 6,000 companies and did deeper research on 250, and he says the setup can create 250 personalised company reports in two minutes. He also names lead generation as about 20x faster, research 4x, AI-assisted coding 8x and content 3x versus his 2023 baseline.

> 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 his post on Substack](https://metacircuits.substack.com/p/last-week-i-worked-28-hours-my-ais)

## Try it yourself

Turn a downloaded company list into a short shortlist with fit notes and a next step for each keep.

Prompt:

```text
I sell [offer] to [ideal customer]. I pasted a list of companies below. For each company, use public web info only and say: what they appear to do, whether they fit my offer (yes, maybe, or no), one reason, one risk, and the next step if yes. Drop any company where you cannot find a real website. Mark anything you could not confirm as [check]. End with a ranked shortlist of the top [number] keeps and a one-line reason for each drop.
```

Tools:

- [Claude Code](https://claude.ai/code): Named in the story as the main computer agent
- [Make](https://www.make.com/en/register?pc=anferneeck): Named for his background automations
- [Perplexity](https://www.perplexity.ai): Named for company and strategy research
- [Apollo](https://www.apollo.io): Named for the company list export

Steps:

1. Export a company list from your data tool with name, website and size.
2. Paste your offer, ideal customer and the list into the prompt.
3. Open every keep and confirm the website yourself before you write.
4. Save the shortlist and draft one outreach note per keep by hand.

Watch out: Agent research invents fit. Open each site and check the facts before you send anything.

## More

- [This story as a web page](https://agentstories.org/stories/jonas-braadbaart-claude-agents-4x-week.html)
- [More stories: Get tasks done](https://agentstories.org/categories/get-tasks-done.html)
- [More stories from Netherlands](https://agentstories.org/countries/netherlands.html)
- [More stories that use Claude Code](https://agentstories.org/tools/claude-code.html)
- [More stories that use Make](https://agentstories.org/tools/make.html)
- [More stories that use Apollo](https://agentstories.org/tools/apollo.html)
- [More stories that use Obsidian](https://agentstories.org/tools/obsidian.html)
- [Every story, indexed for AI assistants](https://agentstories.org/llms.txt)
