Another try at LLM workflow automation

📰 Medium · LLM

Learn to automate LLM workflows by understanding the role of human intervention and iteration in achieving optimal results

intermediate Published 18 Apr 2026

Action Steps

Analyze your current LLM workflow automation approach to identify areas where human intervention is necessary
Iterate on different approaches to find the best possible solution for your specific use case
Enforce standards and constraints to guide the model towards optimal results
Use techniques like copy-pasting or recombining model outputs to refine the final solution
Reflect on your own workflow automation attempts to recognize potential loops or inefficiencies

Who Needs to Know This

Data scientists and AI engineers can benefit from this article as it highlights the importance of human oversight in automating LLM workflows, enabling them to design more effective automation strategies

Key Insight

💡 Human intervention and iteration are crucial in achieving optimal results in LLM workflow automation

Key Takeaways

Learn to automate LLM workflows by understanding the role of human intervention and iteration in achieving optimal results

Full Article

Title: Another try at LLM workflow automation

URL Source: https://medium.com/@rafalneves/another-try-at-llm-workflow-automation-9910090df74f?source=rss------llm-5

Published Time: 2026-04-18T20:00:32Z

Markdown Content:
# Another try at LLM workflow automation | by José Neves | Apr, 2026 | Medium

[Sitemap](https://medium.com/sitemap/sitemap.xml)

[Open in app](https://play.google.com/store/apps/details?id=com.medium.reader&referrer=utm_source%3DmobileNavBar&source=post_page---top_nav_layout_nav-----------------------------------------)

Sign up

[Sign in](https://medium.com/m/signin?operation=login&redirect=https%3A%2F%2Fmedium.com%2F%40rafalneves%2Fanother-try-at-llm-workflow-automation-9910090df74f&source=post_page---top_nav_layout_nav-----------------------global_nav------------------)

[](https://medium.com/?source=post_page---top_nav_layout_nav-----------------------------------------)

Get app

[Write](https://medium.com/m/signin?operation=register&redirect=https%3A%2F%2Fmedium.com%2Fnew-story&source=---top_nav_layout_nav-----------------------new_post_topnav------------------)

[Search](https://medium.com/search?source=post_page---top_nav_layout_nav-----------------------------------------)

Sign up

[Sign in](https://medium.com/m/signin?operation=login&redirect=https%3A%2F%2Fmedium.com%2F%40rafalneves%2Fanother-try-at-llm-workflow-automation-9910090df74f&source=post_page---top_nav_layout_nav-----------------------global_nav------------------)

![Image 1](https://miro.medium.com/v2/resize:fill:32:32/1*dmbNkD5D-u45r44go_cf0g.png)

# Another try at LLM workflow automation

[![Image 2: José Neves](https://miro.medium.com/v2/resize:fill:32:32/1*XfcLoBL7AoRVE98IKWfftg.jpeg)](https://medium.com/@rafalneves?source=post_page---byline--9910090df74f---------------------------------------)

[José Neves](https://medium.com/@rafalneves?source=post_page---byline--9910090df74f---------------------------------------)

Follow

8 min read

·

Just now

[](https://medium.com/m/signin?actionUrl=https%3A%2F%2Fmedium.com%2F_%2Fvote%2Fp%2F9910090df74f&operation=register&redirect=https%3A%2F%2Fmedium.com%2F%40rafalneves%2Fanother-try-at-llm-workflow-automation-9910090df74f&user=Jos%C3%A9+Neves&userId=9a7adc3ad581&source=---header_actions--9910090df74f---------------------clap_footer------------------)

[](https://medium.com/m/signin?actionUrl=https%3A%2F%2Fmedium.com%2F_%2Fbookmark%2Fp%2F9910090df74f&operation=register&redirect=https%3A%2F%2Fmedium.com%2F%40rafalneves%2Fanother-try-at-llm-workflow-automation-9910090df74f&source=---header_actions--9910090df74f---------------------bookmark_footer------------------)

[Listen](https://medium.com/m/signin?actionUrl=https%3A%2F%2Fmedium.com%2Fplans%3Fdimension%3Dpost_audio_button%26postId%3D9910090df74f&operation=register&redirect=https%3A%2F%2Fmedium.com%2F%40rafalneves%2Fanother-try-at-llm-workflow-automation-9910090df74f&source=---header_actions--9910090df74f---------------------post_audio_button------------------)

Share

After trying time and again, with what I now recognize as a sort of blind approach to LLM workflow automation, I kept landing on the same conclusion: the best results required a brain behind it. Of course, this depends on what you are trying to achieve; in my case, I still stand by that.

But now that the AI fever has passed — or maybe not — I took a new look at what the brain was doing that the machine wouldn’t. Again and again, I’d find myself enforcing standards, iterating on different approaches to find the best possible solution, forcing the model out of loops, making it see things “my way,” or… simply… copy-pasting different parts of the final solution that I wanted.

Press enter or click to view image in full size

![Image 3](https://miro.medium.com/v2/resize:fit:700/0*OcQJCuXZNNis-YRm.jpg)

I think I was in a loop of my own, betting that AI automation (or rather, my definition of it) would arrive when the models finally got smart enough.

The more I build with it, the

Read full article → ← Back to Reads

Another try at LLM workflow automation

Key Takeaways

Full Article

Related Videos