We have two amazing speakers confirmed for our CTO Circle event in Madrid on May 20.

Javier Turégano - Leadership Coach, former Director of Engineering at Canva and Slack.

Javier Moscardó - Director of Engineering at Multiverse, ex-Spotify.

We'll also host an open discussion around the topics that matter most to the group.

Madrid - Playtomic's office - May 20. CTO networking, tapas, and short talks from engineering leaders. Apply here!

Over the last few weeks, I've been hearing one term everywhere: Harness Engineering.

The term seems to have first been used publicly by Mitchell Hashimoto, co-founder of HashiCorp and Terraform, in February in My AI Adoption Journey. His point was simple: when an AI agent makes a mistake, you shouldn't just fix the prompt; you should change the system so that mistake doesn't happen again.

Shortly after, OpenAI helped popularize the term when talking about how they use Codex in an agent-first environment.

I think we're coming from here:

Prompt engineering was learning how to ask.

Context engineering was learning what information to give the model.

Harness engineering is learning how to build the environment where the agent works.

Tests. CI. Linters. Permissions. Tools. Memory. Skills. Repo rules. Workflows. Review gates. Scope limits.

Basically, everything that turns an agent from "a model writing code" into a working part of an engineering system.

The interesting part is that this is still not fully defined.

Every company, every team, and maybe even every developer is building their own harness right now. Their own way of saying: "This is how we work here."

The future won't just be about better models. It will be about better systems around the models.

Other reads on this trend:

Agent Skills - By Addy Osmani | SWE at Google.

The Agent Harness Belongs Outside the Sandbox - Andrea Luzzardi | Cofounder at Dagger and Mendral.

Specsmaxxing - Acai.sh.

10 Lessons for Agentic Coding. When code becomes cheap, the real advantage shifts to learning fast through implementation, rebuilding often, investing in tests and intent, automating the easy parts, and using taste and experience to focus on the hard problems that still make software valuable.

Formatting an entire 25 million line codebase overnight: the rubyfmt story. Stripe explains how it built and rolled out rubyfmt, a fast zero-config Ruby autoformatter, across the world's largest Ruby codebase to eliminate formatting debates, reduce developer friction, and make Ruby easier to work with at massive scale.

GPT-5.5 matches heavily hyped Mythos Preview in new cybersecurity tests. GPT-5.5's new cybersecurity test results suggest that advanced cyber capabilities are emerging across frontier AI models generally, not as a unique breakthrough limited to Anthropic's heavily hyped Mythos Preview.

Musk's trial against Sam Altman and OpenAI enters its second week, centered on whether OpenAI betrayed its original nonprofit mission as testimony reveals early power struggles, funding disputes, conflicts of interest, and Musk's attempts to control the company.

Open Design. A local-first, open-source alternative to Anthropic's Claude Design.

Open Spec. Open-source spec-driven development for AI coding assistants. Alternative to Spec Kit (GitHub) and Kiro (AWS).

Recently, I received this message from someone in the community, referring to our bot that organizes virtual coffees between engineering leaders:

"Hey Marco! I just wanted to tell you that CTO Circle has been a game-changer for my career. I'm not sure you realize the impact it has for an IC moving toward a Tech Lead / CTO role to have regular conversations with much more experienced CTOs. The quality of insights that come out of those chats is truly incredible."

This made my day.

If you'd like to join those weekly coffee chats too, you can join the #virtual-coffee-1-1 channel.

But first, you need to join the Slack community.

Vivara is hiring a Head of Engineering | Barcelona

Preply is hiring a Senior Engineering Manager | Barcelona

Docplanner if hiring an Engineering Director | 100% Remote within Spain

GrafanaLabs is hiring an Engineering Manager | Remote within Spain

Datadog is hiring a Manager I, Engineering - Code Coverage | Madrid

Deel is hiring a Head of Engineering - Fintech | EMEA

FEVER is hiring an Engineering Lead | Madrid

JetBrains is hiring a Head of ML | Madrid

Perk is hiring an Engineering Manager | Barcelona

Preply is hiring a Senior Engineering Manager | Barcelona