CTO Circle

Barcelona CTO Lunch, AI Playbooks, AI Costs

Reply-To: marco@pullpo.io

Issue 009

Ninth issue

GuruSup x CTO Circle: 95% of support tickets resolved without a human

800,000 support tickets a year. One person running the team.

GuruSup builds AI agents for customer support that resolve requests end-to-end: not just routing or deflecting them.

They integrate with your existing tools, work across 6 languages, and handle the volume spikes that break human teams without seasonal hiring.

CTO Circle members get 20% off the first year.

Get 20% off your first year

Next community events.

Last CTO Lunch in Barcelona before summer - Barcelona - Itnig - June 22nd

CTO networking, tapas, and short talks from engineering leaders. Apply here!

Short opinionated trend: Creating your own playbook for AI engineering.

In software, we are used to hearing the term best practices.

Writing tests is a best practice. Version control, CI/CD, code reviews... they are industry standards that save us from rethinking the same decisions over and over again.

I don't know many teams that start a new project by seriously debating whether to use Mercurial instead of Git.

Now, with AI, everyone is trying to find the new best practices.

We hear about RPI (Research, Plan, Implement). Spec-driven development. Context engineering. Harness engineering. Code review agents. AI coding workflows.

But two things are happening.

First: there are no real best practices yet.

We are still creating them. We don't really know what works best. That's why it is so important to look at what other teams are doing, experiment internally, and build your own playbook.

Second: the context is moving faster than our ability to adapt.

What felt like a best practice two months ago may already feel outdated today. A year ago, LangChain was everywhere. Now I barely hear teams talk about it.

And we may be entering another major context shift: AI costs that were heavily subsidized may not stay that way forever.

The reality is that this will keep changing.

Some practices will stay. Some will disappear. Some will only make sense for a few months.

So for now, the best thing we can do is watch what other teams are trying, experiment internally, and avoid turning any AI workflow into dogma too early.

AI engineering is still too young for that.

News, reads and launches.

Recent AI-linked layoffs include ClickUp cutting 22% of its workforce, Meta restructuring around AI investment, Intuit laying off 3,000+ employees to refocus on AI, and Groupon cutting nearly 25% as it tries to become "AI-native."

AI costs are becoming harder to justify: Uber burned through its 2026 AI budget in four months, Microsoft reportedly cut back Claude Code licenses, Nvidia executive says right now AI is more expensive than paying human workers

Karpathy said vibe coding is obsolete. What he described instead is product management

--dangerously-skip-reading-code. If AI makes it impossible to review every line of generated code, engineering rigor may need to move from reading diffs to owning specs, tests, and automated checks that define what the software should do.

AI-assisted engineers are burning out. AI-assisted coding can make engineers ship faster, but it also creates a new kind of burnout by replacing the satisfying craft of coding with high-intensity prompting, reviewing, context-switching, and pressure to produce more.

Use boring languages with LLMs. LLMs work better with boring, conventional languages and ecosystems because consistent training data, strong defaults, and standardized tooling produce more reliable agentic code than fragmented stacks with many "right" ways to do the same thing.

From the community.

Last week, we hosted a CTO gathering in Madrid, and it was great. From now on, we'll start uploading some of the talks here.

R** shared Don't Outsource the Learning. The article argues that using AI to close tasks faster is useful, but if you let it skip the struggle of understanding, you quietly trade long-term engineering judgment and learning for short-term productivity.

Feel free to join the Slack community here.