Leonid Bugaev

Feel free to ask questions :)

MVP - Maximum Vibe Product

Important change with AI, that it is ok to re-roll the dice to wipe all previous work, and re-do it with updated prompt, rather then trying to fix whats already done. The work itself becomes very cheap, the most expensive part here is capacity of human to review and think.

The recent agent-to-agent protocol more than just a technological solution, it is attempt to "fix" colapsing SaaS economy and API market, and moving to value based pricing.

Vendors will likely shift to charging for the actual value they deliver rather than billing per API call.

Over time, I see public API usage dropping off, but total API usage skyrocketing – as these agents will make a ton of calls behind the scenes. MCPs are still in a technical adoption phase, but they will evolve with more user‑friendly experiences.

So their plan is to restrict API access and push official “A2A agents,” selling them as virtual employees. In the future, you might just visit some developer portal and rent as many virtual workers as you want, each capable of parallel tasks, etc.

Why would they do that? Because most SaaS vendors want total control over their products and how they’re used. With these “shadow” MCP integrations, they lose the ability to track usage or enforce pricing.

We’re also seeing major companies sign up for this kind of format, because it preserves their revenue streams. I fully expect more vendors to limit or even block their existing APIs, raise prices, or make them available only through premium tiers. (Twitter did quite long time ago.)

Google’s new A2A protocol helps address this issue. From a pure technology angle, I like it. You can schedule tasks, define “skills,” and basically treat these agents like virtual employees. It’s probably the direction the industry is heading.

Now, with MCP and agentic stuff, you can deliver an experience so good it might actually beat the vendor’s own UI. That’s alarming for SaaS providers because you basically get 90 % of the value at 10 % of the price – and they lose control.

Historically, API usage wasn’t a big threat, because sure, you could export data, crunch numbers, or build some custom scripts, but replicating a polished user interface or full product experience was too much hassle.

Think about it: why pay for an extra seat on a SaaS platform – like Zendesk – if you can just integrate its API into your chatbot and let everyone in your team access it? Vendors often can’t even tell if your requests are coming from AI or human users.

First of all, the recent agent‑to‑agent (A2A) protocol that Google introduced isn’t really some massive tech breakthrough in itself. It’s more like an attempt to fix the very shaky SaaS economy, which is getting hammered by “shadow API usage.”

The recent agent-to-agent protocol more than just a technological solution, it is attempt to "fix" colapsing SaaS economy and API market, and moving to value based pricing.

GitHub - buger/docs-mcp Contribute to buger/docs-mcp development by creating an account on GitHub.

Now you can chat with documentation or code, via MCP, just by specifying github url - all search happens locally!

More over you can create your own MCP servers, with pre-baked data!

The easiest way to create MCP so far!

All free and Open Source.

github.com/buger/docs-mcp

Chatting with AI changed the "search" paradigm - simplifying it to Question -> Answer format.
No wonder it become so addictive.

MCP changes the game again, bringing it local and adding action to the flow:

Question -> Answer -> Action

Don’t underestimate its power.

Chatting with AI changed the "search" paradigm - simplifying it to Question -> Answer format.
No wonder it become so addictive.

MCP changes the game again, bringing it local and adding action to the flow:

Question -> Answer -> Action

Don’t underestimate its power.

GitHub - buger/docs-mcp Contribute to buger/docs-mcp development by creating an account on GitHub.

Now you can chat with documentation or code, via MCP, just by specifying github url - all search happens locally!

More over you can create your own MCP servers, with pre-baked data!

The easiest way to create MCP so far!

All free and Open Source.

github.com/buger/docs-mcp

Important change with AI, that it is ok to re-roll the dice to wipe all previous work, and re-do it with updated prompt, rather then trying to fix whats already done. The work itself becomes very cheap, the most expensive part here is capacity of human to review and think.

Recently started spending more time working outside. Living in a sunny place, it’s almost impossible to use a laptop outdoors.

I’ve been using these Xreal One glasses - like portable monitors, not VR. They look a bit odd on calls, but honestly, it’s working really well for me.

Recently started spending more time working outside. Living in a sunny place, it’s almost impossible to use a laptop outdoors.

I’ve been using these Xreal One glasses - like portable monitors, not VR. They look a bit odd on calls, but honestly, it’s working really well for me.

MVP - Maximum Vibe Product

These questions about training, career progression, and future engineering roles are crucial. Even without clear answers, they're important conversations to explore.

With advanced AI tools, anyone in a company—not just product managers but people in virtually any role—could handle tasks traditionally done by coding juniors. Does it then still make sense to hire dedicated coding juniors?

Juniors are valuable in startups for rapid experimentation and innovation. But transitioning from early-stage ideas to sustainable, scalable growth remains unclear. Could mid-level roles vanish, increasing demand for seniors?

But a key issue remains: how can we ensure juniors still acquire foundational classical engineering knowledge, especially as these traditional skills are becoming less commonly practiced yet remain important?

Currently, I'd hesitate hiring juniors for complex products due to mentoring overhead and uncertainty about evaluating their potential. At my current company, I've successfully mentored four juniors to seniors and one to tech lead.

This shift could work for simpler apps, but complex enterprise systems might suffer from increasing complexity and technical debt unless AI also learns to manage complexity automatically.

Perhaps soon, AI will handle architecture, security, and essential considerations automatically. Traditional engineering skills might matter less, replaced instead by broader product vision and overall effectiveness.