Marcelo Emmerich

• • •

[Marcelo Emmerich @EmmerichMarcelo]

We just claimed our .agent domain and joined Agent Community! Get yours now and help shape the future of autonomous agents https://t.co/ew5mQcCPsm @agentcommunity_

[Marcelo Emmerich @EmmerichMarcelo]

I’m increasingly convinced most custom software is just expensive glue.

Integrations, adapters, CRUD, orchestration, internal dashboards, brittle workflows.

In the AI era, a lot of that should move from coded software to configured systems:
- reusable tools
- bounded agents
- explicit contracts
- human escalation where needed

Compose, don’t rebuild.
Adapt, don’t maintain.

The teams that understand this early are going to look unfairly fast.

[Marcelo Emmerich @EmmerichMarcelo]

Most “AI products” are still regular software with an LLM bolted on top.

That’s not agentic architecture. That’s garnish.

The real shift is:
- agent as kernel
- MCP tools as capability layer
- APIs / DBs / PDFs / websites / legacy systems as raw material

Once you model the stack that way, you stop asking “where do we add AI?” and start asking “what parts of this system should still be hardcoded at all?”

That’s a much more interesting question.

[Marcelo Emmerich @EmmerichMarcelo]

@Matt_Pinner Sure.

[Marcelo Emmerich @EmmerichMarcelo]

@Gamingtronium That is not a backup plan. It will be like that and that is the actual plan.

[Marcelo Emmerich @EmmerichMarcelo]

@Ravenismeee In the Brenta Dolomites or near Chamonix.

[Marcelo Emmerich @EmmerichMarcelo]

I never thought this would happen. I mean, I did say that git itself is at stakes due to agentic engineering, but not for just being unreliable.

[Mitchell Hashimoto @mitchellh]

Ghostty is leaving GitHub. I'm GitHub user 1299, joined Feb 2008. I've visited GitHub almost every single day for over 18 years. It's never been a question for me where I'd put my projects: always GitHub. I'm super sad to say this, but its time to go. https://t.co/DQDemHdytV

[Marcelo Emmerich @EmmerichMarcelo]

@big_duca True. But it's the early days, people are learning, exploring. It will get more normal once it has become mainstream.

[Marcelo Emmerich @EmmerichMarcelo]

@felangelov Me too, but I guess that will become a thing of the past or stay alive in very specific niches.

[Marcelo Emmerich @EmmerichMarcelo]

@kalashnikovapv Yeah, same for me. I am trying to motovate me to do 20 push-ups instead of playing Candy Crush while waiting 😂

[Marcelo Emmerich @EmmerichMarcelo]

New Post: The Hard Part of Agentic Software Is Not the Agent

📖 Read: https://t.co/4FJEnBYPvn
🎧 Listen: https://t.co/Sji1MeIStC

[Marcelo Emmerich @EmmerichMarcelo]

https://t.co/qcRycHSarx

[Marcelo Emmerich @EmmerichMarcelo]

https://t.co/qcRycHSarx

[Marcelo Emmerich @EmmerichMarcelo]

The market rewards AI theater.
Reality rewards operational sharpness.

I’m much more interested in founders who can answer:
- where does the data come from?
- what gets escalated?
- what stays deterministic?
- what breaks when the source changes?

That’s the difference between a demo and a company.

[Marcelo Emmerich @EmmerichMarcelo]

AI in travel gets real very fast.

You start with “build a hotel seller.”
Then reality shows up:
- room types named differently across brands
- occupancy rules that don’t map cleanly
- partial pricing
- external booking engines
- inconsistent data everywhere

If your architecture only works on polished demo inventory, it doesn’t work.

[Marcelo Emmerich @EmmerichMarcelo]

@karomancer No, I don't "use" it anymore in the sense that I post regularly or build an audience. I do that here in X now.

[Marcelo Emmerich @EmmerichMarcelo]

I genuinely cannot hear the word "align" anymore. Everything and everyone have to "align" to everything and everyone. Corporate is doomed, let's align on that 😂

[Marcelo Emmerich @EmmerichMarcelo]

What makes MCP interesting is not function calling.

It’s the architectural consequence of interchangeable capabilities.

Swap the booking backend.
Keep the kernel.
Swap the data source.
Keep the behavior.
Swap the surface.
Keep the system.

That’s a much bigger shift than “LLMs can use tools now.”

[Marcelo Emmerich @EmmerichMarcelo]

Hot take: most custom business software is still just expensive translation work between systems.

That’s why I’m so bullish on composable tool layers.

If an agent can interpret semantics and tools provide stable capability boundaries, a lot of the old application layer starts to look unnecessary.

That’s the opportunity: not better glue. Less glue.

[Marcelo Emmerich @EmmerichMarcelo]

The hard part of agentic software is not the agent.

It’s everything around it:
- permissions
- tool boundaries
- escalation rules
- memory
- versioning
- auditability

If your whole product story is “we have a smart model,” you’re still at the toy layer.

[Marcelo Emmerich @EmmerichMarcelo]

https://t.co/zvv5MuuJgT