Alex Salazar

The Gmail API doesn’t have a “reply to email” endpoint. Let that sink in.

When a user says “reply to Alex’s email,” they’re expressing clear intent. The LLM understands it perfectly. But the API underneath? It has no idea what a “reply” even is.

So your agent has to:
- Figure out which Alex
- Search through messages (40 parameters deep)
- Unpack MIME by hand
- Maintain threading
- Repack everything
- Finally send

This isn’t a prompt-engineering problem.
It’s not a model problem.
It’s an architecture problem.

You’re asking your LLM to translate human intent into low-level API primitives.

Every translation step adds:
- More tokens ($$$)
- More latency (seconds add up)
- More hallucination risk

Teams keep trying to fix this by dumping context into prompts —
“Here’s how MIME works. Here’s the threading format. Here’s…”

Wrong approach. Your LLM is doing plumbing work when it should be doing reasoning work.

The right approach: Build tools that match agent intentions.
One “reply to email” tool. Handles all the complexity internally.

The agent makes one decision, not six.

That’s why 70% of agent projects fail — they’re building API wrappers when they should be building intention engines.

At Arcade.dev, we built that layer — tools that map human intent directly to secure, real-world action.

Today, Arcade.dev was named to the 2026 Enterprise Tech 30 alongside Anthropic, OpenAI, Stripe, and Cursor.

We started Arcade because we kept running into the same wall. Everyone wanted agents that could actually take actions, but nobody had figured out how to make that safe at scale. The biggest blocker was authorization at runtime, across multiple users, with full audit trails. That's where agent demos were dying before reaching production. So we built the solution.

When MCP took off, we were ready. We shipped the first MCP runtime, built 8,000+ production-grade tools, and started working with some of the world's largest enterprises to put entire fleets of agents into production.

The demo era asked 'can the agent do it?' The production era is asking something harder: what did the agent do, on behalf of which user, in which system? That's the exact problem Arcade was built for from day one, and it's where the hardest problems in enterprise AI are now concentrated.

More on our blog via the link in comments. Thank you Wing Venture Capital and Eric Newcomer for the recognition, and congrats to all the other listees.