AI agent development for companies

I design, build and operate AI agents for companies on contract: agents that read your data, call your tools and hand work to people, with tests that decide what ships. I work remotely from Monterrey, Mexico, with teams in Mexico and the United States.

An AI agent is a program that uses a language model to decide its next step: which tool to call, which record to read, when to answer and when to pass the case to a person. A company needs one when a process has too many variations for fixed rules and too much volume for people alone, and when a wrong step has a cost that someone can name.

What I build

  • Agents for one process at a time. Admissions questions, quotations, support cases, internal requests. One agent, one process, a clear list of what it may do.
  • Multi-agent systems. Several agents with separate tasks behind one conversation, with routing, shared state and handoffs between them.
  • The tools the agent uses. Connections to your databases, CRM and internal systems, each with its own permissions, built on the Model Context Protocol where it fits.
  • The evaluation that decides a release. Cases written as code, deterministic checks, a judge model calibrated against people, and a gate that blocks a release when the agent gets worse.
  • Operation. Deployment, logs of every tool call, and a way to see what the agent did and why.

Signs that a process is ready for an agent

  • The work arrives in language (messages, documents, requests) and ends in an action in a system.
  • People already follow a procedure for it, even an unwritten one, and can tell a good outcome from a bad one.
  • The data and the systems it needs can be reached through an interface, with an account that can be limited.
  • A wrong answer can be caught: by a rule, by a person or by a later step.

When one of these is missing, that piece is the first work and the agent comes after it. The order matters more than the model: a company that describes its process first gets an agent it can check, and one that starts from the model gets a demonstration.

How the work runs

  1. The process first. I read how the work is done today, where it breaks and what a correct outcome is. An agent placed on a process nobody has described repeats its confusion faster.
  2. Cases before code. We write the situations the agent must handle and the outcomes that are not acceptable. These cases become the tests.
  3. A first agent on real data. A narrow version runs against the cases, with the real tools and a copy of the real state.
  4. The gate. Before any release the suite runs. A failure in a required case stops the release, whoever asks for it.
  5. Release and watch. The agent goes to a small share of the work first. What it does is recorded, and new failures become new cases.

What you receive

The agent and its tools in your own repositories and your own cloud account, the cases and the evaluation harness, the deployment, and written notes on how to operate and change it. Nothing depends on an account of mine.

What this does not include

I do not promise that an agent replaces a team, and I do not put an agent in front of customers without tests that say what it may not do. If the process is not ready for an agent, I say so, and the first piece of work is the process.

Where the evidence is

The agents of a higher-education group that serves 700,000+ students run in production on Vertex AI, the Agent Development Kit and Cloud Run. My part was the evaluation harness, the calibrated judge, the isolated state for every case and the gates of each environment. The case study and the guides linked below describe it, with what it shows and what it does not.

Work and evidence

MetaMCP as a Cloud Run MCP gateway (opens in a new tab)

My contribution: Built and documented the cloud-facing gateway path, registration artifacts, smoke checks and evidence export.

What this supports: Public implementation account covering transport, caller identity, secrets and tool-call evidence.

What it does not establish: The case study is not an independent security audit or a published concurrency benchmark.

Source reviewed:

Airtable MCP (opens in a new tab)

My contribution: Built an open-source MCP integration for querying and editing Airtable bases.

What this supports: A concrete database-to-agent integration with a linked public repository.

What it does not establish: An integration example, not evidence that arbitrary corporate databases or tenant policies are secured by default.

Source reviewed:

Evaluation gates for a multi-agent education system (opens in a new tab)

My contribution: Built the evaluation harness, calibrated LLM judging, isolated case state and environment-specific evaluation gates.

What this supports: The public account describes golden cases as code, a calibrated LLM judge and the evaluation harness around them, on a Google Cloud agent stack.

What it does not establish: The figure of 700,000+ students describes the population served by the system. It does not measure simultaneous users, requests per second or personal ownership of the whole platform. Client code and data remain private.

Source reviewed:

Common questions

How long does it take to build an AI agent for a company?

It depends on how clear the process is. The model is the short part. Describing the process, writing the cases that say what a correct answer is and connecting the tools take most of the time. I give an estimate after reading the process and the systems involved.

Which platforms and tools do you build agents with?

Mostly Google Cloud (Vertex AI, the Agent Development Kit and Cloud Run), Python and FastAPI, and the Model Context Protocol for tools and data. The choice of model follows the task and the constraints of the company, not the other way round.

Can an agent work with our internal data and systems?

Yes. The agent reaches your systems through tools with their own permissions, so it reads and writes only what its task needs, and every call leaves a record. A database is connected through a server that separates queries from changes.

Do you work with companies in the United States?

Yes. I work remotely from Monterrey, on Central Time, in English and in Spanish, on contract engagements and on full-time senior roles.

Are you an AI consultant or an engineer?

An engineer who takes contract work. I can advise on what to build and what to leave alone, and I also build it, test it and operate it.

Related questions

Open to senior AI engineering roles and contract engagements, remote in the US, Mexico and Latin America.