Internal tools with AI for companies

I add AI to the dashboards, CRMs, spreadsheets and back-office applications a company already runs: assistants that answer from company data, questions in plain language and automations where a person approves the steps that matter. It is for operations and data teams in Mexico and the United States that want less manual work without replacing the systems they trust.

Internal tools with AI means adding a language model to the systems a company already runs (the dashboard, the CRM, the spreadsheet, the back-office application) so that people can ask instead of search and approve instead of retype. A company needs it when its data lives in tools that work, but getting an answer out of them takes a person who knows where to click, and when its repeated tasks are held together by scripts that nobody wants to touch.

What I build

  • Assistants over company data. A chat inside the tool, with the context of the screen, suggested actions and alerts, that answers from the records of the company.
  • Questions in plain language. A connection between an AI assistant and a database or a base of tables, so that a person asks for the overdue tasks or the last order of a customer and gets the answer.
  • Analysis that explains itself. Answers that arrive with the queries, the checks and the figures behind them.
  • Automations with approval. Flows where the model proposes and a person confirms the steps that change a record, with a trial mode before production.
  • One layer in place of scattered scripts. A single service for synchronization, with change detection, retries, logs and a history of the data.
  • A safe door to the model. One service that holds the keys and that every tool calls, so that no key sits in a script or a browser.

Symptoms in the tools you already have

  • People leave their work to look something up in another tab, and lose the thread.
  • The same report is rebuilt by hand from exports, and reconciling it takes hours.
  • A sync fails at night and the company finds out from a customer.
  • A key for a model is pasted into a spreadsheet script or a front end.
  • A dashboard shows a number and nobody can say which records produced it.

Each symptom points to a different piece of work. The first asks for an assistant. The second and the last are data work. The third is integration. The fourth is security, and it comes before all the others.

How the work runs

  1. Inventory. I list the tools, who uses each one, what data it holds and how it can be reached: an interface, an export or a database.
  2. Put the data in order. If records are scattered, or lost between syncs, they go first into one database with a model that keeps history. An assistant over inconsistent data repeats the inconsistency with confidence.
  3. Define the terms once. What margin, overdue or active mean in this company, written where both people and the model read it.
  4. Read before write. The first version only answers. Actions that change records come next, each one behind an approval, a flag that the business can turn off, or a trial mode.
  5. Watch and correct. Corrections made by people go back into the rules, and failures show in one place.

What you receive

The code in your repositories, the service that holds the keys in your cloud account, the definitions of your business terms as a document, and the controls: flags, trial mode and logs.

What this does not include

I do not replace a system that works to make room for AI, and I do not build a chat window with no data behind it. I do not let a model write to your records without a step where a person can stop it. If the data is not in order, that is the first project, and I say so before starting.

Where the evidence is

For Talisman, an accounting platform from Texas, I built a project management module inside the product as an AI engineering contractor. That included the full experience of its assistant: streaming chat, suggested actions and alerts, staged for the connection to a model. For a company in the warranty management industry, I moved scattered records into one relational database and built the dashboard on top. I turned an inherited integration between a property management system and a field service system from a bridge that kept no history into a data warehouse with history, duplicate detection and flags that the business controls. And Airtable MCP, which is open source, lets a person talk to an Airtable base in everyday language through an AI assistant.

Work and evidence

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:

Enterprise analytics platform (opens in a new tab)

My contribution: Worked on MongoDB migration, data modeling and the analytics application described in the case study.

What this supports: Experience integrating corporate data and building its application layer.

What it does not establish: Reported record volumes and page timings are case-study claims, not an agent load test.

Source reviewed:

Common questions

Can we add AI to our existing systems without replacing them?

Yes, and it is usually the better path. The AI reaches each system through its interface, with its own account and limits, and the screens people know stay as they are. What changes is that a question or a repeated task no longer needs several tabs or a person in the middle.

Can employees ask questions about company data in plain language?

Yes, when the data is in one place and the business terms are defined once. A good answer is not a single number: the system plans what to look up, runs small queries, checks the result and explains it with the figures it used. Without that process the answers sound confident and are often wrong.

Is it safe to connect AI to our CRM or our spreadsheets?

It is safe when no key sits in a script or a browser and every tool calls one service that holds it. That service handles authentication and errors in one place, so a change of provider or of rule is made once. Reading comes first, and changes to records go through a step where a person approves.

We have many scripts that sync data between systems. Can AI help?

The first help is not AI. It is one system in place of many scripts, with one way to detect changes, retry and log. On top of that, a model can propose how the fields of two systems correspond: proposals with high confidence are applied and the rest wait for a person.

Can you work remotely with our internal team?

Yes. I work from Monterrey with teams in Mexico and the United States, on contract or in a senior role, in English and in Spanish. Internal tools are built next to the people who use them, so I work in your repositories and talk to the team that opens the tool every morning.

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