Company data ready for AI agents

Give an AI workflow a dependable route to the company records it
needs. We map the relevant sources, clarify what each field means,
connect the data and set access rules with you. The first
deliverable is one agreed question answered from traceable records,
with checks for data quality and permissions.

Gathered: one place an agent can reach

We build the pipelines that bring your systems together: ETL jobs
that run on a schedule, load only what changed and report what they
skipped, into a database whose schema names your business in your
words — customers, orders, vessels, contracts, cases. Old PDFs,
scans and mail archives are turned into searchable text with their
source kept beside them, so they can be found rather than only
stored. The agent reaches all of it through one described door: an
MCP server or an API, never a copy of the database on somebody's
laptop.

Cleaned: one customer, not five

The same customer can be written five ways in five systems. When an
agent reads conflicting versions of one fact, it needs a rule for
which source to trust. We decide with you which system is the source
of truth for each fact, merge duplicates by rules you can read, and
keep the merge running, so a new duplicate is caught on the next
load rather than at the next audit. Types and constraints in the
database refuse a bad row instead of storing it, every column says
what it means, and every migration is versioned and checked, so the
schema an agent reads is the schema that is deployed.

Permissioned: each agent sees what its user may

An agent that can read everything is a leak with a friendly voice.
The rules belong in the data, not in the prompt: roles in the
database (RBAC), read-only by default, row-level rules wherever one
customer must never see another's, and personal data kept out of
reach unless the task needs it — which is also what GDPR asks. The
agent acts with its user's privileges, never an administrator's, and
every read is logged with the person it was made for. How we lock
the agents themselves is its own page.

Every answer traced to its source

An answer drawn from company data is worth what its source is worth,
so the source travels with it. Every row keeps where it came from
and when: the system, the load, the file and the page. An agent can
cite the record behind a figure, and a person can open it. A load
that skipped rows says how many and why rather than reporting
success, and a figure that turns out wrong leads to the load that
brought it in, not to a week of guessing. It is the rule our own
reporting is built on: a number is never printed that the run did
not measure.

The work behind it

Every claim on this page is a method we have run, and each one has
its record. We made a geographical data pipeline 50 times faster by
fixing its SQL and its data model, and designed and ran six ETL and
ELT pipelines across BigQuery, MS SQL and PostgreSQL. We modelled a
whole trade in 348 tables across 34 schemas and kept that schema
honest across 1,022 migrations behind a drift gate. We generated 495
pages from a read-only SQLite export, and replaced 963
structured-data blocks with one linked graph, which is what an agent
reads first on this site.

How an engagement runs

It starts with a map, made read-only: which systems hold what, who
owns each, and which questions an agent should be able to answer.
Then we take the one question that matters most and build its path
end to end — the sources, the cleaning, the permissions and the door
— with checks that stop a load when the data drifts. Then the next
question. Everything lives in your infrastructure and your
repository, through your review, and the agents that read it can be
built for your trade or be the ones you already use. It is bought
like the rest of our work, on the terms in what it costs.

If the answers your people need are in more places than anyone can
name, tell us where your data lives (read by the engineer).

hThis page on the web	URL:https://data.engineer.company/ai-data/	data.engineer.company	70
