AI made a mess.
We’re here to fix it.

Connecting the dots · enabling new forms of access

For teams usually skeptical of tech, but want to embrace AI.

Our forward-deployed engineers embed with yours and move in measured, low-risk steps towards frontier technology.

CLEAN UP

Mend what you already have

We audit what you already run, from code and prompts to pipelines and vendor licenses, then restore the lineage, testing, and monitoring that make it trustworthy and enterprise-grade.

INNOVATE

Ship new products safely

We design and build AI products inside the controls you have, on whatever cloud and models you already use. High governance and regulatory compliance go into the plan on day one.

TRANSFORM

Bring your people along

New tools change little if the organization around them stays the same. We train your people and help update policies and processes until the new systems are part of how the work gets done.

OPTIMIZE

Delegate vibe-code management

AI coding tools let your people spin up dozens of personal apps, each with their own upkeep. We make them enterprise-grade: automated tests and deploy, cost limits, role-based access controls, and more.

The impact we enable.

We create platforms to make your organizations make decisions and execute more quickly. Read our case studies and detailed use cases to learn how.

VALUE

Grow EV

New products, new lines of business, and more ways to bring in revenue, all with longevity and high governance in mind.

EFFICIENCY

Do more with less

Agents and automation that take work off your team’s plate, inside the systems and budgets you already have.

SPEED

Accelerate your ROI

Put the investments you have already made to work, and see a positive return sooner.

We build with

We work in the stack you already have and ensure integrations hum. Want to use open-source frameworks or something not listed here? Let us know!

VENTURE STUDIO

We also build, operate, and advise new ventures.

Alongside client work, we help start and grow new companies in healthcare and life sciences.

BUILDProduct, platform, and data foundations, from zero to first customers.

OPERATEFounding and fractional leadership through launch, growth, and exit.

ADVISEStrategy, go-to-market, and technical diligence for founders and boards.

LAST UPDATED 29 SEP 2026

What we are paying attention to right now.

What we are testing, and where we think it will matter in regulated industries.

How can we help?

Let’s chat

HEALTHCARE & PHARMA

Our healthcare and life sciences data work, in more detail.

Three previous projects. Client names and exact figures stay private. Where we show numbers, they come from tests on synthetic data or are marked approximate.

WHAT IT DOES

HEALTHCARE DATA · CASE STUDY

Teaching a data agent the rules of the data.

A life-sciences team wanted its researchers to ask plain-English questions of real-world oncology data and get patient counts back. Most of the time the agent got them right. When it was wrong, nothing about the answer said so.

DOMAINReal-world data · HEOR

OUR ROLEDesign and build

DATALicensed oncology data products, inside the client’s own warehouse

STATUSAgent built; safeguards tested on synthetic data

2 → 16

Questions right out of 16 once the agent was given checked rules instead of bare column names

Wrong answers in the first round that came back with no error at all

yes ≠ True

One mismatch between a vendor manual and the data made whole queries return zero

600

Synthetic patients and 16 questions, with every right answer known in advance

TRY IT · BREAK THE AGENT, THEN FIX IT

Pick a question, then change what the agent is given. These are the real results from our test on synthetic data.

AGENT ANSWERED{{av.said}}

CORRECT ANSWER{{av.truth}}

VERDICT{{av.verdict}}

WHAT WE DID

Read the sources

Each licensed data product comes with a data dictionary and a usage manual. We read both and turned them into short, single-statement rules, each pointing back to its page.

Test every rule against the data

Before a person approves a rule, it is run against the real tables. Do the columns exist? Do the values match what is stored? Is it really one row per patient? This step is where the disagreement between the manual and the dictionary over values like yes and True turned up.

Give the agent only what is approved

For each question the agent gets the approved rules and the real column values for the tables it needs, and nothing else. A query that returns zero rows goes back as a failure, not as an answer.

Writing the SQL was never the problem. The agent did not know how this particular dataset records things: which values mean yes, which dates count, which rows to leave out. Once it did, 16 of 16 test questions came back right, with no retries.

Building something like this? Close case study

AI EVALUATION · CASE STUDY

Can a small decision model check the agent’s work?

Jev, a new model from TypeSafe AI, does not write text. It picks from a set of options we give it, such as yes or no, and reports how confident it is. We tested whether it could review each plan our healthcare-data agent writes before any number reaches a user.

MODELJev, by TypeSafe AI

OUR ROLEEvaluation and design

TEST DATASynthetic only

STATUSExperiment. Nothing is in production.

14 / 14

Planted mistakes caught in oncology questions, with 1 false alarm in 16 correct plans

≈ 0.3 s

To check one plan, against about 3 seconds for a general-purpose AI

≈ 50¢

For ten thousand checks

2 → 11

Questions right out of 16 when Jev checked plans against the rules, up from 2 with a dictionary alone

PLAY · CATCH THE SLIP

These are six plans the agent wrote during our tests. Some are correct; others answer a slightly different question from the one asked. Read each plan, decide, then see what Jev decided.

THE AGENT’S PLAN

How sure Jev was the plan fits the question{{jr.conf}}

{{jr.said}}what the report would have said

{{jr.right}}the right answer

FINAL SCORE

You

6/6

Jev, in {{jJevTime}} in total

WHAT WE LEARNED

It enforces the rules it is given

Jev checks a plan against a rulebook. If the rulebook is wrong, so is the check. With a verified rulebook the agent scored 16 of 16 without Jev, which is why we would fix the rulebook first and add Jev after.

Its job is narrow

Counting, date math and report writing stay with the agent and the database. Jev’s only job is to say whether the plan fits the question.

The free option was not ready

We also tested an open-source look-alike that runs on our own machines. It was fast, but out of the box it was worse than guessing on three of seven tasks, so we parked it.

Worth adding as a fast, inexpensive check on the agent, once the rulebook is right.

Building something like this? Close case study

KNOWLEDGE GRAPH · CASE STUDY

One graph across the warehouse and the papers.

The client’s structured data sat in the warehouse, while most of what its scientists knew about a disease, drug or biomarker sat in internal publications and reports, with no link between them. We built a knowledge graph across both, so a question about any one of those things leads to everything connected to it.

DOMAINKnowledge graph · discovery

OUR ROLEDesign and build

SOURCESData warehouse tables and internal publications

STATUSIn production

~30

Warehouse tables mapped into the graph

~1,500

Internal publications and reports linked in

~10K

Entities such as diseases, drugs, biomarkers and trials

Standard vocabularies used to line up names: ICD-10, SNOMED CT, LOINC, RxNorm

FIGURES ARE APPROXIMATE AND ROUNDED. EXACT COUNTS AND NAMES ARE WITHHELD TO PROTECT THE CLIENT.

TRY IT · FOLLOW THE LINKS

A simplified picture of how it connects. Click any node, or start from a question. Copper nodes are entities, gold are warehouse tables, brown are publications.

DIRECTLY LINKED TO {{gsel.links}}

HOW IT WAS BUILT

Start from the questions

We began with the questions people bring to the data, then defined a small set of entity types to answer them: diseases, biomarkers, therapies, trials.

Link the sources

Warehouse columns are mapped to those entities, and the same entities are pulled out of the publications. Names are matched through standard vocabularies, so different spellings of one thing land on one node.

Record where every link came from

Each link stores its source, whether a table and column or a page in a document, so any answer can be traced and checked.

Answering that kind of question used to take three people and a dozen files. Now it takes one lookup, with the sources attached.

Building something like this? Close case study

AI made a mess. We’re here to fix it.

AI made a mess.We’re here to fix it.

For teams usually skeptical of tech, but want to embrace AI.

Mend what you already have

Ship new products safely

Bring your people along

Delegate vibe-code management

The impact we enable.

Grow EV

Do more with less

Accelerate your ROI

We build with Databricks.Snowflake.dbt.Claude.Codex.Cursor.AWS.Google Cloud.Azure.Databricks.

We also build, operate, and advise new ventures.

What we are paying attention to right now.

{{n.title}}

How can we help?

AI made a mess.
We’re here to fix it.

We build with