How we work
Small steps, each with an exit
Nobody should sign a year-long contract with a company they have not worked with. So engagements start with a free scan and earn each next step. At every step you leave with something you own.
The ladder
Four steps. Each one is a complete piece of work on its own, and you can stop after any of them.
Step 0 · About a week
Free readiness scan
A short conversation and a read-only look at usage, with a two-page findings note. No commitment.
Exit: You keep the findings. Nothing else is owed.
Step 1 · 2–3 weeks
Fixed-fee audit
Cost recovery, or readiness for semantic layer and agents. A prioritized plan and the specific fixes, written down.
Exit: Take the plan to your own team or another vendor. It is yours.
Step 2 · 6–8 weeks
Pilot
One governed ask-your-data agent in production, or one semantic-layer migration, with a stop-point at week two.
Exit: A working system, the code and the docs. Stop here if that is all you need.
Step 3 · Scoped quarterly
Dedicated pod
Senior engineers under one accountable lead, working against a quarterly scope you set with us.
Exit: Quarter by quarter. No long-term lock-in.
What the client provides
- A sponsor who can make decisions and a technical contact who knows the data
- An NDA, then read-only access to usage history for the scan or audit
- For a pilot: a working environment in your cloud account, a repository, and SSO for the users who will try it
- Thirty to sixty minutes a week for a working session, and someone who answers questions within a day
Ownership and IP
The client owns the deliverables: code, infrastructure configuration, semantic models, evaluation suites, documentation and runbooks. They are produced in your repositories and your cloud accounts, under your access control, from the first week.
We keep nothing of yours. Reusable tooling we bring to the work stays ours and is licensed to you for the project; the contract names what that is, if anything, before work begins.
Nothing about your engagement appears on this site or anywhere else without written permission.
How we communicate
Weekly working session
One hour, on a call, with the engineers doing the work. Decisions are written down the same day.
Written status every week
What shipped, what is next, what is blocked, and what it costs so far against the scope. Short enough to read.
A shared channel
Slack or Teams, in your workspace. No ticket system of ours; we work in yours.
Everything in your repositories
Code, docs and runbooks are committed where you can see them as they are produced, not delivered at the end.
Security and data access
An NDA before any data access, least-privilege roles inside your environment, no production credentials outside it, and an audit trail. The full practice is on the security page; details are available under NDA.
Tell us what you're trying to build
A 30-minute technical conversation about your stack and what you are trying to do. If a free readiness scan makes sense, we will say so; if not, we will say that too.