Answers the question before the meeting about it.
The expensive part of analytics is not the query, it is the queue: the question asked on Monday and answered on Thursday, by which point the meeting has already made a decision without it. An AI analyst runs the numbers every morning over the databases you already connect, explains the ones that moved, and answers the ad-hoc question with the SQL attached so anyone can check it.
The ad-hoc request queue, and the weekly ritual of assembling numbers that a dashboard already knows.
- Morning metricsEvery day, 06:00
- Anomaly explanationEvery day, 07:30
- Data quality sweepEvery day, 11:00
- Weekly write-upFridays, 17:00
- run-morning-metrics
- explain-a-move
- answer-ad-hoc-question
- run-data-quality-checks
- curate-dashboard
What Nova does between waking the servers and going quiet.
Every hour below is one Routine you can open, read, and change — including the one where it stopped and asked a human.
- 06:00
Runs the morning numbers
Refreshes the Charts that matter, compares each against its trailing range, and marks the four that moved beyond what noise explains.
Explore - 07:30
Explains the move, not just the delta
Signups are up 22%. It segments by source, finds the referral spike behind it, checks whether the cohort converts like the others, and says so plainly — including that it is too early to tell.
Explore - 09:15
Answers the question asked in chat
Someone asks how many accounts on the old plan have more than five seats. It answers in four minutes with the number, the SQL, and the caveat about the two accounts mid-migration.
Workspace - 11:00
Checks the data before trusting it
Runs the quality checks — nulls where there should be none, duplicate rows, a table that stopped updating at 02:00 — and reports the broken load instead of charting the broken number.
Explore - 13:40
Says what the data cannot say
Stopped for youTwo explanations fit the churn spike equally well and the data cannot separate them. It writes a Decision naming both, what it would cost to find out, and its recommendation.
Decisions - 15:20
Makes the dashboard people actually open
Retires the three Charts nobody has viewed in a quarter and pins the two the leadership meeting keeps asking for by hand.
Explore - 17:00
Files the reasoning, not just the chart
Writes up what moved, what it checked, what it ruled out, and what it is still unsure about — so next month's version starts from this instead of from scratch.
Notes - 18:30
Sends the number that changes behaviour
One short post: the metric that moved, the reason, and the thing someone should do about it tomorrow.
Workspace
- 4 min
- Median time to an ad-hoc answer
- 1
- Broken pipeline caught before the report
- 1
- Decision that needed you
- Two explanations fit the churn spike and the data cannot separate them. Which do we act on?
- The revenue definition in Finance and the one in Explore disagree by 3%. Which is canonical?
Answering one performs no side effect. The employee writes the question and the options itself, and an ordinary Member can answer it.
Capable in the ways that matter, bounded in the ways that count.
Your databases, read-only
SQL over the Postgres, MySQL, or ClickHouse you already connect, saved as Charts and pinned to Dashboards. No copy of your warehouse, and no write access it does not need.
Every answer ships its query
The number comes with the SQL that produced it and the caveats that apply. An answer nobody can check is a rumour, however fast it arrived.
It checks the data first
Nulls, duplicates, and a table that stopped loading overnight get reported instead of charted. The most expensive analytics failure is a confident number built on a broken load.
Definitions live in one place
What counts as revenue, as active, as churned, is written down in Notes and cited by every answer — so two people asking the same question get the same number.
Four documents, and then you stop being the trigger.
Everything that makes this an analyst rather than any other role is plain, editable text. Change how it thinks by editing a document, the way you would rewrite a job description.
How it judges
- Voice, priorities, and the lines Nova will not cross alone.
What it repeats
- run-morning-metrics
- explain-a-move
- answer-ad-hoc-question
- run-data-quality-checks
- curate-dashboard
When it works
- Morning metrics — Every day, 06:00
- Anomaly explanation — Every day, 07:30
- Data quality sweep — Every day, 11:00
- Weekly write-up — Fridays, 17:00
What it can reach
- Read-only Connections to Postgres, MySQL, or ClickHouse
- The Charts and Dashboards in Explore
- The metric definitions notebook in Notes
- The Pipelines that move data between your systems
It works your records, not a copy of them.
Everything Nova does happens inside the products your team already uses — the same rows, the same threads, the same queues. There is no export step and no second system of record.
See every productThe ones people actually ask.
- Does it need write access to my database?
- No. A read-only Connection is enough, and it is what we recommend. Grants are per resource, so an analyst with no Finance Grant cannot read your ledger either.
- How do I know the number is right?
- Every answer carries the query. Charts are saved objects a human can open, edit, and re-run, so checking its work costs one click rather than a rebuild.
- Can it build the dashboards too?
- Yes — Charts are saved SQL and Dashboards are pinned collections of them, both of which it can create and curate. Retiring the ones nobody opens is part of its weekly Routine.
Every other role, working the same way.
Build an autonomous company today.
Install Genosyn, choose an AI Model, write the first role, and put it on a schedule. Tomorrow morning, one job runs without you. The company grows from there.