For Analytics engineer · 9 Grok Bots

A modeling back office that keeps your metrics tested, documented, and trusted

9 Grok Bots for an analytics engineer: log every request, trace lineage before a change, draft dbt models and their tests, propose the PR and run window, track metric definitions, and report build health — all as drafts you approve.

Hire the team See the bots
● Drafts only — nothing sends without your approval · Uses only your own data
After checkout
Your setup link arrives by email
We set up your fleet
After checkout, Workplace AI provisions your fleet on our Cursor Teams workspace and follows up soon. Watch for your Cursor invite and Grok Bot download link — then accept, install, and go.
9 bots·3 domain specialists·Success metric: Model test coverage and metric-definition agreement·Category: Tech & digital
The problem it targets

Standing between raw source tables and the dashboards the business trusts — triaging ad-hoc metric requests, tracing which columns feed which dashboard before a change, writing dbt models and their YAML and tests from scratch, reconciling two teams that define the same metric differently, and chasing a failed build or a stale table after someone downstream notices — so requests pile up, models ship undocumented, metrics quietly drift apart, and trust in the numbers erodes.

What you get

From day one

1

Every metric and dashboard request logged and scoped, and a lineage brief that traces which source columns feed a model and which dashboards read it before you touch anything.

2

A dbt model and its YAML documentation drafted on a branch from the approved definition, with the data-quality tests and data-contract checks drafted and reviewed against it.

3

A proposed PR and warehouse run sequence with the stakeholder change note ready, plus a weekly analytics-health digest of what built, what failed, and where test coverage dropped.

Meet the team

9 bots, each with one job and clear approval points

Read-only bots watch and prepare; drafting bots write but never send. You approve everything that leaves.

1

Chief of Staff

coach
Drafts for your review — you approve before anything leaves
Your morning brief, meeting prep, fleet roundup, and after-meeting coaching.
Approves: none — nothing leaves without you
2

Metric Request Intake

intake
read-only
Watches & prepares — never sends
Logging and scoping every metric, dashboard, and model-change request
Approves: none (nothing leaves; requests are internal)
3

Source & Lineage Mapper

researcher
read-only
Watches & prepares — never sends
Upstream-and-downstream lineage and impact briefs before a change
Approves: none (nothing leaves; briefs are internal)
4

dbt Model Drafter

drafter
specialist
Drafts for your review — you approve before anything leaves
dbt SQL models and YAML docs on a branch from the approved definition
Approves: every model before any run or merge
5

Data Test & Contract Reviewer

specialist
specialist
Drafts for your review — you approve before anything leaves
Drafted data-quality tests and data-contract review of the model
Approves: every test set before it is committed
6

Transformation Run Coordinator

coordinator
Drafts for your review — you approve before anything leaves
Proposed PR and run sequence, drafted PR and stakeholder change note
Approves: every merge, run, and send
7

Metric Definition Tracker

tracker
Drafts for your review — you approve before anything leaves
Definition-drift tracking and one proposed canonical entry per conflict
Approves: every definition before it is made canonical
8

Analytics Health Reporter

reporter
read-only
Watches & prepares — never sends
Weekly build, freshness, and test-coverage digest, every figure traceable
Approves: none (nothing leaves; the engineer acts)
9

Social & Referrals

growth
Drafts for your review — you approve before anything leaves
First-party, disclosed posts and data-changelog notes to the engineer's own opted-in network
Approves: every post and message before it is sent
The handoff — one shared chat
Intake→Mapper→Drafter→Reviewer→Coordinator→Tracker→Reporter
What the fleet does in week one

All read-and-prepare — you check its work before anything is trusted

What it does not do

The guardrails are the product

  • ×It drafts; it does not ship. Every model, test, PR, and change note waits for your review, and no merge or warehouse run happens on its own.
  • ×It never drops a table, deletes data, or alters a live schema, and it never commits a metric definition — which definition is canonical is your call and stays in your dictionary.
  • ×It works only from the warehouse metadata, the dbt project, and the catalogs you point it to; it reaches only your own opted-in network and never builds an audience for you.
Model
test coverage and metric-definition agreement
How you'll know it's working

One number, measured over time

Share of shipped models that carry documentation and a passing test, and the share of business-critical metrics that resolve to a single canonical definition across dashboards

Before day one

What you fill in — the bots never guess these

request-log
the header contract for the request log every bot reads.
model-spec
the shape of a model spec: grain, sources, columns, and the canonical definition cited.
metric-dictionary
your canonical metric dictionary; definitions come only from here.
Pricing

Cancel anytime.

Workplace AI provisions and runs your CrokPot fleet on our Cursor Teams workspace. We invite you on your own email — you accept, install Grok Bot, and we handle the rest.
$200/mo
  • Your whole fleet provisioned and installed for you
  • Cursor Teams seat included — paid by Workplace AI, never billed by Cursor
  • Onboarding + ongoing training
Hire the team
Your Cursor Teams seat is included and paid by Workplace AI. Drafts only, using your own data. No earnings, time-saved, or outcome guarantees are made.
How access works

You buy a CrokPot fleet from Workplace AI — not a Cursor plan

CrokPot runs on Workplace AI, Inc.’s (WAI) Cursor Teams workspace. WAI keeps the unpaid admin seat and pays Cursor for your seat. You join as the invited user on your real email and work through the installed Grok Bot fleet.

Your card is charged by WAI via Stripe for the CrokPot fleet ($200/mo, auto-renewing monthly) only — never by Cursor. If you cancel your fleet subscription, the invite/seat ends with it and is not portable to your own Cursor account.

FAQ

What you get, who owns the seat, and what happens after you pay

From the team behind Ancestry — CrokPot is built by Paul Allen, a co-founder of Ancestry.com.

Drafts only — you approve everythingYour own data, never shared$200/mo · cancel anytimeProvisioned & supported by Workplace AI

What do I actually get?

A pre-built fleet of Grok Bots for your trade, provisioned and installed for you on Workplace AI’s Cursor Teams workspace, plus onboarding and ongoing training. Every bot drafts; you approve.

Who owns the seat?

Workplace AI, Inc. (WAI) owns the Cursor Teams account and pays Cursor for your seat. You’re invited as a paid user on your own email. The seat isn’t portable to a personal Cursor account.

Do the bots act on their own?

No. The fleet is drafts-only, working from your own data. Nothing sends, files, or is trusted until you review and approve it — that’s the whole design.

Can I cancel?

Yes, anytime. It’s an auto-renewing monthly subscription at $200/mo. If you cancel, your invite/seat ends with the subscription.

What happens after I pay?

We follow up soon: our team provisions your fleet and invites you on the email you used at checkout. Watch for your Cursor Teams invite and Grok Bot download link, then accept, install, and go.

Training

New to Grok Bots? Get your team trained.

Live sessions and replays to get you and your coworkers productive with your fleet fast.

Explore Grok Bot training