For ML / AI engineer · 9 Grok Bots

A lab notebook that keeps your runs reproducible and your impact visible

9 Grok Bots for an individual ML / AI engineer: log every run, scout the prior art, rank your errors, draft the write-up, prep the review, track the evals, and keep your portfolio — 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: Run reproducibility and review turnaround·Category: Tech & digital
The problem it targets

Keeping the work reproducible and legible around the actual model building — logging every training and eval run with its config and data version, digging through papers and repos before trying a technique, doing error analysis by hand across eval slices, writing model cards and review write-ups from scratch, and rebuilding the story of what improved for standups and reviews — so runs go untracked, results are not reproducible, reviews stall on missing context, and the engineer's own impact is invisible when it matters.

What you get

From day one

1

Every training and eval run logged with its config, data version, and metrics, plus a sourced technique brief of papers and repos before you spend the compute.

2

A ranked error analysis grounded in real failing examples, and a model card and write-up drafted from the logged record with every number traced to its run.

3

A review packet drafted for a ready change and an eval trend tracked against your baselines, plus a weekly portfolio of what improved with the numbers behind it.

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

Experiment Logger

intake
read-only
Watches & prepares — never sends
Capturing every run — config, data version, seed, metrics — into the run log
Approves: none (nothing leaves; the log is internal)
3

Paper & Technique Scout

researcher
read-only
Watches & prepares — never sends
Sourced technique briefs of papers, repos, and prior runs before a decision
Approves: none (nothing leaves; briefs are internal)
4

Error-Analysis Analyst

researcher
read-only
Watches & prepares — never sends
Ranked error analysis across eval slices, grounded in real failing examples
Approves: none (nothing leaves; the analysis is internal)
5

Model-Card & Write-up Drafter

drafter
specialist
Drafts for your review — you approve before anything leaves
Model cards, design docs, and experiment write-ups from the logged record
Approves: every write-up before it is shared
6

Review-Prep Coordinator

coordinator
Drafts for your review — you approve before anything leaves
Review packets — PR description, evidence, and drafted review-request messages
Approves: every message; every posted request or proposed merge
7

Eval-Run Tracker

tracker
Drafts for your review — you approve before anything leaves
Eval and benchmark trends against baselines, with each number linked to its run
Approves: the engineer confirms which numbers are the baseline
8

Impact & Portfolio Reporter

reporter
read-only
Watches & prepares — never sends
Weekly progress summary and the engineer's impact portfolio, every claim sourced
Approves: none (nothing leaves; the engineer shares it)
9

Social & Referrals

growth
Drafts for your review — you approve before anything leaves
Draft posts and outreach to your own audience, credited and approved by you.
Approves: sends
The handoff — one shared chat
Logger→Scout→Analyst→Drafter→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 send. Every write-up, review request, and portfolio post waits for your approval.
  • ×It never merges, deploys, or changes a production model or pipeline — that stays your call.
  • ×It never invents, rounds, or extrapolates a metric; every number comes from a logged run or a named result file.
  • ×It reaches only your own opted-in network. It does not add anyone you have not chosen.
Run
reproducibility and review turnaround
How you'll know it's working

One number, measured over time

Share of training and eval runs captured with a complete config, data version, and metric set, and how quickly a change moves from ready to reviewed with a complete write-up

Before day one

What you fill in — the bots never guess these

run-log
the header contract for the run log every bot reads and writes.
baselines
your named baselines per metric and slice. Trends are measured only against these.
model-card
your own layout for a model card and write-up so drafts match what your team expects.
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