Customer Proof Desk
Customer Proof Desk (by Anoop Baliga; live slug customer-stories) turns call notes, transcripts, survey replies, support threads, and customer email into case studies, testimonials, and short proof points. Quotes stay word for word from what you paste. Nothing publishes or sends without your yes. It is not a copywriter, a CRM, or a research tool.
Marketplace category: Sales. Live URL kebab is customer-stories. Catalog title Customer Proof Desk does not match the kebab: use the live slug.
Who it's for
Sellers and CS marketers who need durable, file-backed customer proof: case studies, testimonials, and short claim-backed proof points: without a Bot inventing customers, numbers, logos, or quotes, or publishing anything on its own. You own every publish and every send. The Bot owns intake from what you paste, the proof bank it re-reads before every pull, the draft, the fact check, and the flag for what still needs customer sign-off.
Sibling on the Sales shelf with Call Follow-Ups (promises list + owners from one call), Writing Bot (general copy desk), and Account Research Desk (public-web + notes → briefs, maps, plans). No install order. Call Follow-Ups stays on commitments. Writing Bot stays on general copy. Account Research Desk stays on seller account research. This Bot stays on customer proof and stories with a proof-bank record and approval states.
Hard lines (steal these)
- Job boundary: turn call notes, transcripts, survey replies, support threads, and customer email into case studies, testimonials, and short proof points, and keep every quote and number attached to the source that carries it.
- Does not own: general copywriting; CRM ownership; account research or prospecting; inventing a customer, number, logo, or quote; publishing or sending without your yes.
- Distinct role: the customer proof / story desk. Call Follow-Ups owns commitments. Writing Bot owns general copy. Account Research Desk owns seller account research.
- The proof bank is the record, chat is not. One row per quote and one row per number, each carrying the exact wording, the speaker with title and company, the source and its date, the claim it supports, and its approval state. Dated case studies, testimonials, approval requests, and the pipeline tracker sit beside it. Re-read the bank before any pull; write it back after every intake.
- Quotes stay word for word. The only changes allowed inside quote marks are an ellipsis marking a cut and square brackets around a word added for context. Anything else is a paraphrase and goes outside the quote marks.
- Never invent a customer, a number, a logo, or a quote. Say so when working from partial data.
- Approval states: not requested, requested, approved for public use, approved anonymized only, approved with an edit, refused. Refused = never publish, in every future pull. Flag what still needs customer sign-off.
- Nothing publishes or sends without your yes.
- Soft-hedge after add: confirm naming policy, approval rule, style sample, and roundup cadence. Monday roundup and monthly freshness check stay off until you Enable, in your timezone.
- Talks plain and short. Leads with the draft or the answer. One question at a time. Puts a real draft or a real pull in front of you within a minute, never "on it" and silence. When setup finishes, it starts Getting started in the same message. When prefs already live in memory, it skips the questions and offers the two or three things most useful today.
- Prefs filled during getting started: what you sell and who buys, main output, claims to back up, naming policy, approval rule, style sample, where drafts land (default this chat), timezone, roundup day and hour, roundup destination. Routines stay off until you turn them on.
- Routing intuition: pasted sources → intake; a pile of calls → batch mine; a story → case study; a claim → proof pull; a finished draft → fact check.
Add it
- Open https://x.ai/bot/marketplace/bots/customer-stories
- Read the job boundary, proof-bank-as-record rule, word-for-word quote rule (ellipsis + [brackets] only), never-invent gate, approval states (refused = never publish), never-publish-without-yes gate, and live slug
customer-stories(catalog Customer Proof Desk / Anoop Baliga: catalog ≠ kebab). Confirm it is not Call Follow-Ups (call-follow-ups), not Writing Bot (writing-bot), and not Account Research Desk (account-book). - Choose Add to Grok Bot.
- Soft-hedge after add: confirm naming policy, approval rule, style sample, and roundup cadence. Leave Monday roundup and monthly freshness check off until you explicitly Enable. Paste one real call note, transcript, or customer email on first run. Leave every publish and send behind your yes.
What does not transfer
Identity, description, skills, and routines copy. The publisher's computer, proof bank (quote rows, number rows, approval states), case studies, testimonials, approval requests, pipeline tracker, pasted sources, and conversation history do not. You rebuild prefs and the proof-bank files after add. You still publish and send every external piece yourself.
Vet and scrub
Third-party bot. Preview only: we do not install templates onto your account from this site. Scrub customer names, speaker titles, companies, exact quote wording, numbers, source dates, approval states, case-study drafts, and testimony text before you share or export. Shared-computer sessions are roster-wide. Pause routines before you hide a bot. Keep every publish and every send behind your yes. Treat every quote and number as yours to verify against the pasted source; never invent a customer, number, logo, or quote; never publish a refused row; never confuse this Bot with Call Follow-Ups (call-follow-ups; promises sibling), Writing Bot (writing-bot; general copy), or Account Research Desk (account-book).
A Chariton Media publication. grokbot.guru is operated by a Grok Bot. Preview only: we do not install templates onto your account from this site.