Onboard a new client end to end: draft the contract, set up their Slack channel and podcast feed, and build website mockups for your review
Have Claude run a client-onboarding skill that drafts the client's contract, creates their shared Slack channel, adds them to your client database, and prepares samples, website mockups and a podcast feed for your review, while you send the invites, grant access and write the client messages yourself.
What the agent did
Source-reported example · as described by Peter Hartree, who runs TYPE III AUDIO (T3A, bespoke AI narration services for the AI safety and effective altruism communities) and calls himself an AI Uplift Consultant; author of the AI Wow journal (wow.pjh.is); describing his own business's onboarding of the client Epoch AI
The author, Peter Hartree, runs TYPE III AUDIO (T3A), which provides bespoke AI narration of articles for organisations. For a new client, Epoch AI, he had Claude do much of the onboarding work.
Setup: Claude read T3A's internal documentation and client notes and wrote an overview of how the business works; then, from his long context dump and voice notes, it drafted the onboarding process, which they iterated into a "t3a-client-onboarding" skill.
Contract: given the client emails and call transcripts, Claude looked at his previous service contracts in Google Drive, merged in the agreed service details, found the client's public details online (registered address, charity number), created a Google Doc and downloaded a PDF for signature; he made minor edits and added one detail.
Claude's browser use created the signing item in Signwell but could not use the file-upload dialog, so he finished that step himself.
Slack and portal: Claude created a Slack Connect channel through browser use, following his existing channel-naming pattern, and gave him the invite link to send to the client; it added the client's information to the client-portal database, but for security he granted the client's access in Cloudflare himself, with Claude opening the right dashboard page and reminding him of a known pitfall.
Tailoring: Claude crawled the client's articles, identified special elements (graphs, images, tables, formulae, footnotes and so on) and proposed narration rules; its first pass had "a few glaring errors", so he gave feedback and they wrote detailed guidelines.
Claude then implemented the client-specific changes in T3A's own narration codebase, generated test MP3s of a handful of articles it suggested and short MP3s of especially tricky passages it found by crawling the client's site, and improved T3A's internal proof-listening tool. He did the proof-listening himself.
Client materials: Claude produced sample narrations, a list of key judgement calls to discuss with the client, audio-player mockups on a copy of the client's site layout with their brand colours (three designs he suggested, with screenshots), and the client's podcast feed, including cover art from the client's logo sized to Apple's podcast requirements (he touched up the art in an image editor).
Client messages: he wrote all client communications himself, almost from scratch, using Claude for a bullet list of points to cover and a clarity check of his drafts; he rewrote Claude's draft status update from scratch.
Reported by the author, as his own estimates: onboarding a complex client like this typically takes him 4–5 days of full-time work, and for this client Claude saved him "roughly a full day of full-time work, despite the one-off training investment"; he guesses it could save 2–3 days for the next comparable client.
Limitations
One client (Epoch AI), described by the author in his own post; the time savings are his estimates, and the onboarding was still awaiting the client's feedback when he wrote it.
He stayed closely involved: he wrote all client communications himself, almost from scratch (Claude's draft update was, in his words, "verbose and horrible"), edited the contract, sent the Slack invite link himself, uploaded the contract to the signing service himself after browser use failed, chose not to let Claude grant the client's portal access for security, did the proof-listening of the audio himself (he says none of the AIs he has tried can do it reliably yet), touched up the cover art, and corrected Claude's analysis after its first pass.
He says Claude cannot yet onboard a client autonomously. A large part of the work was specific to his business: Claude changed T3A's own narration codebase and internal proof-listening tool.
A business without its own software would use only the contract, setup, mockup and client-message parts. The skills themselves are not published (the post shows only screenshots), and the post does not name the Claude app, plan or model.
Caution (ours, not the author's): be careful about letting an agent create accounts or channels, invite people, grant access, upload documents for signature, publish anything, or send messages for you or your client. Review each of these steps and do them yourself, as the author did with the client invite, the portal access and all client messages.
Try it in your business
What you'll need
Claude with skills (or saved instructions) describing your onboarding process; your internal docs, past contracts and the client's correspondence; access to your documents (for example Google Drive and Docs) and, if you let it do setup steps, to your team chat (the author used Slack via Claude's browser use) and client database; your own review of the contract, every account, channel or access change, and every client message.
Building the skills was a one-off investment of about a day of the author's time, by his estimate.
Claude works across the author's existing tools (Google Drive and Docs, Slack, a signing service, his client database) using skills he wrote with it, with browser use for some steps.
Part of the job, tailoring his narration system, was Claude changing his business's own code; that part needs your own software and is not required for the contract, setup, mockup and messaging steps.
Starting prompt
The author didn't publish their prompt (read the full post and its links to type3.audio and epoch.ai, and the author's About page, on 2026-10-29; the post describes what he asked Claude to do, for example to read T3A's internal documentation and write an overview of "what T3A does, and how everything works", but publishes no prompt or skill text, only screenshots), so this is our adaptation.
How ours differs from the original setup: Same execution agent (Claude). The author did not publish his prompts or skills; this is our starting prompt, based on the steps he describes, which you could save as a skill.
Ours is strictly draft-and-approve. Claude asks before creating any channel, record or account, and never invites the client, grants access, uploads to a signing service, publishes or messages the client.
In the post, Claude created the Slack channel itself, created the signing item in Signwell and set up the podcast feed, while the author sent the invite link, granted portal access and wrote the client messages.
Ours leaves out the work on his own software (tailoring his narration system in T3A's codebase, generating test MP3s, improving his proof-listening tool), and uses placeholders for his tools and deliverables.
Help me onboard a new client for my [type of service] business. Work in stages and stop for my approval at the end of each one. Stage 0 (first time only): Read my internal docs and past client notes in [folder]. Write a short overview of what my business does and how it works, then draft a step-by-step client onboarding checklist. I'll correct it. Once I approve it, save it as reusable instructions I can run for future clients. Stage 1, contract: Using the client emails and call notes I've attached and my past contracts in [folder], draft a service contract for [client] as a document. Look up their public details (legal name, registered address, registration number) and list where you found each one. Highlight anything that differs from my usual contract or that you're unsure about. Don't send it or upload it to a signing service. I'll review it and send it myself. Stage 2, setup: List every channel, record and account this client needs (for example a shared [Slack] channel that follows my naming pattern, or an entry in my client database), and wait for my OK before you create each one. Don't invite the client, grant access, change permissions, or enter any password or payment details. Give me the invite link or the exact page to open, and I'll do those steps. Stage 3, tailoring and samples: Review [the client's website or materials], list the special cases my service needs to handle for them, and propose a rule for each. After I approve the rules, prepare [sample deliverables] for me to check, and flag anything you're unsure about. Stage 4, mockups and delivery setup: Make mockups of [how my deliverable would look on their website], using their public branding, and draft [the feed, page or other delivery setup] privately. Don't publish anything until I approve it. Stage 5, client update: Don't write or send messages to the client. Give me a bullet list of points to cover in my update, then check my draft for clarity and for anything I've missed. Finish with a checklist of what's done, what's waiting for my approval, and what I need to do myself.
Replace the [bracketed] parts with your own files and tools.
Get examples like this every Tuesday and Friday
Practical ways to put AI agents to work in your business. We check the original sources, explain the setup and point out the limits. Free.
Unsubscribe any time. Privacy policy
Related use cases
Run a new client's standard audits and draft the kickoff strategy brief
Have Claude Code run a new client's standard first-week audits and draft a strategy brief with recommended priorities for you to review before the kickoff call.
Our suggested starting prompt — not the author's original · untested
You'll need: Claude Code; read access to the client's website and, for the analytics and CRM reviews, the client's Google Analytics/Tag Manager and email/CRM tools; a written audit checklist; a brief template; the owner's review before anything is sent
We're onboarding a new client: [client name], website [URL], industry [industry], main goal [goal] (from their intake form in [file]). Please prepare a first-week audit and a draft strategy brief for me to review. 1) Technical SEO: check the public site for crawlability, page titles and descriptions, broken links, page speed and mobile issues. 2) Analytics: from the export or read-only access I've given you [path/access], note whether Google Analytics and Tag Manager are set up and tracking key actions. 3) Competitors: for these competitors [list], compare the main keywords and topics they appear to target. 4) Email/CRM: from my notes [file], summarize their current setup and gaps. Save each audit as a separate file with findings, evidence and what you couldn't check. Then draft a one-to-two page strategy brief with the top 3–5 recommended priorities, each tied to the audit findings, and list open questions for the kickoff call. Keep everything as drafts in [folder]: don't send anything to the client, don't change any site, analytics or CRM settings, don't buy any tools and don't delete anything. Ask me before using any login or access I haven't listed.
Categorize bank transactions, number vouchers, match payments to invoices and draft year-end accounts
Have Claude Cowork do the bookkeeping from a bank statement and spreadsheet, match payments to invoices and draft year-end accounts, as the author describes in a LinkedIn post that he says Claude wrote.
Our suggested starting prompt — not the author's original · untested
You'll need: Claude Cowork with access to your bookkeeping spreadsheet (and a backup copy), your bank statement export and your sales invoices; last year's accounts prepared by your accountant, for the format; a rules file kept alongside the spreadsheet; your own answers to its questions; your accountant's review.
You are helping me with bookkeeping in Cowork. Files: bank statement [file], bookkeeping spreadsheet [file], sales invoices [folder], last year's accounts from my accountant [file]. Step 1: make a backup copy of the spreadsheet before changing anything and tell me where it is. Step 2: read the spreadsheet and describe my categories, how voucher numbers run and which kinds of transaction never get a number; wait for me to confirm. Step 3: fill in only blank rows where the category and voucher number are clear from the history; for anything new or ambiguous, list a question for me instead of guessing, and never overwrite a filled row. Step 4: check your work against the backup: row counts, and gaps or duplicates in the numbering; report what you find. Step 5: match each client payment to a sales invoice and list any invoices still outstanding and any matches you are unsure about. Step 6: save the rules we agreed, and my answers, to [rules file] and show me what was added. Then, only after I have reviewed all this, draft this year's accounts in the same layout as last year's, section by section, from the categorised data, and flag anything that needs my accountant's judgement (for example depreciation, tax and opening balances) instead of filling it in. Do not send anything to my accountant or anyone else.
Project inventory and recommend when to reorder each product
Have Claude Code pull inventory and sales data, project the next twelve months of sales and stock by product, and recommend when to reorder each one, using written notes on supplier lead times and holidays.
Author's example instructions
You'll need: Claude Code; sales and inventory data by SKU (the author pulled it from Amazon with scripts Claude Code wrote); written notes per brand covering supplier lead times, holiday closures, off-platform stock and past stockouts; an instruction file or command listing the projection steps. Not disclosed: The scripts' code and how the Amazon credentials were connected; the full text of the instruction file and per-brand context files; the number of brands and SKUs; how accurate the projections turned out against actual sales.
1. Check to see if the sales/inventory data we have locally is >5 days old, and if not, pull fresh data from Amazon. 2. Check the context notes for the brand it's working on. 3. Pull inventory and sales data from the local cache. 4. Display the trailing twelve month sales data by SKU and by month. 5. Describe any factors it's going to use to make adjustments to TTM sales data when projecting NTM sales. 6. Review its stated adjustment factors, then project NTM sales by SKU on a monthly basis, and display the amount of stock remaining at the end of each month based on those projections. Use Python for the math here. 7. Recommend when to reorder each SKU, factoring in CNY and other holidays.

