Check local prospects' email security and draft personalized outreach for your approval
Have Grok Bot research local businesses' public email-security records and draft personalized first-touch emails for your approval, the work the author says his AI team did.
What the agent did
Source-reported example · as described by Eddy Kawira, runs a one-person local tech services business in South Bend, Indiana (Eddy Services); infrastructure engineer and writer of the eddykawira.com blog (per the post, his About blurb and his services site)
The author, Eddy Kawira, who runs a one-person local tech services business, wrote a blog post about running his business with an AI team for three weeks. He says the team has an orchestrator, Vision ("a Grok Bot"), that coordinates nine specialist agents.
On the sales side he says the team researched 100 local small businesses with reachable contacts. For each one it ran a passive email-security check on the business's domain, looking at three records, SPF, DKIM and DMARC; he says "passive" means reading what each domain already publishes, "not poking at anyone's systems".
From that research he says the team drafted 96 personalized first-touch emails, each naming that business's actual finding, and that none went out without his approval.
The post also describes other work (a revenue tracker, a weekly funnel routine, an offer sheet, two self-hosted services, secrets cleanup and a billing catch), which this listing does not cover. The post gives no prompts, steps or example email, and does not say why 96 of the 100 businesses got a draft.
He reports 100 local businesses researched and 96 personalized first-touch email drafts, none sent without his approval. The post does not report replies, meetings or sales from them.
Separately, his own table of estimates lists 30 hours ("$1,022") for "Lead research and domain checks" and 15 hours ("$511") for "96 personalized emails": the hours are his own estimates of what a person would take, priced at Bureau of Labor Statistics mean hourly wages for the South Bend-Mishawaka, IN-MI area (May 2025), and he says they are "a way to size the work, not a precise savings figure".
Limitations
One part of a long post that covers many other jobs. The post names Vision as a Grok Bot but credits the research and drafting to "the team" and does not say which of the specialist agents, or which tool or model behind them, did this work.
It gives no prompts, steps, setup, example email or finding, and no outcome beyond the 96 drafts; it does not say why 4 of the 100 businesses got no draft. The hour and dollar figures are the author's own estimates of what people would cost, not measured savings, and we do not total them.
The author sells business email setup (per his services site), each email names that business's email-security finding, and the post ends with an offer of a free email-spoofing check; it does not say what the drafts offered. The author also uses Claude Code and Gemini for coding, which is not part of this task.
Try it in your business
What you'll need
Grok Bot, or a Grok Bot team set up with roles like the author's; a list of the businesses to research (the post does not say whether the team found them or he supplied them); somewhere to keep the drafts and findings; your own approval of every email before anything is sent.
The post describes a multi-agent team (an orchestrator, nine role agents, short instruction files and skills) that the author set up himself, but not how the prospect research and drafting are wired. The label is our reading, not something the author states.
The original is a custom-built system. The prompt below is a simpler starting point and won’t reproduce it.
Starting prompt
The author didn't publish their prompt (read the full page; no prompt or instruction is quoted), so this is our adaptation.
How ours differs from the original setup: Same execution agent (Grok Bot, one assistant instead of the author's nine-agent team). The author published no prompt, so this is our starting prompt from his description.
It asks for 'unknown' where a record cannot be read, adds a findings table and a no-contact, no-send instruction, and leaves the businesses list as a blank for you to fill in, because the post does not say how his were chosen. It does not include his other work (revenue tracker, funnel routine, offer sheet, infrastructure, billing).
Here is a list of local businesses: [name, website, contact]. For each one, read only the DNS records the domain already publishes publicly and note whether it has SPF, DMARC and DKIM records and anything that looks missing or misconfigured. If you cannot tell (for example DKIM may depend on a selector you cannot see), write 'unknown' instead of guessing. Do not probe, scan or log in to anything. Then draft a short first-touch email to the owner, in plain English and in my tone, that names what you found for their domain and offers [my free check or service]. Put the findings in a table (business, domain, what you found, how sure you are) and save each draft with it. Do not send any email or contact anyone; give me the table and the drafts for my review and approval.
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
Screen potential clients against your ideal-client criteria and log the scores in a spreadsheet
Have Claude Cowork screen potential clients against your ideal-client criteria and log each score with a link to its proof in a spreadsheet, the agent the author describes.
Our suggested starting prompt — not the author's original · untested
You'll need: Claude Cowork; your written ideal-client criteria and any disqualifying rules; access to the sites it searches (the post does not say how); a spreadsheet for the results; your own decision on who to contact.
Screen potential clients for [my business]. My ideal client is: [criteria]. Skip any company that [disqualifying rule, for example already has its own IT staff]; check that before you score. Find companies through [job postings, LinkedIn, Upwork or other places I name] that look like [type of company or role]. For each company, read its website and LinkedIn page, then score it from [low] to [high] against my criteria. For every score, record a link to the evidence behind it. If you cannot check something, give the company no score and write down what is missing and why. If two sources disagree, record both with their links; if either source fails my criteria, disqualify the company; if you cannot tell which source is accurate, give the company no score and flag it for my review. Put everything in a spreadsheet called [name]. Do not contact any company or send anything; I decide who to reach out to.
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.
Draft the weekly recap email to a client
Have Grok Bot write the weekly recap email to a client, then clean it up, as the author says he does.
Our suggested starting prompt — not the author's original · untested
You'll need: Grok Bot with enough access to, or notes about, the week's work for the client (the post does not say which); your usual recap format or an earlier recap to follow; your own read-through and clean-up of each draft before it goes to the client.
Draft this week's recap email to [client name]. Cover what we did for them from [date] to [date], what is in progress and what we need from them next. Use [where the week's work is recorded: notes, a task list or a folder I give you] and my last recap, [paste or attach], as the format and tone to follow. Where you are unsure whether something happened, mark it 'check' instead of stating it. Do not send anything to the client; give me the draft to review and edit.

