by Audra Carpenter

Run a small hiring round: review applicants, draft outreach and replies, track interviews and prepare offer letters

Have Claude Cowork read each applicant's resume, draft personalized outreach and replies for the author to edit and send, set up interview booking and a candidate tracker, and prepare offer letters, while the author does the interviews and makes the hiring decisions with the team.

What the agent did

Source-reported example · as described by EntreProfessor (pseudonymous Substack author; startup founder who is part of an AI startup and teaches university courses)

The author, part of an AI startup with no HR team or applicant tracking system, used Claude Cowork to recruit four summer co-ops (AI/Automation Designer & Coordinator, Graphic Designer, Marketing Specialist, Social Media Coordinator) from applications that arrived by email through a university partnership.

Per the post, Cowork read every resume to write an analysis of each candidate ("not to screen"), including where candidates who applied to several roles fit best; drafted personalized outreach for each candidate and staged it in the author's email for the author to read, edit and send; ran scheduled email review and drafting sessions (morning, midday, afternoon), drafting replies and flagging anything needing the author's judgment; set up a Calendly scheduler, tracked who had booked interviews and who hadn't; kept a live Finalist List, synthesizing the author's interview notes and tracking each candidate's status from "Invite Sent" to "Offer Accepted"; generated four individualized offer letters with the internship agreement attached as PDFs ready for DocuSign; and drafted personalized release emails for candidates not selected.

The author did the interviews, made the hiring decisions with the team, and reviewed and edited every email before it was sent.

Reported: the author says it took "eight days" "from first application to signed offers" for four hires from "twenty-three candidates", and that the author "had at least one real conversation with almost every single one of them." Reported: handling email took "less than two minutes per exchange instead of twenty."

Reported: the four offer packets were ready "in about twenty minutes." Reported: "Every single person in our pool got a thoughtful, personalized response. Nobody got ghosted." Reported: there were "a few minor glitches that were quickly corrected with a personal message."

Limitations

The post doesn't show the instructions given to Claude Cowork, any example email, candidate analysis, tracking document or offer letter. It doesn't say how the inbox, calendar or Calendly were connected or what access Cowork had.

The author says every outreach email "read like I wrote it, because the connections were real", and separately notes having spent a lot of time training their AI tools to write like them with years of writing samples and edited messages; the post doesn't say whether that training was done in Claude Cowork, and that setup isn't described.

Every email was reviewed and edited by the author before sending, and the author did the interviews and, with the team, made the hiring decisions. The "minor glitches" aren't described. The time savings are the author's own figures; the post doesn't say how they were measured.

The startup and the author's name aren't stated. The post also describes Cowork designing an onboarding program for the hires (6-module course outline, four pre-work assignments, 3.5-hour kickoff agenda); that is a separate job and not part of this listing.

Using AI to read resumes in hiring can raise fairness and data-protection questions; the author says it was used to contextualize, not to screen.

Try it in your business

What you'll need

Claude Cowork; access to the inbox where applications arrive (drafts only); a scheduling link such as Calendly and a calendar; a candidate tracking document; an offer-letter template and agreement; an e-signature tool such as DocuSign used by the owner; clear role criteria; the owner's review of every email before sending

Claude Cowork worked across the author's email, a Calendly scheduler it set up (which filled the author's calendar), and documents (tracking list, templates, PDFs), with scheduled review sessions; no custom code is described.

Starting prompt

The author didn't publish their prompt (the post describes each step and gives an eight-step "Blueprint" in prose, e.g. give Cowork "the job description, their resume, and one sentence about what caught your eye", but publishes no prompt or instructions given to Claude Cowork; checked the full free post, its section links and the author's Substack profile on the page 2026-10-18; no linked repos, docs or templates), so this is our adaptation.

How ours differs from the original setup: Same Claude Cowork execution agent. Written as one guided session rather than the author's scheduled morning/midday/afternoon email sessions; keeps every message as an unsent draft, adds no ranking or rejecting by the agent, and leaves interviews, decisions, sending and signing to the owner.

Assumes the owner supplies role criteria and an offer template; the author's writing-style training isn't reproduced.

Our suggested starting prompt — not the author's original · untested
Help me run a hiring round for [roles]. Here are the role descriptions and what success looks like for each: [criteria]. Applications arrive by email at [inbox/label]. For each applicant, read their resume and write a short summary of relevant experience, strengths and open questions against only my stated criteria, noting if they might fit another open role. Don't rank or reject anyone. Draft a personalized reply to each applicant inviting them to book an interview at [scheduling link], and save it as a draft for me to review; do not send anything. Keep a tracking document with each candidate's status (invite drafted, booked, interviewed, decision) and tell me who hasn't booked. After interviews I'll add my notes; update the summaries. When I tell you who gets an offer and the terms, fill in [offer letter template] for each and save PDFs for me to review and sign. Draft a personal note for each candidate not selected, as a draft only. Don't delete emails, accept or cancel meetings, or contact anyone yourself.

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

Report a correction

Related use cases

Screen and rank incoming job applicants against the role's requirements

Have Claude Code pull in recent job applications, score each candidate against the role's requirements and keep a ranked list, flagging hidden instructions and suspicious profiles.

Claude Code · Hiring and people · Custom development · Source: Taimoor Tariq (Founder & CEO, GTM Base) · March 31, 2026

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.

Claude Cowork · Finance and bookkeeping · Prompts and files · Source: Andrew Blumson, founder of Adevious, a UK AI training and software business (per adevious.co.uk); the business whose bookkeeping the post describes is not named · October 24, 2026

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.

Claude · Operations · Connected apps · Source: 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 · May 20, 2026