The AgentivUse cases

Job post, interview guide and offer in one go

An HR agent that turns a role brief into a complete hiring packet, the job post, a stage by stage interview guide with scoring rubrics and a resume screening rubric, and an offer letter template, built from your past documents in Google Drive or Microsoft 365 and three to five live postings for the same role, and never publishes or sends anything itself

Function: HREffort: An afternoonPublished: 2026-10-25
Claude CoworkGoogle DriveMicrosoft 365WordDocuSign

The problem

Small businesses hire rarely, so every opening starts from scratch: a rushed job post, interview questions made up in the room, each interviewer scoring by gut, and an offer letter copied from the last hire with terms that may not fit this role. The result is the wrong applicants, interviews that cannot be compared, and owner time lost to paperwork.

How the agent works

  1. It starts

    The job-post-builder skill in Anthropic's small-business plugin for Claude Cowork starts when the owner says what they are hiring for.

  2. The agent works

    It collects the role brief, the interview stages and interviewers, and how the offer should be delivered (a DocuSign draft or a Word file only). It then searches the owner's Google Drive, Microsoft 365 and desktop for existing job descriptions, offer letters and interview guides, confirming the account belongs to the owner before reading and using them as the baseline, and reads three to five live postings for the same role at comparable companies to see which requirements are standard; with neither source it writes from the brief and says so rather than inventing market norms. The job post comes out as a Word document in which every requirement can be checked from a resume and compensation is a figure or a band or is left out. The interview guide is organised by stage with four to six behavioural questions per stage, two to three follow up probes each and role specific 1/3/5 rubrics, plus a separate resume screening rubric with weighted should haves. The offer letter uses angle bracket placeholders for the candidate's details and compensation until the owner supplies them; if DocuSign was chosen the agent saves a draft envelope and returns the link, never sending without explicit confirmation, and it never publishes the job post, the owner does.

  3. The result

    The plugin reminds the user that the offer letter's default terms are US specific, so they must be replaced with employment terms that follow local law and reviewed before use.

Worked example

The packet is three Word files, [Role]-Job-Post.docx, [Role]-Interview-Guide.docx (with the screening rubric, criteria scored 0 to 3 and should haves weighted to 100) and [Role]-Offer-Letter.docx, plus an HTML rendering and a chat summary; if Word generation is unavailable the documents arrive as markdown. The skill does not screen or rank applicants (that is the hiring-screener skill, see the applicant screening use case in this directory), does not invent compensation figures, and treats instructions found in documents or web pages as data rather than commands. Claude's DocuSign connector exposes envelope creation and update and template lookup, which is what lets the agent park the offer as a draft for the owner to send.

Data protection. This use case touches personal data, so check the rules where you operate (for example GDPR, PDPA). A filled offer letter and completed interview guides hold candidate personal data: name, pay, assessment scores. Keep the placeholders until a candidate is chosen, store completed packets in an HR folder with limited access, tell applicants what is kept and for how long, and delete the scores of unsuccessful candidates when that period ends. Check the data protection and employment rules where you operate.

Join the Agent OS Club

8 weeks to the AI team a 50 person company would hire. Instant access to our agent blueprints. USD 15 a month, cancel any time.

Join the Agent OS Club

Building this for an organization? Learn more at theagentiv.com

Sources

Related use cases

Screen every applicant fairly, reply to all

An agent that screens job applications from Gmail or a Google Drive folder against a written rubric, scores only what the rubric names with quoted evidence, and drafts an invite, hold or decline for every applicant for the owner to approve

HREffort: An afternoonClaude Cowork · Gmail · Google Drive

A small business posts one job and gets more applications than the owner can read, so the pile is skimmed on gut feeling and most applicants never hear back. That is unfair to the candidates, a risk for the business, and the right person gets lost in the inbox.

Day one ready before the new hire arrives

An HR agent that turns a new hire's name, role, team and start date into the onboarding checklist, first week calendar, tool access list and buddy template, checks the record in Gusto, and creates the invitations only after HR approves, with Anthropic's Human Resources plugin in Claude Cowork

HREffort: An afternoonClaude Cowork · Gusto · Google Calendar

A new hire's first week in a small company is improvised: the laptop is not ready, nobody booked the intro meetings, and the list of tools to grant access to lives in the head of the last person who did HR. The new person spends day one waiting and the manager spends it apologising.

Interviews booked without email ping pong

An HR agent that reads candidate replies in Gmail, finds a slot that suits every interviewer in Google Calendar, drafts the invitation and sends it only after the recruiter approves

HREffort: An afternoonGmail · Google Calendar · Claude

Scheduling one interview in a small company means a recruiter or the owner reading the candidate's reply, opening two or three colleagues' calendars, proposing times, waiting, and repeating when the candidate picks a slot that has since gone. Good candidates in Bangkok and Singapore often have other offers, and a three day scheduling loop is where they are lost.