All agents
    PeopleAvailable now

    HR policy drafter

    Drafts a new HR policy, or an update of one of yours, with the law behind each legal point, for you to check.

    How it works

    Ask for a policy, like “work from home policy for a 50-person IT company in Karnataka”, or pick one of your policies and say why it should change (or pick a change the Compliance watcher found for your company). It drafts the policy in sections. Where it states a legal requirement, it names the law it relies on (a built-in reference to a central law, or a notice the Compliance watcher stored); where it has no source, the statement is marked “check with your legal adviser”. An update shows exactly what changed against your current policy and why. Every draft says “not legal advice; review before publishing”. Nothing is saved until you confirm; then the policy is saved in People › Documents as a draft, as you. Publishing it, and asking employees to acknowledge it, stay yours; once published, the policy search reads it.

    Uses AI credits for each draft (the larger model, as it writes the whole policy). Finding missing policies uses none.

    What it reads

    • Your company's policies in People and those synced in Agents › Knowledge, only your own company's
    • Changes the Compliance watcher matched to your company, and a built-in list of central labour laws

    When it starts

    • When you write a brief or pick a policy on the agent's page, or ask the assistant on the web

    What it can do

    • Save the drafted policy in People › Documents as a draft, as you (after you confirm)

    What it never does

    • Publish a policy, ask employees to acknowledge it, or change a published policy

    Safe by design

    • One assistant, many agents. Ask the Employee assistant in the app or on WhatsApp; it calls the agents your company has hired that you may use.
    • Hired, not switched on. Your admin hires each agent from the catalogue and chooses who can use it.
    • Agents propose, people confirm. Anything that changes data, like a leave request, waits for a person to confirm it.
    • Same access as the user. An agent sees only what the person asking is allowed to see.
    • AI processing in India. Agents run on models hosted in India (AWS Mumbai).
    • Budgets and a hard stop. Set a monthly credit limit per agent; agents stop when credits run out.
    • Every run recorded. Admins see each run, the credits it used and what it did.

    Frequently asked questions

    What does the HR policy drafter do?

    Ask for a policy, like “work from home policy for a 50-person IT company in Karnataka”, or pick one of your policies and say why it should change (or pick a change the Compliance watcher found for your company). It drafts the policy in sections. Where it states a legal requirement, it names the law it relies on (a built-in reference to a central law, or a notice the Compliance watcher stored); where it has no source, the statement is marked “check with your legal adviser”. An update shows exactly what changed against your current policy and why. Every draft says “not legal advice; review before publishing”. Nothing is saved until you confirm; then the policy is saved in People › Documents as a draft, as you. Publishing it, and asking employees to acknowledge it, stay yours; once published, the policy search reads it.

    Can the HR policy drafter change data on its own?

    No. It asks a person to confirm before it will: save the drafted policy in people › documents as a draft, as you. It never does the following: publish a policy, ask employees to acknowledge it, or change a published policy.

    How much does the HR policy drafter cost?

    Uses AI credits for each draft (the larger model, as it writes the whole policy). Finding missing policies uses none.. Credits are a paid add-on to any flowwork.ai plan at ₹100 (US$ 1.19) per 1,000 credits, and new companies get 500 free trial credits for 30 days.

    Where is the data processed?

    Agents run on AI models hosted in India and see only what the person using them is allowed to see. Admins see every run and the credits it used.

    Other agents