AI agents

Two agents that do the groundwork

One searches and screens, the other prepares the documents. The last step is yours: you do the sending.

The job finder goes through your sources, pre-sorts them by your rules and scores every remaining posting against your master profile. The documents agent then tailors resume and cover letter to the applications you hand it, and attaches whatever you picked. Both land with you for review.

Agents are part of Pro. Pro includes 3 complete runs to try them out; Autopilot brings 150 job checks and 150 applications per billing period.

How the job finder works

Example view

  1. Searching through the same path as the job scanner
  2. Pre-sorting by rules, not by feel
  3. Scoring against your master profile
  4. Reporting what clears your threshold

Reporting what clears your threshold

  1. Fill in your master profile

    Every posting is scored against this profile, and the documents are built from it. If it is missing, the run stops and says so - it does not make anything up.

  2. Set your search profile

    Role, location, sources and a blocklist. Plus the threshold above which a match is worth reporting. The percentage comes out of the scoring; the threshold only decides what you get to see afterwards.

  3. Review and send

    Whatever the run found and prepared sits in your agents area. You read it, change it, discard it - and send from your own mailbox.

How it runs

How the job finder works

A run is a fixed sequence of named steps, not one big question to a model. Three of the four steps cost nothing at all - only the scoring is expensive, and that is exactly where the caps bite.

  1. Searching through the same path as the job scanner

    The agent has no second search path. It calls the same scan you can start by hand: watched career pages and your saved searches in the German Federal Employment Agency job board. Whatever is filtered out there never arrives here.

  2. Pre-sorting by rules, not by feel

    From the findings the agent takes the newest ones, drops whatever is on your blocklist and cuts the list down to your daily cap. This step is pure arithmetic: no model, no cost, and you can follow it.

  3. Scoring against your master profile

    Every remaining posting goes through the same evaluation as a job check you start yourself - percentage, criteria and the questions that may come up in an interview. After each single score the run saves its state, so an abort does not cost the whole batch.

    A posting that cannot be read is counted and skipped. The run does not stop over it.

  4. Reporting what clears your threshold

    At the end there is a summary in your agents area, and an email or a push message if you want one. Reported is what clears your threshold - everything that made it through the pre-sorting was scored.

Pre-sorting by rules, not by feel

Example view

  1. Searching through the same path as the job scanner
  2. Pre-sorting by rules, not by feel
  3. Scoring against your master profile
  4. Reporting what clears your threshold

From the findings the agent takes the newest ones, drops whatever is on your blocklist and cuts the list down to your daily cap. This step is pure arithmetic: no model, no cost, and you can follow it.

Documents

Documents, if and when you want them

The second agent does not work on a hunch. You hand it a list of finished job checks and it prepares exactly those - twenty at most in one go.

  1. You pick the applications

    What documents get built for is your call. The agent does not decide it. Every application you hand over is checked first: is it yours, and is its evaluation finished? Otherwise nothing runs.

  2. Tailoring the resume, writing the cover letter

    The resume is tailored to the posting and the cover letter written to match - through the same generation path the 1-click application uses. The document language follows a fixed rule, not the model.

  3. A fact check that flags instead of rewriting

    A mechanical check then compares cover letter and resume against your master profile and marks whatever is not in there. The findings sit with the application. Nothing is edited in - "not evidenced" is not "disproven", and that distinction belongs to you, not to a model.

  4. Attachments from your own selection

    Which references travel along is in your settings and never comes out of a model. If you have never picked, all references are the default; if you deliberately picked none, none go.

Documents, if and when you want them
  • You pick the applicationsDocuments
  • Tailoring the resume, writing the cover letterDocuments
  • A fact check that flags instead of rewritingDocuments

A fact check that flags instead of rewriting

Control

What keeps you from being surprised

An agent that runs without you needs hard limits - otherwise it is a risk, not a tool. There are four, and they hold independently of each other.

  1. Your explicit consent first

    Turning it on the first time asks for its own consent, and the server refuses to start without it - not just the button. No agent runs before that, at night or otherwise.

  2. A daily cap you set yourself

    You decide how many scorings a day may cost; your plan caps that value on top (currently 20). Two runs of the same kind are at least 6 hours apart.

  3. A quota that cannot be overdrawn

    Autopilot brings 150 job checks and 150 applications per billing period. Pro gets 3 complete runs to try things out - once, for the lifetime of the account, not monthly. When a pot is empty the run stops instead of quietly billing on.

  4. A kill switch that closes when in doubt

    Above all of it sit two cost ceilings and a switch that halts every run at once. If its state cannot be read it counts as pulled - in doubt nothing runs, rather than in doubt everything.

What keeps you from being surprised
  • A quota that cannot be overdrawnControl
    150
  • A daily cap you set yourselfControl
    20
  • Your explicit consent firstControl

A kill switch that closes when in doubt

Limits

What the agents do not promise

Automatic here means the groundwork happens without you. It does not mean anyone applies. Four limits that belong on this page rather than in a footnote.

  1. You do the sending

    Jobvin never sends an application to an employer. That is a decision, not a missing feature: an application arriving from an address that is not yours reads as unprofessional. You get the finished files and the text blocks and send from your own mailbox.

  2. No promised cadence

    What is reliable is the run you start yourself. This page does not promise you a fixed rhythm in the background - that would hang on a schedule outside the product, and a promise someone else would have to keep is no promise.

  3. The fact check corrects nothing

    It marks what is not in your profile and tells you where to look. It deletes no sentence and rewrites none. Whatever ends up in your application, you have read and released.

  4. Agents are part of Pro

    Turning them on, starting a run and seeing the results are tied to Pro, and that is checked on the server. The full quota comes with Autopilot; Pro has the trial run. Without either you still have the job scanner and the job check by hand.

What the agents do not promise
  • You do the sending
  • No promised cadence
  • The fact check corrects nothing
  • Agents are part of Pro

Automatic here means the groundwork happens without you. It does not mean anyone applies. Four limits that belong on this page rather than in a footnote.

Common questions

What do the agents cost?

They are part of Pro, and the full quota comes with Autopilot: 150 job checks and 150 applications per billing period. Pro gets 3 complete runs to try them out; those last for the lifetime of the account and do not come back. What else the plans include is on the pricing page.

How often do the agents run?

What is reliable is the run you start yourself. Two runs of the same kind are at least 6 hours apart, and your daily cap limits how many scorings a day may cost. This page does not promise a fixed rhythm in the background - an honest gap beats a promise that would depend on a schedule outside the product.

Does the agent apply for me?

No. It searches, scores and prepares; you do the sending. There is no sending through a Jobvin address, and that stays the case. You get the finished PDF files and the fields to copy, and you send from your own mailbox - so your name is in the sender, which is where it belongs.

What if the AI makes something up?

That is what the fact check is for. It compares cover letter and resume mechanically against your master profile and marks whatever is not evidenced there - an employer you never entered, or a number of years that does not add up. Findings are shown, never edited in: whatever you send, you have read.

What does the agent see of me?

Your master profile, your search profile and the postings it finds. Anything it acts on, such as the attachments, comes from your settings and never from a model. Delete your account and the runs go with it; what is kept for how long is in the privacy policy.

Let the groundwork run

Fill in the master profile, set up a search profile, switch it on - after that you find scored roles and finished documents waiting, instead of assembling both yourself.

Go to your agentsThe agents area sits behind the login. Switching on and starting a run are part of Pro.

See pricing

Go to your agents

The agents area sits behind the login. Switching on and starting a run are part of Pro.