Free · works in the AI your clients already use

Your know-how, on call.

Name an agent, teach it what you know, invite your clients. They ask it from their own AI; it answers from your know-how and asks you when it isn't sure.

  1. Your libraryYou teach it
  2. Your agentIt answers
  3. Your clientsIt asks you when it isn't sure

Illustration: a consultant's library full of books on the left, an owl agent at a lectern in the middle, and three client houses on the right. Answers travel to the clients; a question mark flies back to the consultant's inbox.

How it works

Three steps, then it runs by itself

You stay the expert. agentor keeps your know-how ready and hands the right part of it to your client's AI, every time they ask.

  1. Teach it

    Give your agent a name and a voice, then feed it what you know: notes, documents, answers you keep repeating, and where things are. Push it straight from your own files with your coding agent, or type it into the dashboard.

    teach Artur from ./handbook
  2. Invite your clients

    One email per client with everything inside: the address, the steps for their AI tool, the first thing to type. No account, no password, no app to install.

    invite ana@firma.si to Artur
  3. They ask, it answers

    Your client asks in Claude, ChatGPT, Cursor or wherever they work. Your agent finds the passages that answer it, and their AI replies in your agent's voice, citing where each fact comes from.

    Artur, how do I set up the database?

The whole journey, step by step →

Start from a template

Pick your field, skip the blank page

A template fills in your agent's voice, what it covers, what it passes to you and the answering rules for your field. Then it gives you a checklist of the questions your clients are likely to ask, so you know exactly what to teach it.

  • Technical consultant

    For software, devops and database consultants who keep their clients' apps running.

    25 questions your clients are likely to ask, in 9 sections

  • IT support / MSP

    For IT support providers who look after a company's devices, accounts, email and network.

    21 questions your clients are likely to ask, in 8 sections

  • Accounting & tax

    For accountants and tax advisors who keep small businesses' books, payroll and filings in order.

    20 questions your clients are likely to ask, in 8 sections

  • Legal advisor

    For lawyers and legal advisors who help businesses with contracts, company matters and compliance.

    20 questions your clients are likely to ask, in 8 sections

  • Marketing & growth

    For marketing and growth consultants who run brands, campaigns, content and analytics for clients.

    18 questions your clients are likely to ask, in 8 sections

  • Sales coach

    For sales coaches and consultants who train teams on pipeline, discovery, objections and closing.

    18 questions your clients are likely to ask, in 8 sections

  • HR & people

    For HR consultants and people partners who run hiring, onboarding, policies and reviews for companies.

    19 questions your clients are likely to ask, in 8 sections

  • Customer success / product support

    For product and customer success teams who help customers get started and get unstuck.

    19 questions your clients are likely to ask, in 8 sections

  • Business / management consultant

    For management consultants who run strategy, process and change projects with leadership teams.

    18 questions your clients are likely to ask, in 8 sections

  • Coach / trainer

    For coaches and trainers who run programmes, sessions and courses for people or teams.

    18 questions your clients are likely to ask, in 8 sections

  • Start from scratch

    A blank agent: you write the voice, scope and rules yourself.

    14 questions your clients are likely to ask, in 6 sections

Answer the checklist in the dashboard, or let your coding agent fill it from your files: teach Artur from ./docs using the Technical template outline

A sample exchange

Answers your clients can trust

Every answer comes from your know-how, with the source next to each fact. Nothing invented, nothing guessed.

Ana's AI, connected to Artur

Artur, how do I set up the database?

Ask Artur 3 passages confidence high

Here is how Maja sets it up for your project:

  1. Create the database in the shared account, named after the project K-17
  2. Turn on daily backups before anything else K-17 K-4
  3. Put the connection details in the team vault, never in a chat K-9

Want me to walk you through the backup settings?

Can we move our hosting next month?

Ask Artur 1 passage not sure

That isn't in Artur's know-how yet, so I won't guess. I've passed your question to Maja; you'll get her answer by email, and here too, next time you ask.

When it isn't sure

It asks you, then it remembers

An agent that admits what it doesn't know is one your clients keep using. Every gap you fill makes the next answer instant.

  1. Not sureIt says so

    The question isn't covered by your know-how. Your agent tells the client you'll answer, instead of guessing.

  2. Your inboxYou hear about it

    One short email with the open questions, and an inbox in your dashboard: who asked, what they asked, what your agent found.

  3. Their answerYou reply once

    Type the answer in the dashboard or tell your coding agent answer Q-12: …. Your client gets it by email and in their AI.

  4. It learnsIt's covered from now on

    Your answer joins the know-how, so the next client who asks the same thing gets it straight away.

And round it goes: the more your clients ask, the less often you are needed.

Learns by itself

Point it at a folder once. It keeps up.

Your agent can watch a project folder or git repository on your computer. New and changed docs become know-how, deleted files are retired, and what clients keep asking that it can't answer turns into a short list of what to write next.

One line, once

Click Watch a project on your agent's Learning page and paste the line it gives you in that folder. It shows exactly which files it would read, asks once, and keeps running in the background.

You approve what's new

New files wait for your OK in the dashboard ("12 new, 3 changed"); changes to files you approved update by themselves. Prefer to see everything first, or nothing at all? Pick the policy per folder.

Only what's meant to be read

Docs, READMEs, runbooks, decision records, API specs. Never .env files, keys, credentials, node_modules or build output, and the server still never reads your disk.

The one lineyour dashboard fills in the code
npx -y --package=https://agentor.si/dl/agentor-watch-launcher.tgz agentor-watch setup --pair K7QD-92MX

Every Monday you get a short mail: what your agents learned that week, and what clients asked that they couldn't answer yet. How watching works →

Two sides, one agent

Built for you and for the people you advise

For consultants

  • Your agent, your name for it, your tone, your topics.
  • Teach it from your own folders in one sentence to your coding agent — connecting it takes one line (how).
  • See every question your clients ask, and how sure it was.
  • Answer the gaps once; it remembers.

For their clients

  • One invitation email with everything in it.
  • Ask in the AI tool you already use, any time of day.
  • Answers with sources, in plain words.
  • When it doesn't know, your consultant answers you personally.

Pick one of eight faces for your agent. The name is yours: Artur, Vera, Doc, whatever your clients will remember.

No card

It’s free

Create your agents, teach them, invite your clients. Sign in with your email; no password, no card.