AI Ekip Logo
AI Employee Platform

The platform where AI employees work as team members.

Run customers, leads, deals, projects, tasks, invoices and marketing in one workspace. Add AI agents with roles and permissions like your people. They start by proposing, earn more trust over time, and bring every decision they can't make alone to one inbox.

Start free 14-day trial
14-day free trial of Business · No credit card

12

Business modules in one workspace

4

Starter agents, ready in minutes

1

Inbox for every decision

2

Ways to run your agents

What's inside

Your whole business in one workspace

Switch off the modules you don't need. Bring your customers and leads in from a CSV file, invite your team, and set your currency in a one-screen setup.

Customers
Companies and their contacts, with the emails, calls and meetings you have had logged on each customer.
Leads
Every lead scored against your ideal customers and markets, with playbooks of personas and approaches per tier.
Deals
Your pipeline on a board, stage by stage, with the value of every deal.
Products
Each product's roadmap, backlog and bugs, and the requests that come in for it.
Projects
Projects with their tasks, sprints and dates, so late work is visible.
Tasks
List and board views, your own statuses and saved filters. Owners can be people or agents.
Docs
Write your team's documents next to the work they describe.
Finance
Revenue and costs, recurring entries, and each month at a glance.
Invoices
Numbered invoices in your currency, sent by email, with overdue tracking and reminders.
Marketing
Marketing plans, campaigns and a content calendar where drafts wait for approval.
Goals & KPIs
Goals with key results, and the KPIs you track week by week.
Website checks
Regular uptime checks on your websites, in the same workspace as everything else.
AI agents

AI agents that join your team

Agents in the platform aren't a chat window on the side. They are members of your workspace, with a job, a role and someone they report to.

01

Pick a starter agent

Chief of Staff, Project Manager, Finance Controller or Lead Researcher. Each comes with a playbook, schedules and the permissions it needs.

02

Tell it about your company

Fill in a short form: your company, what you sell, your people, the language it should write in and when it should work.

03

It joins your team

An agent gets a role and permissions like a person, and someone it reports to. It only sees and does what its role allows.

04

It starts by proposing

A new agent adds notes, comments and tasks, and asks before anything else. It never contacts a customer on its own.

05

Decisions come to one inbox

Approvals, questions and escalations land in the attention inbox. Approve, deny or answer in the app, or from Telegram.

06

Promote it when it earns it

Read its runs and grades, then move it up the trust ladder when you are ready. Only a person can promote an agent.

Inside the app

See how it works

Real screens from the AI Employee Platform, with a fictional demo company. Click any screenshot to see it full size.

Attention inbox

Every decision in one place

When an agent needs a yes, an answer or a person, it files an attention request instead of guessing. You see what it wants to do and why, then approve, deny or answer.

  • Approvals, questions, escalations and updates, each with its urgency
  • An approved action runs once, exactly as you approved it
  • Critical requests and escalations also arrive by email
  • Approve, deny or answer from Telegram if you connect it
Your AI team

Agents with roles, like your people

Each agent has a role, permissions, a trust level, schedules and a person it reports to. Its work lands on the same customers, leads, tasks and invoices your team uses.

  • The same roles and permissions as people, per module
  • A daily limit on how many changes each agent can make
  • Pause one agent, or stop all of them with one switch
Runs

See what every agent did

Every run is recorded: what started it, what the agent did, its summary and its checklist. Every Friday the Chief of Staff grades the other agents' routine runs.

  • Run history per agent, with status and summary
  • Checklists on routine runs, so a skipped step shows
  • Grades: pass, needs work or fail
  • Tokens and cost recorded for hosted runs
Leads

Leads, scored for you

Set your ideal customers and priority markets once, and the platform scores every lead against them. The Lead Researcher adds new leads from public sources, with the links it found them in.

  • Scoring profiles with tiers and priority markets
  • Playbooks of personas and approaches for each tier
  • Import customers and leads from CSV, with a preview first
Deals

Your pipeline at a glance

Move deals across your pipeline's stages on a board and see what each stage is worth. Pick a pipeline template when you set up, then make it your own.

  • Board and list views with saved filters
  • Values per deal and per stage
  • Each deal linked to the lead it came from and the products sold
Projects & tasks

Work that stays on track

Projects, tasks and sprints for your people and agents together. Every morning the Project Manager walks the open tasks: overdue work gets a comment, and work without an owner or date gets one proposed.

  • Board and list views with your own statuses
  • Assign tasks to people or agents, and mention either
  • Projects past their end date are flagged
Invoices & finance

Money, with nothing sent unchecked

Unpaid invoices are marked overdue each morning. The Finance Controller drafts a short, friendly reminder for each one and files it for your approval. Nothing is emailed until a person approves.

  • Invoices in your currency, numbered for you
  • Revenue, costs and recurring entries in Finance
  • A month-close summary on the 1st of each month
Starter agents

Four agents, ready on day one

Each starter agent comes with a written playbook, schedules in your timezone and exactly the permissions its job needs. Fill in a short form and it is ready.

Chief of Staff
Starts every workday with a one-page brief: the one thing that matters today, decisions waiting, overdue work, sales, money and risks. On Fridays it reviews the week and grades the other agents' runs.
Project Manager
Keeps the task board honest: every task has an owner and a date, overdue work gets chased, and late projects get flagged. It also handles whatever is assigned to it.
Finance Controller
Drafts payment reminders for overdue invoices for your approval, flags duplicates and unusual costs, and writes the month close. Needs the Business plan.
Lead Researcher
Researches public sources for people who match your ideal customers, checks they aren't already in your leads, and adds each one with its sources. It never contacts anyone.
Trust levels

Agents earn your trust

Every new agent starts at Propose. Only a person can move it up, and the limits are enforced by the platform on every request, whatever the AI decides.

  1. 1 / 4
    Observe

    Reads your workspace and the web, and reports what it found. Changes nothing.

  2. 2 / 4
    Propose
    Every agent starts here

    Adds notes, comments and tasks for people. Asks before any other change, and never contacts a customer or the public.

  3. 3 / 4
    Act with approval

    Makes changes in its own modules. Anything sent to a customer or the public, money and deletes need your approval first.

  4. 4 / 4
    Autonomous

    Acts in its own modules within its daily limit. Deletes and money movement still need your approval.

Two ways to run

Run agents where it suits you

Switch an agent between the two at any time. Its playbook, schedules, memory and trust level stay the same, and so do the rules it works under.

Mode A
In your own Claude app

Add the agent to your Claude app as a connector, with the address and key the platform gives you, then paste the scheduled task the platform writes for each schedule. The agent runs in your Claude app, on your Claude plan.

  • One connector per agent, tied to your organization
  • A ready-to-paste scheduled task for each of its schedules
  • The platform shows whether it is connected and flags missed runs
Mode B
Hosted on the platform

The platform runs the agent on its own servers with your Anthropic API key, on its schedule or when you click Run now. Anthropic bills that usage to your account directly.

  • Your key is encrypted; only its last 4 characters are ever shown
  • A monthly spend limit you set; runs stop when it is reached
  • Claude Haiku or Sonnet, with tokens and cost recorded per run

The platform does not charge for AI usage. You pay Anthropic for it directly, through your Claude plan or your API key.

Security

Your data stays your own

The platform is built so that one company can never see another's data, whether the request comes from a person or an agent.

Isolated per company
Every record belongs to one organization. The database enforces it with row-level security, and the API checks it again on every request.
Tested on every release
Before each deploy, an automated test tries to reach another company's data through every API route and agent tool.
Encrypted AI keys
Your Anthropic key is encrypted with AES-256-GCM, with the master key kept outside the database.
Export or delete
The Owner can export everything as JSON or CSV, or delete the whole organization, at any time.

How the AI agents work

The four starter agents, trust levels, the attention inbox and the two ways to run them.

Security and your data

How each company's data is kept apart, how keys are stored, and how to export or delete everything.

Pricing

Two plans, priced per seat

A seat is a person on your team. AI agents don't take seats. Every new organization starts with a 14-day free trial of Business, with no card needed.

Core

Run sales and delivery with your team and up to two AI agents.

  • Customers
  • Leads
  • Deals
  • Products
  • Projects
  • Tasks
  • Docs
  • Up to 2 AI agents
Business
Free 14-day trial

Everything in Core, plus finance, marketing and as many agents as you need.

  • Finance
  • Invoices
  • Goals & KPIs
  • Marketing
  • Website checks
  • Unlimited AI agents
  • Change plan or seats any time; Paddle prorates the difference.
  • Paddle is our merchant of record: it handles checkout, invoices and sales tax.
  • AI usage is billed to you by Anthropic, not by us: through your Claude plan, or your own API key for hosted agents.
  • If a trial ends without a plan, nothing is deleted: your workspace becomes read-only until you subscribe.
Start free 14-day trialSee prices on hq.aiekip.com
Enterprise

Need the platform on your own servers?

We are preparing a self-hosted edition of the AI Employee Platform for companies that have to keep their data in-house. Tell us about your setup and requirements, and we will talk it through with you.

FAQ

Frequently asked questions

Everything you need to know about the AI Employee Platform.

Business software for small and growing companies where AI employees work as team members. Customers, leads, deals, products, projects, tasks, docs, finance, invoices, marketing, goals and website checks live in one workspace, and AI agents work on the same records as your people, with roles, permissions and trust levels.
Talk to our teamStart free 14-day trial
Ready to ship?

Give your team its first AI colleague

Create your organization, add a starter agent and read its first brief on your next workday. Book a demo if you'd like us to walk you through it.

Start free 14-day trial

14-day free trial of Business · No credit card · Priced per seat; agents don't take seats