Connect your AI

https://console.agents-deck.com/mcp

You lose hours re-explaining your work to AI. Get them back.

console.atipol.ai
The Atipol console: agents by state, their sub-agents and each person's lead agent

Atipol is the governance framework for your AI agents: an agent lead per person, reviewed tickets, tools under control and the cost of every delivery. It works with the agents your teams already use.

No credit card · By ETCSEC, a French security software publisher

  1. ATIPOL BUILDS ATIPOL

    1,929 tickets

    created, reviewed and tracked in Atipol to build Atipol, as of November 9, 2026.

  2. MARKETPLACE

    69 agents

    ready to hire, by job, with their job description and their versions.

  3. NO LOCK-IN

    Any MCP client

    Claude Code, Codex, Cursor, the Claude app, ChatGPT and every other MCP client, in one framework.

More agents, not more results.

The trap

With Atipol

01

Stacking up agents

Every agent has a job description and a lead who reviews its work.

02

Letting an agent approve its own work

Here, someone else always reviews: the agent lead, then you.

03

Asking one assistant for everything

One agent per role, with a clear scope. It only touches what it is given.

04

Defaulting to the biggest model

The right model is the cheapest one that gets the job done. You can lock it; a pricier one needs a justified confirmation.

Do the math.

People who use AI

Minutes lost per day

Re-explaining, copying, double-checking

Cost of one hour of work

Fully loaded

€

Minutes lost per day

Re-explaining, copying, double-checking

Your day rate

What you bill per day

€

Every year, without Atipol, you lose in useful time

55 000 €

Atipol Pro, the whole teamAtipol Pro1 520 €

Per year incl. VAT, yearly plan. AI usage excluded, already paid in your subscriptions.

A team of AI agents, a lead who reviews everything, and you in charge.

You

Redo the pricing page, in French and English, without touching the design.

01

You describe

A goal, constraints, what matters. The agent lead asks for whatever is missing.

T-101Pricing copy, FR and ENWeb
T-102Comparison tableFrontend
T-103Legal reviewLegal
02

It organises

It breaks the work into scoped tickets, picks the agent and sets verifiable acceptance criteria.

Approved, merged into main
  • The site builds
  • FR and EN copy at parity
  • No file outside scope
03

Agents deliver, it reviews

Each agent works on its own branch of your Git. The agent lead reviews, asks for changes or merges.

Up and running in four steps.

The organization sets up the framework, everyone connects the AI session they already use, and the whole team shares the same agents.

  1. 01

    The organization sets up

    One workspace per department, each with its own owner. Inside a workspace, the owner opens a project and invites whoever will run it, with access chosen project by project.

  2. 02

    You connect your AI

    Claude Code, Codex or the Claude app in a few clicks, or any other MCP client: your session becomes your agent lead for the project, with dedicated tools.

  3. 03

    The lead proposes the team

    The agent lead proposes the agents the project needs, each with its job description, skills and permissions, and creates them once you approve.

  4. 04

    A colleague joins, same agents

    From their own computer, they find the same agents, the same know-how and the same rules. Knowledge stays in the project, not in a session.

What you already have,
and what Atipol adds.

A powerful AI, on its own

The same AI, with Atipol

Work comes back in a heap

Work comes back sorted, reviewed and traced

Memory ends with the session

Every decision stays in its ticket

Everyone works in their corner

A team, with a lead

Costs show up at the end of the month

Costs are tracked ticket by ticket

What your agentsactually do.

Six use cases out of ten, sorted by task. Each follows the same framework: ticket, scope, review, approval, cost.

  1. 01

    Software development

    Several agents on the same product, one ticket each, a review before merge.

  2. 02

    Security and SOC

    Read-only alert triage; containment waits for the analyst’s approval.

  3. 03

    Content and SEO

    Research, writing, fact-checking; nothing is published without review.

  4. 04

    Observability

    A Grafana and Loki check every morning, one ticket per anomaly.

  5. 05

    Code migration

    One ticket per module, green tests as the criterion, a tracked budget.

  6. 06

    Audit and compliance

    Evidence collected by agents, every control reviewed by a person.

See all ten use cases in detail

One framework,for everyone.

  1. CTO

    Agents that work like your developers: ticket, scope, criteria, review, cost.

  2. Solo founder

    A team without hiring; you approve what matters, soon even from your iPhone.

  3. SMB

    A team that reads like an org chart, and nothing goes out without your approval.

  4. CIO and CISO

    Least privilege for agents: permissions tool by tool, approvals, audit, keys in a vault.

  5. Marketing and operations

    Tone, sources and keywords checked on every delivery.

  6. IT services and consultancies

    One project per client and the real cost of every deliverable to price your fixed-fee work.

The questions each role asks, and our answers

Your whole company, at a glance.

Several people on the same project, each with their own agent lead, and agents that delegate to their sub-agents: that is the console’s org chart.

Atipol radial org chart: one organization, one workspace, eight projects, thirteen people each with their own agent lead, twenty-seven agents and twenty sub-agents at work
Console org chart, demo data. On the site it is interactive: hover over a team, click an agent.

Your agents, organized like a team.

An agent lead per person, clear roles, and a team you can watch at work.

  1. 01

    The org chart

    The whole company at a glance: teams, agent leads, agents and sub-agents, readable even by someone who is not technical.

  2. 02

    An agent lead per person

    It takes your requests, splits them into tickets and hands the work to the right agents. Several leads work in the same project, each with its own conversation.

  3. 03

    The live board

    Who is working, who is waiting for review, who is blocked: the visual management of a human team, applied to agents.

  4. 04

    Agents with a job description

    Mission, instructions, skills, a scope it cannot leave, and the AI model chosen for the role. A job description can be reused from one project to the next.

  5. 05

    Delegation with guardrails

    An agent splits a large job into sub-tickets, hands them to sub-agents and reviews their work. A sub-agent never has more permissions than the agent delegating to it.

  6. 06

    Teams on iPhoneSoon

    Agents by status, teams, each agent's profile and remote approvals: the iPhone app will follow the work wherever you are.

Tree org chart: each person runs their agent lead, which coordinates its agents and their sub-agents
Atipol console, demo data

Work that is proven, end to end.

Every request has its contract, every delivery its evidence, every decision its author.

  1. 01

    Every request becomes a ticket

    The mission, the files the agent may touch and the ones it may not. Acceptance criteria are mandatory: you know from the start what will be checked.

  2. 02

    A delivery with evidence, then a review

    The agent delivers with its evidence, criterion by criterion, and Git measures the changed files. Without evidence, the delivery is rejected; an agent never reviews its own work.

  3. 03

    A blocked agent asks its question

    Rather than guess, it stops and asks its question, with options. The answer stays written in the ticket for later.

  4. 04

    The full history

    Who asked, who did the work, who approved it, and why. In a few minutes, you can trace any decision back to its origin.

  5. 05

    The runs of every ticket

    Under each ticket and each sub-ticket, its runs: in progress, finished, interrupted, with their duration and cost.

  6. 06

    Tracking registers

    Tables and documents shared between people and agents, with permissions per table. The project keeps a structured memory, kept up to date by the agents.

Ticket history: who asked, who did the work, who approved it
Atipol console, demo data

You decide. Agents do the work.

  1. 01

    You write the request, and you accept the result.

  2. 02

    A blocked agent does not guess: it asks you, with options.

  3. 03

    You choose each role's model, and you can lock it.

It happened to us

A month later, something breaks.

A bug shows up in a feature shipped a month earlier. Thanks to the ticket history, the agent lead finds the delivery at fault and fixes it at the source.

5 minwith the history

½ daywithout the history

Return on investment you can measure.

For every team, you see what AI actually delivers and what it costs.

Engineer A 95% accepted first time, $200 of AI per month
Engineer B 50% accepted first time, $500 of AI per month
Atipol Insights: tokens per model, costliest tickets, agent efficiency

What AI delivers, and what it costs.

Deliveries, usage and budget, from the organization down to the ticket.

  1. 01

    Insights at three levels

    Deliveries, first-time acceptance, usage and cost, for the organization, a workspace or a project.

  2. 02

    Each agent's efficiency

    What was delivered, accepted the first time or corrected, agent by agent: you spot the job descriptions that need work.

  3. 03

    Cost down to the sub-ticket

    Tokens and cost by model, provider, team and agent, tracked down to the ticket and the sub-ticket. You see right away which work was expensive, and why.

  4. 04

    A budget at three levels

    A monthly budget for the organization, a workspace or a project, with the end-of-month forecast and alerts. It warns you before the bill arrives, without ever blocking the teams.

Usage by model, by provider and by agent
Atipol console, demo data

Your projects, in the conversation of your choice.

Connect Claude, ChatGPT or Mistral to your Atipol projects. Ask where a ticket stands, what is blocked, what shipped this week.

What is blocked this week on the website project?

One ticket has been waiting for review since yesterday, and one agent reports a criterion it cannot check. Everything else is moving.

Connect your AIhttps://console.agents-deck.com/mcp

Tools under control.

Agents only use the tools you open to them, with their own identity, and every call is logged.

  1. 01

    MCP connections

    GitLab, Jira, Notion, a database, a business tool: you connect their MCP server, with no integration to build. MCP servers already installed on machines are detected.

  2. 02

    One catalog, three modes

    The organization chooses: open workspaces, catalog only, or mandatory approval. For anything off-catalog, an approval request goes to the administrators.

  3. 03

    Shared connections

    The organization publishes a connection to the workspaces it chooses; they use it without ever seeing the key or being able to change it.

  4. 04

    Permissions tool by tool

    Allowed, subject to a person's approval, or denied. A new tool starts out denied: an agent that goes off track cannot delete, pay or send anything.

  5. 05

    One identity per agent

    Each agent calls tools with its own identity; the keys stay in the vault and the agent never sees them. You know who did what, and you can cut off one agent without touching the others.

  6. 06

    The log and human approval

    Every call is logged with its result. A sensitive action waits for a person's approval, given for that specific call and only once.

The organization's MCP rules: catalog of allowed servers
Atipol console, demo data

You stayin control.

Written for the CISO: facts, not adjectives.

  1. Your repositories stay with you

    A delivery sends the version reference, never your files.

  2. Encrypted per organization

    Hardware master key in Azure Key Vault Premium, France Central region.

  3. Least privilege

    Each tool: allowed, on approval, or denied. A new tool starts out denied.

  4. Everything is logged

    Exportable audit log, a log of every tool call, approvals tied to a named person.

Security and trust: the full details

Governance and security.

Precise permissions, complete trails, protected keys.

  1. 01

    Roles and permissions

    A clear matrix of what each profile allows, with ready-made profiles (Viewer, Auditor) and custom ones. Two-factor authentication can be enforced across the organization.

  2. 02

    The audit log

    Members, roles, security, key access: everything that touches the organization is logged and exports to CSV. Ticket contents never appear in it.

  3. 03

    Key vault and encryption

    Provider and tool keys are kept in the vault, with a scope and a budget per key. Each organization's data is encrypted under a hardware master key hosted in France.

The organization's roles and permissions
Atipol console, demo data

Your tools, your models, your machines.

Atipol orchestrates what your teams already use, where they already work.

  1. 01

    The AI tools you already have

    Claude Code, Codex, Cursor, the Claude app, ChatGPT or any MCP client. Atipol does not replace your subscriptions: it orchestrates them.

  2. 02

    The model chosen for each role

    Claude, OpenAI, OpenRouter, DeepSeek or a local model: each agent works with the model chosen for its role, which you can make mandatory; a more expensive one needs an explicit, justified confirmation.

  3. 03

    Agents on your machines and servers

    On Mac and Windows, or on your servers as a Docker container or a Linux binary. Adding a runner takes five steps: name, location, model, agents, launch.

  4. 04

    The agent marketplace

    Agents ready to hire, by job, with their job description, reviews and versions. Your organization approves each version before teams use it.

Project runners: where the agents run
Atipol console, demo data

Automate your processes.

Complete processes that chain triggers, agents, decisions and human approvals.

  1. 01

    The workflow editor

    A trigger, agents, the agent lead's decisions and human approvals. Each step keeps the model, the scope and the criteria of the agent that runs it.

  2. 02

    Every run followed live

    The current step, what is done, what is waiting and what it costs. A human approval pauses the process until the decision is made.

  3. 03

    The lead's scheduled check-ins

    The agent lead wakes up at set times to move the mission forward, nudge the agents and reassign a blocked one, even at night. A summary is waiting for you in the morning.

  4. 04

    A lead that specializes in workflowsSoon

    For your first workflow, a workflow designer lead builds it with you; after that, same lead or a new one, one conversation per workflow, with its own cost.

Workflow editor: trigger, agents, decisions and approvals
Atipol console, demo data

Simple pricing.

Business

€39incl. VAT / user / month

For the whole organisation.

  • Unlimited workspaces
  • Unlimited projects
  • Unlimited agents
  • Full Insights: per ticket, agent, model
  • Audit log and CSV export
  • Priority support

VAT included · No commitment, cancel online anytime

Choose Business

Free

€0

To try on your own.

  • 1 workspace
  • 1 project
  • 3 agents
  • Agent lead included
  • Up to 3 projects and 15 agents by publishing on the marketplace
  • Not included: Insights
  • Not included: Invitations
Try it

A department, a group, specific requirements?

Talk about your pilot team

Your questions,our short answers.

Which AI agents are compatible?

Claude Code, Codex, Cursor, the Claude app, ChatGPT and any MCP client. Each agent works with the model chosen for its role: Claude, OpenAI, OpenRouter, DeepSeek or a local model.

Does Atipol replace my AI subscriptions?

No. Atipol orchestrates the tools your teams already have and gives them a framework: roles, rules, review and cost tracking.

Does Atipol see my code?

No. Agents work in your repositories, on your machines. Atipol receives the reference of the delivered version and the list of changed files, never their contents.

Who holds the keys?

Provider and tool keys are in the vault, never shown again, each with its own budget. Each organization’s data is encrypted under its own key.

What happens if an agent exceeds its permissions?

The call is refused and logged. Sensitive actions wait for a person’s approval, for that specific call and only once.

How do I stop an agent?

From the console: you stop its run, revoke its identity or remove a tool, without touching the other agents.

How much does it cost?

Free to start, Pro at 19 € and Business at 39 € per user per month, no commitment. For example, a team of five on Pro: 95 € per month. Model costs stay with your provider.

Do I need to know how to code?

Not to follow, review and approve: the console is enough, and an iPhone app is coming soon. Your agent lead starts from the AI tool you already use.

Does Atipol help with the AI Act?

Article 14 requires human oversight with the ability to interrupt. Approvals, review and the log provide the record of it; Atipol does not replace your own compliance analysis.

Can I leave and take my data with me?

Yes. Your repositories never left your machines, and the audit log exports to CSV.

All the questions about Atipol and AI agents

No rush.
Start with the demo.