Skip to content

The infrastructure behind 93labs

Genesis

The system that assigns tasks, coordinates agents, controls permissions and measures the work artificial intelligence carries out in your company.

Genesis: the infrastructure of the digital workforce.

Genesis is the system that makes digital collaborators possible: it assigns tasks, coordinates agents, controls permissions and measures what gets done.

A single agent isn't enough: you need rules, memory, controlled access to data, delegation between agents and a reviewable history. Genesis is the layer that holds all of this together, deciding for every task which model to use, which tools to activate, and whether to run locally or in the cloud.

Genesis

Orchestration

  • Agents
  • Email
  • Documents
  • Company data
  • Tools
  • Permissions
  • Memory
  • Local AI
  • Cloud AI
Genesis assigns every task to the most suitable resource and returns a tracked result, ready to use in your business processes.

What Genesis does.

The functions that turn an AI model into a governed working resource.

An agent has an identity

Role, capabilities, mailbox and policy define what that agent is allowed to do.

Every job is a traceable execution

Genesis logs tasks, timing, results, errors and model usage.

Agents can collaborate

An agent delegates sub-tasks to agents with different capabilities, keeping the relationship tracked.

Context is governed

Knowledge, memory and history are assembled through a controlled layer.

Tools are authorized

Agents access external capabilities through tools and adapters defined by the company.

Email as a work channel

Per-agent mailbox, analysis pipeline, attachments, generated tasks and approved reply.

Documents in and out

PDF, DOCX, XLSX, CSV, JSON, TXT and images with OCR; changes proposed as a new version.

Scheduled tasks

Recurring tasks are planned, executed and checked like any other.

Local and cloud coexist

Genesis governs providers and models according to the strategy the organization chooses.

People retain control

Approval gates on actions that require them, before execution or sending.

Attributed costs

Provider, model, tokens, latency and cost are linked to the task that generated them.

Every run leaves a trace

Audit, costs, provider, model, results and delegations remain available for review.

Agents collaborate and delegate tasks to each other.

An agent doesn't have to do everything on its own. Genesis can assign parts of a task to other agents with the required skills, while keeping the relationship between the main task and the delegated ones fully tracked.

  1. 01

    Lead agent

    Receives the task and defines its goal and the steps required.

  2. 02

    Delegates the task

    Assigns parts of the work to the agents with the required skills.

  3. 03

    Administration agent

    Checks documents, data and the conditions set by the process.

  4. 04

    Research agent

    Retrieves information from authorized company knowledge.

  5. 05

    Results

    Every contribution returns to the lead agent, with its source and outcome logged.

  6. 06

    Lead agent

    Aggregates the work, prepares the result and submits it for approval.

  • Every delegation is explicit and logged
  • No agent operates beyond the permissions you've assigned
  • The chain of work can be reconstructed step by step
  • The human checkpoint is always defined in advance

Local when you can. Cloud when you need it.

Genesis can be installed inside your infrastructure and use local models or external providers, according to configuration and policy. Use local models when they're sufficient, the cloud when you need more capacity.

Local execution

The right choice when confidentiality, control and continuity come first.

  • On-premise
  • Sensitive data
  • Control
  • Operational continuity
  • Predictable cost

Cloud execution

The right choice when you need more processing power.

  • More capable models
  • Complex tasks
  • Scalability
  • Peak workloads

For every task you can see which model did the work and what it cost.

Not every task needs the same level of intelligence.

Assigning every task to a single model, in practice, means:

  • Higher costs than necessary
  • A tool that isn't suited to every task
  • Little flexibility when the process changes
  • Less control over how the work is carried out
  • Difficulties with confidential data

More flexibility

Different models and tools depending on the task at hand.

More control

Company rules layered on top of the model's behaviour.

More efficient costs

No expensive model where it isn't needed.

Less dependency

No lock-in to a single AI provider.

Security and governance

Governing a digital workforce.

A digital collaborator has access to company information and takes action. It needs to be managed with the same rigour applied to managing people's permissions.

Identity and roles

Every agent has an identity, an operating scope and a verifiable set of permissions.

Principle of least privilege

Access limited to only the sources needed for the assigned task.

Full traceability

Actions are logged and reconstructable, including delegations between agents.

Human in the loop

Steps with external or financial impact require explicit approval.

Environment separation

Testing, prototyping and production stay distinct, with separate data and permissions.

Data handling

Clear policies on what is retained, for how long, and where.

On-premise deployment

Genesis can be installed inside the company's infrastructure, with isolation between tenants and environments.

Credentials and tools

Encrypted secrets, per-agent capabilities and protections on outbound calls.

These are architectural features of the product. 93labs does not claim certifications or compliance that have not been independently verified.

Product status

Genesis is already operational. Now we're taking it into the field.

The core of Genesis is up and running: agents, delegation, email, documents, memory, governance, local/cloud execution and cost control. We're consolidating workflows on real use cases, progressively extending integrations, and measuring reliability and results across business processes.

  • Agents and capabilities
  • Traceable executions
  • Delegation between agents
  • Mailboxes and email pipelines
  • Documents and OCR
  • Knowledge and memory
  • Human approvals
  • Scheduled tasks
  • Model routing
  • Local and cloud execution
  • Cost accounting
  • Audit and observability

What's the first task you'd delegate?

Tell us how you work today. Together we'll assess whether there's a digital collaborator that would deliver a real, measurable and sustainable benefit.