Algorithma · We put AI to work

Customer stories

A shared platform. Real work in production.

See how customers use AOS and work with our engineers to bring agents into their operations.

9 agents

in production across five brands, in under four months

E-commerce & Retail

“Our growth strategy is built on entrepreneurship and autonomy, but scaling technology across a multi-brand group requires a shared operational foundation. Sponsoring the initial setup centrally gave us a repeatable playbook, allowing every brand to move fast on a common platform without sacrificing local ownership.”

Gustaf ÖhrnCEO, BHG Group

Read the case study

See all case studies

Meet our agents

65+ agents in production.

Every agent has a job description, tools, a model and rules. Here are 20 of them.

1 of 20· Choose an agent

Customer service, mail, chat and phone

Live in production · Retail · 42 180 conversations / 30 d

Job description

Answers mail, chat and phone from the knowledge base and order data, and hands over what it shouldn't decide.

Tools

Zendesk

Dixa

Freshdesk

Fluent Commerce

Ongoing WMS

nShift

Klarna

Twilio

Models

Claude

OpenAI

Gemini

Mistral

Rules

Never shares card numbers or personal data
Refunds above the policy limit go to a person

AOS Control· overview

Past 30 days

Conversations

42 180

Resolved without a person

82,7%

First reply

Volume by week

What customers contact about

Where is my order11 840
Product questions8 620
Returns and complaints5 940

Peter Wahlgren Chairman & CFO
Simon Althoff AI Engineer
Marcus Banér AI EngineerSimon Lanngren AI EngineerEmely Wiegand AgentOps Manager
Peter Wahlgren Chairman & CFOKristofer Kaltea COOAlexander Ekdahl CTOViktor Ekberg CCO
Jonas Röst AI EngineerVilma Ylvén AI EngineerMarcus Banér AI EngineerSimon Lanngren AI Engineer
Felix Baart AI EngineerHampus Hallman AI EngineerSimon Nygren AI EngineerOliver Johansson AI EngineerDaniella Zhou AI Engineer

Leadership, engineers and engagement leads, in Stockholm and Gothenburg.

Meet the team How we work

Integrations

Agents built into the stack you already run.

We build the agents. AOS runs them in your cloud, on your models, connected to your systems.

Qlik

Snowflake

Ongoing WMS

Slack

Fortnox

Fluent Commerce

GitHub

Kubernetes

DocuSign

Elastx

Dynamics 365

Google Gemini

Mistral

Shopify

Jira

Intercom

Quinyx

On-premises

Microsoft Azure

OpenAI

ServiceNow

Freshdesk

Gmail

Cohere

Outlook

Salesforce

AWS

HubSpot

IBM Maximo

Twilio

Rillion

Visma

Anthropic Claude

Google Cloud

Berget AI

Klarna

DeepSeek

Confluence

Ingrid

AWS Bedrock

SAP

Microsoft Teams

nShift

Meta Llama

PostgreSQL

Google Drive

SharePoint

Zendesk

Power BI

Dixa

Databricks

NVIDIA NIM

7clouds & platforms10model providers35business systems

Ask about your stack

FAQ

Before you get started.

Can our team build on AOS?: AOS provides reusable components for building and managing agents. Our engineers help your team get started with the first workflows.
What do your engineers do?: We work with your team to define the workflow, connect systems, build the agent and test it before launch.
Where is AOS deployed?: AOS can be deployed in your own supported environment. We confirm hosting, model endpoints and data flows with your team.
Who manages agents after launch?: Operational responsibilities are agreed with your team before launch.
Can we change model providers?: Swap the model without rebuilding the agent. Its job, tools and rules stay the same.

The operating layer and agents for enterprise AI.

A shared platform. Real work in production.

65+ agents in production.