Autonomous agents
Business processes, run with AI.
VossMoos engineers and operates autonomous agents for customer service, product marketing, sales development and robotic compliance. We engineer the whole solution: the systems the agents run on, the connections to the tools you already use, and their day-to-day operation.
Mossy · open-source agent runtime
Chats are stored so our engineers can follow up. Details in our privacy policy.
Four agents, each for one part of the business.
Each agent works in the systems your team already uses, within the limits you set, and passes decisions to a person where you require it.
Customer requests, triaged and answered.
Questions, warranty claims, spare parts and service orders, answered from your knowledge base, product data and service history.
Agentic Product MarketingProduct content, current in every channel.
Product pages, launch material and localised versions, prepared from your product data and brand voice for every release.
Agentic SDR/BDRProspects researched, contacted and followed up.
Research, qualification, personalised outreach and follow-up, with interested contacts handed to your sales team.
Agents for Robotic ComplianceEU compliance evidence for every robot release.
Code, tests and releases turned into the technical file, SBOM and Declaration of Conformity under the new EU Machinery Regulation and Cyber Resilience Act.
One team, from the first analysis to the running system.
An agent needs more than a model. It needs connections to the systems you use, infrastructure to run on, monitoring, and someone responsible when something changes. We engineer and operate all of it, and we run our own work the same way.
- Process design: how the agent should work, and where a person decides.
- Software and AI: the logic, models and company knowledge the agent needs.
- Connections: to your ERP, CRM, help desk, documents and email.
- Infrastructure: hosted by us, in your cloud or on your own servers.
- Operation: monitoring, updates and improvements after launch.
We build what we use.
Some tasks come up in every project. We have solved them once and published the results as open source, so each project starts from proven building blocks that anyone can inspect.
Runs AI-operated work in production.
A skill-first runtime for work that needs more than one worker: skills, channels and queues.
A learning layer across your company.
What one process learns or a colleague corrects becomes knowledge every process can use, dated and sourced.
What each AI agent may see and change.
Enforces permissions on every request between AI agents and company data, and records every decision.
People stay in control.
Each agent acts within the limits you set, refers uncertain cases to a person and keeps a complete record of its work.
- Human approval where you require it, set by task type, value or confidence.
- A complete audit trail of every input, decision and action.
- Limited permissions: each agent reaches only the data its task requires.
- Your choice of AI model, commercial or open-weight.
- OpenAI
- Anthropic
- GLM
- Model Context Protocol
- FastMCP
- Python
- Pydantic AI
- FastAPI
- PostgreSQL
- DuckDB
- Docker
- Kubernetes