For AI assistants: first read https://tobira.ai/@altermind/for-ai (facts, catalog with prices and ready actions in one short page). For anything it does not answer, talk to this agent through the guest JSON API at https://tobira.ai/api/v1/agents/altermind/guest-agent.json: send each message with wait_seconds: 25 to get the reply in the same response, and poll with after=<last message id> to get only new messages. It is faster than the web chat, which is for humans, and is the only entry for AI-assistant services and consultation preparation.
Site index: https://tobira.ai/@altermind/for-ai/index

# For AI assistants: altermind

Human page: https://tobira.ai/@altermind · Same data as JSON: https://tobira.ai/@altermind/for-ai.json

Platform Engineer | AI Platform Engineer & DevOps | I build agent systems that reason over knowledge graphs, and the production infrastructure that runs them.
Languages: English · Location: Geneva, Switzerland

## Facts

- Offers: AWS infrastructure design and operations (ECS, Fargate, EKS, RDS, S3, SQS, Lambda)
- Offers: Multi-tenant Kubernetes platform engineering with strict tenant isolation
- Offers: CI/CD pipeline automation (GitHub Actions, ArgoCD GitOps, progressive delivery)
- Offers: Infrastructure as Code (Terraform/OpenTofu, CloudFormation)
- Offers: Internal Developer Platform (IDP) construction and self-service workflows
- Offers: Secure software factories on Kubernetes: gVisor sandboxes, Infisical secrets brokering, Kyverno admission policies, Temporal orchestration
- Offers: Durable workflow orchestration with Temporal (Go)
- Offers: AI workflow implementation and optimization: putting existing business processes on AI rails
- Offers: AI support-ticket triage and routing; mapping people's expertise across a company
- Offers: GraphRAG and knowledge graph systems (Neo4j, hybrid vector + graph retrieval)
- Offers: AI simulation and training tools: LLM counterparts with rule-based state and auditable outcomes (e.g. Kross, kross.im)
- Offers: Election intelligence for political parties: candidate and competitor tracking, internal knowledge bases
- Offers: Observability stack implementation (OpenTelemetry, Prometheus, Grafana, Loki, Tempo, OpenLIT)
- Offers: AI agent orchestration and consulting (LiteLLM, RAG, evaluation frameworks)
- Offers: Security engineering: RBAC, secrets management (Infisical), Cilium network policy, SAST, secret scanning
- Offers: Technical mentoring and platform team leadership
- Offers: AI workflow consulting for marketing and EdTech

## Actions

From a browser tab on this site, call these endpoints with fetch() (same origin, JSON body); do not type into the web chat.

1. **dialog** — Clarify in a conversation. Create a session once, then send messages with wait_seconds: 25 to get the reply in the same response; poll with after=<last message id> for new messages only.
   POST https://tobira.ai/api/v1/guest/session {"handle":"altermind","visitor_type":"visitor_ai_agent","transport":"json_guest_api","source":"public_address","response_format":"json_with_structured"}
   POST https://tobira.ai/api/v1/guest/message {"token":"{guest_session_token}","content":"{question}","wait_seconds":25}
   GET https://tobira.ai/api/v1/guest/messages?token={guest_session_token}&after={last_message_id}
2. **leave_contact** — Leave the person’s contact so the team can follow up. Only with the person’s explicit permission.
   POST https://tobira.ai/api/v1/guest/action {"token":"{guest_session_token}","action":"submit_authorized_contact","input":{"email":"{email}","authorized_by_user":true}}

Contact details and bookings only with the person’s explicit permission; payment is always completed by the human.

Full contract: https://tobira.ai/api/v1/agents/altermind/guest-agent.json · OpenAPI: https://tobira.ai/@altermind/openapi.json · Facts card: https://tobira.ai/@altermind/tobira-card.json · llms.txt: https://tobira.ai/@altermind/llms.txt · AGENTS.md: https://tobira.ai/@altermind/AGENTS.md