Home

Frequently Asked Questions

Everything you need to know about Obsigen AI.

General

What is Obsigen AI?

Obsigen AI is a European enterprise conversational agent built to plan, execute, verify, and deliver outcomes — not just generate text. It combines multi-agent orchestration, tool execution (search, file analysis, code sandbox, image generation, PPTX builder), RAG-ready knowledge grounding, and trainability for domain alignment.

What does "EEA-first" mean?

EEA-first means Obsigen is designed for data residency and operations within the European Economic Area. All persistent data (chat history, files, generated artifacts) stays in EEA data centers. This simplifies GDPR audits and reduces data transfer complexity.

How is Obsigen different from ChatGPT or other chatbots?

Obsigen is an agentic AI — it doesn't just chat. It can search across multiple sources, analyze your files, run Python code in a secure sandbox, generate images, and build PowerPoint deliverables. It also features multi-agent Swarm orchestration (50–100 parallel agents) for complex research tasks, and it's designed for enterprise use with EEA data residency.

Which industries does Obsigen serve?

Obsigen is built for three primary verticals: Manufacturing & Supply (scheduling, maintenance, quality, inventory), Cybersecurity / SOC (alert triage, enrichment, attack surface mapping, DLP), and Sales & Service (pipeline forecasting, creative automation, contact center copilot). The platform is flexible enough for other enterprise use cases as well.

Capabilities

What are execution strategies?

Obsigen has 7 execution strategies that determine how a request is handled: Fast (quick answers), Light (minimal latency), ReAct (tool-based tasks), Master (deep reasoning), Hybrid (tools + lighter swarm), HybridFull (deep research + verify), and Swarm (50–100 parallel agents for maximum coverage). The system can select the strategy automatically or you can choose manually.

What is the Swarm mode?

Swarm mode deploys 50–100 specialized parallel agents — solvers, critics, researchers, and testers — to tackle complex tasks. The results go through MAP (parallel solving) → REDUCE (consolidation) → VERIFY (stress testing) → FINAL (executive synthesis). This approach significantly reduces blind spots and hallucinations on complex research tasks.

What tools does Obsigen have access to?

Obsigen includes five built-in tools: WebSearchTool (multi-source search via Brave, SearXNG, Tavily), FileAnalysisTool (PDFs, Office docs, images), CodeExecutionTool (sandboxed Python), ImageGenerationTool (FLUX.1-schnell), and PptDocumentBuilderTool (professional PPTX generation). Enterprise plans can include custom tool integrations.

What is RAG and why does it matter?

RAG (Retrieval-Augmented Generation) allows Obsigen to answer questions using your internal knowledge — SOPs, policies, ERP docs, product catalogs, etc. This reduces hallucinations, improves accuracy, and provides traceable citations. Every answer can reference the specific document, section, and version it was based on.

Can Obsigen be fine-tuned for our domain?

Yes. Fine-tuning options include SFT/Instruction tuning (for consistent "house style" answers), LoRA adapters (cost-effective per-tenant specialization), Preference tuning (alignment to internal standards), and Tool-use tuning (better agent reliability). All training happens on approved datasets within EEA storage.

Security & Privacy

Is my data safe with Obsigen?

Obsigen uses layered security: TLS transport, JWT authentication, role-based authorization, content safeguards (injection/jailbreak detection), sandboxed code execution (Docker, no network), MIME-checked file handling, strict CORS, Redis-based rate limiting, and environment-variable secrets management. All persistent data stays in EEA.

Is code execution safe?

Yes. Code is executed in Docker containers with no network access, enforced timeouts, and per-run isolation. Each execution creates a fresh container that is torn down after completion. No data persists between executions.

Does Obsigen comply with GDPR?

Obsigen's EEA-first architecture is designed to help simplify GDPR compliance. All persistent data is stored in EEA data centers, inference prompts are transient, and no passwords/tokens/files are forwarded to external models. However, each organization should conduct their own assessment based on their specific use case and data processing requirements.

Pricing & Plans

Can I try Obsigen before committing to a plan?

Yes. Contact our team to arrange a personalized demo and trial period. We'll set up an environment tailored to your use case so you can evaluate Obsigen with real scenarios.

What happens if I exceed my message limit?

You can purchase additional message packs as an add-on, or upgrade to a higher tier. We'll notify you as you approach your limit so there are no surprises.

Is on-premise deployment available?

On-premise deployment is available on the Enterprise plan. This gives you full control over the infrastructure, data, and network configuration. Contact our team for details.

Still have questions?

Our team is happy to help with any questions about Obsigen AI.

Contact Us