Enterprise AI orchestration and AI agents — HAVAA, sovereign by design.
A complete agentic AI platform — visual builder, multi-tenant runtime, four safety modes and a full audit trail — as SaaS, Docker or Kubernetes.
The demo works. Production is the hard part.
Getting an agent to answer well takes an afternoon. Getting it into production inside a bank, a ministry or a hospital means rebuilding safety, isolation, approval and audit from scratch — every single time.
Safety rebuilt per project
Rate limits, kill switches, PII redaction and prompt-injection defence are re-implemented by each team, at each quality level.
Nothing to show the regulator
The question is not whether the agent is good. It is whether you can demonstrate what it did, on whose behalf, and who approved it.
Autonomy without a brake
Agents are shipped either fully manual, which nobody uses, or fully autonomous, which nobody signs off on.
Tenancy leaks
Multi-tenant isolation enforced in application code is one missing filter away from a cross-tenant disclosure.
Cost of inactionPilots stay pilots. The organisation accumulates half-finished agent projects, each carrying its own bespoke risk surface, and none of them survives a compliance review.
A platform, not a framework.
HAVAA supplies the parts every serious agent deployment needs — builder, runtime, knowledge, tools, safety and observability — as one governed artefact you deploy where your data already is.
Visual agent builder
Structured identity, tone, tasks and instructions, with a live playground that shows the exact system prompt before deploy.
Four safety modes
Chatbot, Assistant, Worker and Autonomous — capability is granted per mode, with human-in-the-loop approvals on the actions that need them.
Full audit trail
Every action, input and approval recorded and exportable, with PII redaction and prompt-injection detection applied in the path.
Multi-tenant isolation
PostgreSQL Row-Level Security enforces tenant boundaries at the database, not in application code.
RAG knowledge base
Document ingestion with vector search and source citations, configured per agent so expertise stays scoped.
Autonomous missions
Background execution with a Plan → Execute → Checkpoint → Evaluate loop for scheduled and event-triggered work.
Same artefact, three topologies.
HAVAA runs as SaaS, as Docker Compose on a single server, or on Kubernetes via Helm — the same code path in all three, so a sovereign deployment is a configuration rather than a fork.
Yukon Labs deploys it inside your perimeter, connects it to governed data through Starburst and OvalEdge, and configures safety modes, approval policies and token budgets against your risk appetite.
ISO/IEC 42001 governance is built into the operating model: the model register, the approval trail and the evidence an auditor asks for are produced by the platform rather than reconstructed later.
What happens between the prompt and the action.
An agent request is not a single call. It passes a policy pipeline where every stage can stop it, and every stage leaves a record.
1 · Screen the input
Prompt-injection detection and PII redaction run before the model sees the request, and before anything is written to logs.
2 · Ground the answer
Retrieval pulls from the agent-scoped knowledge base and governed data, with citations carried through to the response.
3 · Gate the action
Tool calls are checked against the agent’s safety mode and budget. Anything above the line queues for human approval with the intent and blast radius shown.
4 · Record everything
The request, retrieved context, decision, approver and result are written to the audit trail in the same transaction as the action.
Frequently asked questions
What is HAVAA?
HAVAA is Yukon Labs' AI orchestration platform: one governed AI agent working across Telegram, WhatsApp, web, mobile and email, in any language.
It drafts a reply in seconds, checks it against your policy before sending, and escalates to a human when the stakes require it. Every reply is logged with the policy it was checked against and the person who approved it. It runs entirely inside your own perimeter.
What is the difference between an AI agent and a chatbot?
A chatbot answers; an agent acts. A chatbot matches a question to an answer. An agent is given a goal, decides which steps to take, calls tools to do them, and continues until it finishes or hands over.
The practical difference is accountability: because an agent changes things, it needs per-user permissions, a boundary on which tools it can reach, and an audit trail.
Can HAVAA run entirely inside our perimeter, with no data leaving the organisation?
Yes — HAVAA runs entirely inside your perimeter, and that is the default for banks and state institutions. The model, orchestration, retrieval index, embedding model and logs all run on infrastructure you control.
The detail where most "private AI" claims fail: self-hosting the model while calling a hosted embedding service still transmits every document you index. HAVAA keeps the whole path local, enforced by network egress control rather than a setting.
Which LLMs does HAVAA support — can we bring our own model?
Yes — you can bring your own model. HAVAA treats the model as a swappable component behind a stable interface, so it runs open-weight models you host, models you have licensed, or a hosted API where that is legally available — and can mix them.
That also makes it cheaper: most enterprise traffic is simple and routes to a small model, with a larger one reserved for the minority of requests that need it.
What is AI orchestration, and why can't we just call an LLM API directly?
AI orchestration is the layer between models and your organisation: routing, tool access, state, permissions and audit.
You can call an API directly, and every project starts there. It stops working when the requirements arrive — look things up in our systems, only show what the user may see, explain an output from three months ago, nothing leaves the perimeter.
What is MCP (Model Context Protocol), and does HAVAA support it?
MCP is the open standard for exposing tools and data sources to AI models, and yes, HAVAA supports it.
Its value is portability: a tool built once works with any compatible model. It is now genuine infrastructure — donated by Anthropic to the Linux Foundation in December 2025, backed by AWS, Google, Microsoft and OpenAI, and running at about 97 million SDK downloads a month.
How do you stop an AI agent from taking an action it shouldn't?
You stop an AI agent structurally, not by instructing the model. Three controls: tools are scoped per context, so an agent answering an HR question does not hold a payment tool; every action runs under the requesting user's permissions, never a shared account; and consequential actions need a named human approver.
Anything enforced only by prompt wording is not a control.
What hardware do we need to run LLMs on-premise?
Running an LLM on-premise needs less hardware than most expect: one server with one or two high-memory data-centre GPUs serves a real internal deployment.
Memory is the constraint: a 70B model needs about 140 GB at full precision but roughly 35 GB at 4-bit. Budget separately for the KV cache, which scales with context length times concurrency.
How well does HAVAA handle Azerbaijani-language content?
Azerbaijani is a first-class language in HAVAA, alongside English, Russian and all other languages, which is treated as a design constraint rather than an afterthought.
It has to be: Azerbaijani is low-resource for language models, quality trails English, and the gap widens on banking and legal vocabulary. We test model and quantisation choices against Azerbaijani cases from your own domain before anything ships.
How long does a first HAVAA deployment take?
A first HAVAA deployment takes ten to twelve weeks to a production use case, assuming the deployment posture is settled early.
Two weeks to define workload and build an evaluation set in the languages you serve, two to evaluate models, two to stand up the stack, three to build the use case with identity-aware retrieval and audit from the start. The second use case costs a fraction of the first.
Can HAVAA integrate with our existing systems — SAP, 1C, internal APIs?
Yes — HAVAA integrates with SAP, 1C and internal APIs. Each system becomes a tool with a defined schema, validated arguments and its own access rules, so an agent can read from SAP, 1C or a core banking system without any of them being exposed wholesale.
The work is less about connectivity than about deciding which operations are read-only and which need a human approval gate.
Is our data used to train any model?
No — your data is never used to train or improve any model, ours or a third party's. It answers your questions and nothing else.
On-premise, this is physical rather than contractual: the model runs on your hardware and there is no outbound path. We also prefer retrieval over fine-tuning, so a deletion request can actually be honoured — remove the document and the embedding and it is gone.
If the model produces a wrong answer, is there an audit trail?
Yes — every HAVAA request carries a full audit trail. It records who asked, what was retrieved, which model and version answered, which tools were called, what came back and what it cost.
That is what reconstructs a specific interaction months later — the form a regulator's question actually takes — and what an ISO/IEC 42001 auditor asks to see. Log retention and storage location are defined as part of the deployment.
How is HAVAA priced?
HAVAA is priced per deployment rather than per message, because the cost of an on-premise system is fixed infrastructure plus support, not consumption.
The shape depends on deployment posture, the number of channels and use cases in scope, and whether we operate the platform or hand it over. Infrastructure is separate and yours. We scope against your real expected volume during the assessment.
Do we need a data lakehouse before we can deploy AI agents?
No — a data lakehouse is not a prerequisite for AI agents, and treating it as one delays the first deployment by a year for no benefit.
What agents need is governed access to the specific data one use case depends on: an authoritative source, defined terms, per-user permissions and lineage good enough to explain an answer. That is a few weeks of catalog work, not a platform migration.