Skip to main content
Ottili AI

Ottili AI Overview

Ottili AI is the AI control surface and assistant layer of Ottili ONE: its own models (Vale, Cairn), adaptive routing, missions, the Dynamic Workforce Engine, tool use, approvals, credits, cost control and audit – company-scoped and audited.

Überblick

Ottili AI* is the AI control surface and assistant layer of Ottili ONE*. It runs Ottili's own models — Ottili Vale* and Ottili Cairn* — behind a single OpenAI-compatible API, with adaptive routing, missions, the Dynamic Workforce Engine (DWE), tool use and usage controls. Ottili AI powers Ottili Coder, Ottili LD3 and other Ottili surfaces from inside your company context.

Ottili AI is publicly available as part of Ottili ONE. Each capability carries the maturity status listed below — most are live, Memory is planned (PLANNED).

This article describes what Ottili AI is, how a workload moves through the Ottili AI surface, how maturity is labelled, how security and approvals work, and how Ottili AI is embedded in Ottili ONE.

What Ottili AI is

Ottili AI is not a standalone chat surface but the shared AI layer of Ottili ONE. Through one OpenAI-compatible API you share models, routing, missions and tools with the same platform that Ottili HQ, Ottili Coder, Ottili LD3 and Ottili Cloud also use.

Typical tasks for Ottili AI:

  • Generate text, code and content with Ottili Vale* (efficient) or Ottili Cairn* (premium reasoning)
  • Let Ottili Auto* route each request adaptively to the right model
  • Frame goals as missions* and have the Dynamic Workforce Engine* execute them
  • Call tools* across the Unified API business.* and ld3.* namespaces
  • Run critical actions approval-first*
  • Pay for usage with credits* and bound it with cost control*
  • Record every action through audit*

Status and availability

Ottili AI is part of Ottili ONE. Each capability carries a maturity status from the canonical product-status registry (config/product_truth/feature_status.yaml):

CapabilityStatus
Ottili Vale (efficient model)Live (LIVE)
Ottili Cairn (premium model)Live (LIVE)
Adaptive routing (Ottili Auto)Live (LIVE)
MissionsLive (LIVE)
DWE specialistsLive (LIVE)
Tool useLive (LIVE)
ApprovalsLive (LIVE)
CreditsLive (LIVE)
Cost controlLive (LIVE)
AuditLive (LIVE)
MemoryPlanned (PLANNED)

The canonical maturity vocabulary covers CONCEPT, PLANNED, IN_DEVELOPMENT, PRIVATE_BETA, BETA, ROLLOUT, LIVE, DEPRECATED and DISABLED. For Ottili AI the current capabilities are LIVE; Memory is PLANNED — we do not claim a memory capability that is not yet verified as live.

How Ottili ONE labels maturity publicly is described in [Understand feature-status labels](/docs/understand-feature-status-labels).

How a workload runs

When you give Ottili AI a task, it moves through a predictable chain:

1. Model* — the request lands with Ottili Vale* or Ottili Cairn*.

2. Routing*Ottili Auto* adaptively picks the right model (everyday work to Vale, heavier reasoning to Cairn).

3. Missions* — a goal is framed as a mission* and tracked.

4. DWE specialists* — the Dynamic Workforce Engine* breaks the mission into work and assigns role-based DWE specialists*.

5. Tools* — specialists call tools* through the Unified API (business.*, ld3.*) to act on your data.

6. Approvals* — critical, external actions wait for an approval* before they take effect outside your company context.

7. Credits & cost control* — every request reserves and deducts credits*; cost control* enforces per-key model and budget limits and rate limits per key and company.

8. Audit* — every action is resolved to exactly one company and recorded through Ottili Core Audit*.

Security and data handling

Every Ottili AI workload stays inside a single company boundary (company_id):

  • Company-scoped isolation* — requests are resolved to exactly one company.
  • Routing inside your context* — Ottili Auto routes within your company context.
  • Approval-first tools* — nothing leaves your company context for an external effect until the required approval is granted.
  • Memory boundary*Memory* is part of the capability set but planned (PLANNED) — not verified as live.
  • Prepaid credits* — usage is prepaid; a request is rejected up front if the balance cannot cover it.
  • Cost control & rate limits* — limits are enforced per key and per company.
  • Audit trail* — every action is traceable.

Embedded in Ottili ONE

Ottili AI is native to Ottili ONE. It shares with the other Ottili surfaces:

  • one login* (One Login)
  • one company context* (every action belongs to exactly one company, company_id)
  • one credit ledger*
  • one audit trail*

This means an Ottili AI job always runs inside your company; every action is resolved to exactly one company and recorded through Ottili Core Audit*. The same models and routing power Ottili Coder, Ottili LD3 and other surfaces from inside your company. The shared account structure is described in [What is Ottili ONE?](/docs/what-is-ottili-one).

Related articles

  • [Dynamic Workforce Engine](/docs/dynamic-workforce-engine)
  • [Chat and agent modes](/docs/chat-and-agent-modes)
  • [What is Ottili ONE?](/docs/what-is-ottili-one)
  • [Understand feature-status labels](/docs/understand-feature-status-labels)

Was this article helpful?