AI Chat
Ask questions about your business, workflows, modules and connected data.
Ottili AI
Company AI that runs on Vale and Cairn — with you in control.
Ottili AI adaptively routes every request through Vale or Cairn, turns goals into missions run by DWE specialists, and lets them use tools with approval-first safety. Credits, cost control and audit keep every action traceable inside your company.
Live
AI capabilities
Everything your company AI can do.
Ottili AI can assist across your entire business — from answering questions to running structured missions with tasks, drafts and approvals.
Missions
Turn bigger goals into structured work packages with tasks, drafts, checks and next steps.
Agents
Use specialized AI roles for operations, content, support, development and strategy.
Approvals
Keep important AI actions reviewable before they affect customers, content, billing or external systems.
Budget
Track AI usage and keep automation costs under control.
Skills
Teach your company AI reusable instructions, workflows and business-specific behavior.
Platform
Ottili AI runs on the Ottili AI Platform
Ottili AI is one product built on the Ottili AI Platform — the shared AI layer with model access, an OpenAI-compatible API, credits and controls. The platform also powers Coder, LD3 and Cloud.
Company context
AI that knows your business — not just general knowledge.
Ottili AI has access to the workspace context you allow. Here is what that means in practice:
Connected integrations
AI can query your Shopify orders, eBay listings and any other connected tool — with your permission.
Module data
AI has access to Ottili LD3 drafts, Shopping deals, Marketplace Connect orders and any module data you allow it to use.
Workflow history
AI can see what automations ran, what approvals are pending and what happened in previous workflow runs.
Company Skills
Define reusable business-specific instructions — how to write for your brand, which rules apply, what thresholds matter.
Ottili AI Platform models
One platform, a clear model line.
Ottili AI Platform ships a focused set of models. Ottili Vale is the efficient everyday tier, Ottili Cairn is the premium price-performance tier for heavy agentic work, and Ottili Spire is the reserved flagship planned for a later release. Every model runs inside your company context with the same approval-first controls.
Ottili Vale 1.2
AvailableEfficient tierEfficient tier
The efficient everyday model for chat, drafting and fast coding tasks.
Ottili Cairn 1.2
AvailablePremium price-performance tierPremium price-performance tier
The premium price-performance model for advanced agentic and reasoning-heavy software work.
Ottili Auto
AvailableAdaptive routerAdaptive router
The adaptive router. It selects Ottili Vale for fast everyday work and Ottili Cairn for heavy or agentic tasks, per request.
Ottili Spire 1.2
Coming soonFlagship tierFlagship (reserved)
The reserved Ottili AI flagship. Not yet available — planned for a later release.
Approval-first
Important actions always go through you.
Ottili AI never takes irreversible actions automatically. Customer replies, purchase requests, publishing actions and billing steps always go through the Approval Queue — so you stay in control of every output that matters. You choose which actions are automatic and which require review. Nothing critical happens without your sign-off. The approval queue is a first-class feature, not an afterthought.
Approval queue
Ottili AI · 3 pending · example
Support AgentEmail
Reply to customer #4821
Drafted a refund-status reply in the customer's language.
96% confidence
Commerce AgentMarketplace
Publish eBay listing
iPhone 13 · €389 · 12 photos · price within target margin.
91% confidence
Sourcing AgentNeeds review
Approve purchase · €240
Kleinanzeigen deal scored 8.7/10 — above the buy threshold.
84% confidence
Every action is logged and reversible until you approve.
Routing & cost controls
How Ottili AI routes and charges every request
Behind every Ottili AI conversation, mission and approval is one control layer that routes your request, caches steady context, charges company credits and enforces hard caps. The rules below are product-level: no internal provider names, no credentials, no private API detail.
Provider routing
LiveOne routing layer maps public model ids to backing providers by capability and tier. The adaptive router (Ottili Auto) picks the efficient model for fast work and the premium model for heavy or agentic work, per request.
Fail-closed fallbacks
LiveWhen a model or provider is degraded, the request is reported — never silently downgraded to a paid or mock provider. You always know which model served the response.
Circuit breakers
LiveA failing provider or route is isolated behind a circuit breaker so one degraded dependency cannot take down the shared platform. A tripped circuit returns a normalized error instead of hanging.
Cache use
BetaRepeated prefix tokens are cached per company, so steady-context workloads cost less and run faster. Cache is scoped to your company and never shared across tenants.
Credit charging
BetaEvery billable request takes a worst-case reservation before work begins, settles on success and releases on abort. Idempotency keys mean retries and replays never double-charge.
Hard caps
LivePer-company, per-project and per-user hard caps stop spend at a ceiling regardless of retries. Exceeding a cap returns a structured, machine-readable error — no silent overage.
Wallet recharge
BetaCompany wallets are topped up through the active plan or purchased credit packs. Spend is metered per request against the wallet, so usage maps cleanly to what was paid for.
Company wallets
BetaA single company wallet backs AI usage across Ottili AI, Coder, Ottili LD3, Cloud and the public API. Spend is company-scoped and isolated — no cross-company charges.
Concrete workflow
How Ottili AI runs one workload
From one request to a logged, cost-controlled result — the AI surface of Ottili ONE. Every step carries its honest readiness status from the canonical product-status vocabulary; nothing claims unverified availability.
From one request to a logged, cost-controlled result — the AI surface of Ottili ONE.
- LiveOttili Valevia Ottili AI
- LiveOttili Cairnvia Ottili AI
- LiveAdaptive routing (Ottili Auto)via Ottili AI
- LiveMissionsvia Ottili AI
- LiveDWE specialistsvia Ottili AI
- LiveTool usevia Ottili AI
- LiveApprovalsvia Ottili Console
- PlannedMemoryvia Ottili AI
- LiveCreditsvia Ottili Core
- LiveCost controlvia Ottili Core
- LiveAuditvia Ottili Core
Native to Ottili ONE
- Native to Ottili ONELiveNative to Ottili ONE
AI operator direction
From assistant to operator.
Ottili AI is designed to evolve from a helpful assistant to a capable operator. The current focus is on drafting, assisting, analyzing and preparing work for your review. Future development aims toward DWE (Digital Workforce Evolution) — where AI can execute more complex workflows while maintaining the approval-first philosophy that keeps you in control.
Put company AI to work — on your terms.
Start with Vale or Cairn, hand over missions to DWE specialists, and connect tools with approvals, memory, credits, cost control and audit built in. You review; nothing critical ships without your sign-off.