Ottili AI

Dynamic Workforce Engine

The Dynamic Workforce Engine (DWE) is the agent engine behind Ottili AI: it breaks missions into work units and assigns role-based DWE specialists. Status, specialists, tools, approvals, credits and audit.

Overview

The Dynamic Workforce Engine (DWE)* is the agent engine behind Ottili AI. When you hand Ottili AI a goal — a mission* — the DWE takes over: it breaks the goal into manageable units of work and assigns role-based DWE specialists* that carry the work forward.

The DWE is live (General Availability)* — publicly documented with the maturity status Live*. It is part of the Ottili AI surface and, like the other Ottili AI capabilities, shares a common company context, a common credit ledger and a common audit trail.

This article explains what the DWE is, how a mission runs through it, what role the DWE specialists play, how tools, approvals, credits and audit work, and how the DWE is embedded in Ottili ONE.

What the Dynamic Workforce Engine is

The DWE is the engine that executes agentic work. It takes a mission (a goal) and turns it into executable work:

Decomposition*: the mission is split into units of work.
Assignment*: role-based DWE specialists carry the work forward. A specialist is an agent with a specific role (for example analysis, creation or review).
Tools*: specialists can call tools to read and change your data.
Consolidation*: the partial results are merged into the mission's goal.

The DWE is the engine behind Ottili AI's agent mode and missions. Its specialists and building blocks are live; a dedicated, standalone "Agent Mode" surface is in development.

Status and availability

The DWE carries the maturity status Live (General Availability)*. That means it is generally available, fully supported, and intended for real workflows.

The maturity status of each Ottili AI capability (from the canonical product-status registry, config/product_truth/ai_feature_status.yaml):

Missions* — live
DWE specialists* — live
Tool use* — live
Approvals* — live (enforced through Ottili Console and Ottili Core)
Credits, cost control, audit* — live (Core-backed)
Memory* — planned (not yet evidenced as live)

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

How a mission runs through the DWE

When you hand over a mission, the Dynamic Workforce Engine (DWE)* takes over:

1. Break down the goal* — the mission is decomposed into manageable units of work.

2. Assign specialists* — role-based DWE specialists carry the work forward. A specialist is an agent with a specific role (for example analysis, creation or review).

3. Call tools* — specialists can call tools to access and change your data.

4. Bring together the result* — the partial results are merged into the mission's goal.

You do not choose the underlying models yourself: adaptive routing (Ottili Auto)* distributes each request to the right model automatically — everyday work to Ottili Vale, demanding work to Ottili Cairn.

Models and routing

The DWE runs on the shared Ottili AI models:

Ottili Vale* — efficient, everyday, cost-effective (Live/GA).
Ottili Cairn* — the premium model for serious engineering and analysis work (Live/GA).
Ottili Auto* — the adaptive router that picks Vale or Cairn per request (Live/GA).
Ottili Spire* — the reserved flagship model; currently reserved, not yet available*.

How models, routing and availability work is described in [Ottili AI API — Models](/docs/ottili-ai-api-models).

Tools and approvals

DWE specialists can call tools — the business.* and ld3.* namespaces of the Unified API — to access and change your data. Critical actions are approval-first*: nothing leaves your company context for an external effect until a required approval is granted. Approvals are enforced through Ottili Console* and Ottili Core*.

Credits and cost control

Ottili AI is prepaid: you add credits, and the cost of a request is reserved and deducted from your balance. A request is rejected up front if the balance cannot cover it. Per API key and per company, model limits, budget limits and rate limits can be enforced — that is the cost-control surface.

How credits and plans relate is described in [Understand plans and credits](/docs/understand-plans-and-credits).

Embedded in Ottili ONE

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

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

That means: a mission always runs inside your company; every action is resolved to a single company and recorded through Ottili Core audit*. The DWE uses the same models and the same routing as Ottili Coder, Ottili LD3 and other surfaces — from inside your company.

[Chat and agent modes](/docs/chat-and-agent-modes)
[Ottili AI](/docs/ottili-ai)
[Ottili AI API](/docs/ottili-ai-api)
[Ottili AI API — Models](/docs/ottili-ai-api-models)
[Understand feature status labels](/docs/understand-feature-status-labels)
[What is Ottili ONE?](/docs/what-is-ottili-one)
[Understand plans and credits](/docs/understand-plans-and-credits)

Was this article helpful?