2.1 AI Team, Agent Studio, and Agent Harness
Teloa · AI-Native Team Studio. An AI team of your own. For everyone.
Teloa helps you build, collaborate with, and run your own AI team. You define the goals and boundaries. Your AI team carries the work forward. Start with goals, colleagues, and deliverables, then build up knowledge, skills, tools, and permissions as you work.
1. Three product layers
TELOA = AI Team + Agent Studio + Agent Harness
| Product layer | Purpose | Core concepts |
|---|---|---|
| 01 · AI Team | Build and run your AI team | Colleagues, tasks, collaboration, business areas, projects, automation |
| 02 · Agent Studio | Define how each AI colleague works | Roles, knowledge, skills, tools / MCP, permissions |
| 03 · Agent Harness | Support safe, continuous, controlled execution | Model, Runtime, Tool Gateway, Sandbox, Approval, Observability |
Team is the product, Agent is the unit of work, and Harness is the runtime foundation. These product layers do not require three new pages or services. See Source architecture for the implementation view.
1.1 AI Team: colleagues and delivery
You need to know who your colleagues are, what they are doing, what needs you, and whether the work meets your expectations. Business areas organize ongoing work; projects connect tasks, colleagues, work groups, and results around a delivery goal. Tasks and automations manage one-off and recurring work.
AI Team means your lasting business team. A task team is temporary delegation within a task, started by a conversation or colleague. Task assistants do not automatically become colleagues. See People and collaboration.
1.2 Agent Studio: five configuration questions
| Configuration | Question |
|---|---|
| Role | Who are you, and what are you responsible for? |
| Knowledge | What should you know, and which references may you use? |
| Skill | How do you work, and which methods can you reuse? |
| Tools / MCP | Which business systems and tools can you use? |
| Permissions | How far may you act, and when is a person needed? |
MCP is one protocol for connecting external capabilities. Configuring a tool does not authorize every action. Skills provide established methods while leaving colleagues able to plan within their permissions.
1.3 Agent Harness: reliable execution
The Harness handles models and runtimes, tool calls, sandbox isolation, approvals, and execution visibility. Teloa uses native engine capabilities first and adapts colleague identity, business scope, and delivery rules. DSH is the current engine. Support for other engines, enterprise security gateways, and distributed deployment is described in Editions.
1.4 From setup to autonomous work
- Recruit colleagues and define their roles and responsibilities.
- Add knowledge, business references, and context.
- Teach skills so established methods can be reused.
- Connect tools or MCP services to real business systems.
- Set permissions, including read, write, and approval boundaries.
- Start work through tasks, supported events, or schedules while the runtime is online.
- Bring key decisions back to a person: approvals, exceptions, high-risk actions, and delivery review.
Start with a role template or industry solution; you do not need to repeat setup for every task. Autonomous work remains subject to permissions, supported triggers, and runtime availability.
2. Skills, connections, and extension packages
A skill describes how to work. A connection provides external information or tools. A task template supplies reusable task inputs, goals, and delivery requirements. Templates can reference skills, and a skill can serve different tasks.
An extension package is a unit of installation and distribution. It can provide multiple skills, connections, or runtime capabilities. These are contents provided by a package. A capability should identify its source package; package management should explain what it provides and which business areas use it.
“Official” and “third-party” describe the publisher. “Built-in” and “user-installed” describe delivery. Neither distinction alone determines whether an item can be disabled or removed. Required system components and optional extensions need different treatment.
3. What an industry solution contains
An industry solution can combine seven kinds of content: AI colleagues, skills, reference knowledge, connections, business boards, task templates, and extension dependencies. It supplies business configuration, rather than representing a single engine plugin.
For example, a marketing solution might define a content colleague, writing skills, product information, a data connection, and a weekly report template. After importing it, check the content, connections, and role permissions separately. Adding the solution does not make all its dependencies ready. See Business resource packages to create one.
4. Installed does not mean available or authorized
| Fact to check | Meaning |
|---|---|
| Installation | Content is installed in the relevant runtime environment |
| Enablement | A loading or enablement choice has been saved |
| Runtime | The component has actually loaded, or has an error or requires a restart |
| Connection and authentication | The external service and credentials are usable |
| Business authorization | A particular colleague may perform particular operations within a defined scope |
These are independent dimensions, not a mandatory five-step sequence. A skill may need no authentication. An enabled plugin that fails to load remains unavailable. A working connection does not grant every colleague permission to publish, change, or delete information.
For a weekly marketing report, the task template defines inputs and delivery requirements, skills provide the analysis method, connections supply data, and the colleague acts within its permissions. The engine records execution. The task requirements determine whether the result is accepted.
5. Where to manage things
Market supports discovery and selection. Capabilities manages existing resources and extension status. Connections and runtime in Settings lists configuration and provides an explicit entry to the official engine manager. Advanced diagnostics → System components is for dependencies. Installation, enablement, runtime state, and business authorization are checked separately.
Current DSH forms belong to a single official page and are not yet embedded in Settings. See the capabilities guide and Capability and engine integration boundaries.