Core concepts

Agents

An agent is the thing that talks. It has instructions, a model, a voice and a set of capabilities, and it runs the same way whichever channel it is on.

An agent comes in one of two shapes, chosen when you create it:

A prompt agent is one prompt doing one job. Fastest to build; the model decides how the conversation goes. A workflow is a graph of steps you connect yourself, for conversations that must follow a path - qualify, then branch, then hand off. See Prompt agents and Workflows.

Sessions

A session is one conversation - one phone call, one web call, one chat. Every session is stored with:

• the full transcript, turn by turn
• the configuration snapshot that produced it, so you know exactly which prompt, model and voice were live at the time
• what it cost, split by component
• latency, so you can see where the time went
• the recording, if recording is on

This is the point of the platform: when an agent gets something wrong, you can open the session and see why. See Sessions and transcripts.

Versions

Editing a published agent does not overwrite what your callers are getting. It opens a new draft version, and the published one keeps running until you publish again. Every revision is kept.

A session is pinned to the version it started on, so editing an agent never changes a conversation that is already in flight.

The Playground

The Playground is where you test an agent before real callers meet it. It can:

• chat or talk to an agent live in the browser
• compare two agents, or two versions of one agent, side by side on the same input
• replay a real past conversation against a version, to check a change did not break what already worked
• try overrides - a different prompt or model - without saving them to the agent

Providers

Glytos does not lock you to one vendor. The language model, the transcriber and the voice are each chosen per agent from a catalog, and you can bring your own keys for any of them, in which case that provider's cost is yours and Glytos does not charge for it. See Models and voices.

Tools and knowledge

Two different ways to make an agent useful beyond talking:

• Tools let it do things - call your API, look up an order, trigger a workflow in another system - during the conversation. See Tools.
• A knowledge base lets it answer from your own documents. See Knowledge base.

Channels

The same agent runs on any of:

• Phone - inbound and outbound, on a number you buy or bring.
• Web - a call from a browser, over WebRTC.
• Chat - the same agent as text.

Nothing about the agent changes per channel. See Channels.

Organizations

An organization is a workspace: its own agents, numbers, credit and members. One account can own several and switch between them. Each organization is created in a region, which is where its data lives and cannot be changed afterwards. See Organizations and regions.