Create an agent by describing the job, then decide what it may create, read, update and delete. An agent can never have more access than the one above it, and everything it does is recorded.
ClaudeFor every person and every agent, set what they may create, read, update and delete in each part of the workspace. Anything not allowed is out of reach.
Describe an agent and it appears on the org chart as a draft. The system agent coordinates the other agents, which each run workflows within their access and spending limits. Every handoff between them is logged.
What each person and agent may create, read, update and delete, in each part of the workspace.
A spending limit for each agent, and approval for anything above it.
Company and agent documents that an agent has to follow.
What it reads before it drafts anything for someone outside the company.
Upload a skill or give it a tool, and take either away later.
Every action, handoff and approval is recorded once and cannot be edited.
While an agent is working, it shows what it is doing now, how long it has been going and what each finished step found. Anyone in the stream can stop it, and the steps it finished stay on the record.
Permissions decide what an agent may do. The model chosen for it decides how well it does it, and what it costs.
Claude
GPT
Gemini
DeepSeek
Kimi
GLMThere is no need to use one model for everything. Daya splits an agent's thinking into named tasks, such as routing, retrieval, perception, generation, reasoning and governance, and offers a short list of suitable models for each.
The subscription pays for seats. Agent work is charged by usage, from credit bought in advance, and the balance shows how many days it will last at the current rate of spending.
No. Agents are part of the plan. Seats are for the people who log in.
Three things: its permissions limit what it can touch, its spending limit caps what it can cost, and anything that cannot be undone needs approval first.
It can propose one. The new agent cannot have more access than the agent proposing it, and a person has to approve it before it runs.
Start with one agent, one base and read-only access. Give it more once you trust it.