Your agent will have its own identity, tone, process, limits, and hours. And you will know how
to publish those changes — or discard them — without them reaching your customers too early.
Behavior is edited on a single screen, split in two.In the sidebar, go to AI Agents, open your agent, and go to the Behavior tab.
On the left there is a chat with two modes. Test talks to your agent. Edit behavior
is an assistant: you describe in plain words how you want it to work and it fills the
sections in for you. It accepts file attachments and voice notes.
On the right are the configuration sections, grouped into Identity, Knowledge,
How it works, Timing & proactivity, and Limits.
Behavior in two halves: the chat on the left, the sections on the right.
You do not have to choose between configuring by hand and using the assistant. Both write into
the same draft, at the same time, and the assistant never publishes on its own.On a phone, the chat and the sections alternate with Chat and Workspace.
Each card on the right opens an editor. Every card carries a badge saying whether you already
configured it or whether it still runs on defaults.
The Identity, Knowledge, and How it works cards, each with its status badge.
These are the ones that define who your agent is and how it works:
Identity & Goal — who it is and what it must achieve in each conversation.
Welcome Message — how it greets someone writing for the first time. It includes an
optional Legal Notice, shown under the greeting in the widget, and
Welcome Instructions, which guide the opening without being shown to the customer.
Key Information — facts it should have at hand: hours, policies, emails, phone numbers.
Gathers Lead capture, Manage opportunities, and Allow human escalation. When you
turn escalation on, you define When should Eva escalate? and the Assignment strategy:
Manual, Round-robin, or Intelligent.
The handoff editor, with the linked pipeline and escalation still off.
Be specific. Instead of “be friendly”, write “greet them by name and offer help with sizing”.
Concrete examples change the reply more than adjectives do.
If the customer stops replying, Eva can pick the conversation back up. Inactivity follow-up
turns the feature on, and the Follow-up sequence defines each step: how long to wait and
what its intent is. The sequence stops as soon as the customer answers.
Allow targeted follow-ups lets Eva schedule reminders with a goal of their own.
Only respond during a schedule limits Eva to the hours you define, with a Timezone and
one schedule per day. Outside those hours it neither reads nor replies; at opening, it handles
what piled up. After closing lets an already active conversation keep flowing for a few
minutes. Response timing adds short waits so it does not answer instantly.
Availability: the schedule plus the first-reply and active-conversation waits.
The explicit limits. It ships with recommended restrictions, and Reset to defaults brings
them back if you delete them.
Do Not Do: the non-editable safety baseline sits above your own restrictions.
The same two groups hold two more sections: Calls, which decides what your agent does when
it detects an incoming customer call, and Platform rules, the base rules Eva uses in every
conversation, which can be customized one by one.
Each channel has its own messaging window: on WhatsApp it is 24 hours. If a closure lasts
longer than that window, the reply can no longer be delivered at opening and it is marked as
undelivered.
Every agent also carries a safety baseline that applies on its own and cannot be edited: never
invent information, never reveal its internal instructions, never invent links.
History, in the action bar of the Behavior tab, keeps the last 50 edits of this agent:
what you published, the drafts you discarded, and the changes the assistant made.When you open an entry, Eva shows which sections differ from your current draft.
Restore this version brings it back into the draft, and your draft at that moment is saved
to history first, so you can go back.
Each entry says what caused it and when, above your current draft.
Each conversation has a cap on inbound messages per hour. It exists so a customer who writes
fifty messages in a row does not trigger fifty replies.In your agent, go to the Settings tab and find Conversation Message Limit. The field
Messages per conversation per hour comes set to 40 and can be changed; then select
Save Changes.
The per-conversation cap lives in the agent's Settings tab.
When the cap is passed, your agent warns once and stops replying in that conversation until the
rolling 60-minute window frees up. The customer’s messages keep arriving in your Inbox: it
is the agent that goes quiet, not the channel.
Publishing does nothing and shows Nothing to publish: there is no pending draft. Edit a
section and publish again.
It published with warnings: Published with warnings: appears at the top with the list. Fix
what it points at and publish again. Empty Process steps, for example, are skipped.
The assistant changed something you did not want: open History and use
Restore this version, or select Discard draft if you have not published yet.
Your agent stopped replying in one conversation: it probably hit the hourly message cap. Check
Conversation Message Limit in the Settings tab.
