Advanced Settings
The Advanced tab contains the agent state, category access, response limits, and external-channel behavior. Open Agents, select the agent, and choose Advanced in the sidebar.
Changes remain a draft. Use Save changes to apply them or Discard to return to the last loaded values. If saving reports an error, check both the fields and category before trying again: those two groups are persisted by separate operations.
Initial agent values
Section titled “Initial agent values”An agent created from the current Agents page starts with these values:
| Setting | Initial value | Available range |
|---|---|---|
| Agent active | on | on or off |
| Temperature | 1.0 | 0.0 to 2.0, in 0.1 steps |
| Context memory | 30 messages | 1 to 50 |
| Search earlier conversations | on | on or off |
| Maximum tool calls | 14 | 1 to 20 |
| Group messages | off | off or a 10- to 60-second window |
| Split response into multiple messages | off | on or off |
State and category
Section titled “State and category”Agent active controls whether the agent can reply. After you turn it off and save, the agent stops replying through channels, automations, and triggers, but keeps its configuration. Turn it back on and save to use it again.
Category limits access to the agent according to the categories authorized for each team. No category removes this category filter; organization permissions still apply. If the expected category is unavailable, ask an authorized person to review categories and teams instead of selecting a different one only to complete the save.
Response behavior
Section titled “Response behavior”Temperature
Section titled “Temperature”Controls output variety. Values near 0.0 favor more predictable replies; high values increase variation. Start low for support, extraction, and procedures. Increase gradually for ideation and creative writing, and validate with real replies.
Context memory
Section titled “Context memory”Defines how many recent messages from the conversation enter the next turn’s context. A larger window helps with long conversations but sends more content to the model. Reduce it only when older context is unnecessary.
Search earlier conversations
Section titled “Search earlier conversations”When enabled, this gives the agent a tool that can locate summaries of the same person’s earlier conversations with the same agent. It works only in an individual Hub conversation: it does not cross people, agents, rooms, person-to-person direct chats, or external channels. Search results contain title, date, topics, and a summary, not the full transcript.
This option differs from Context memory: memory reads recent messages in the current conversation, while search looks through summaries of other eligible conversations.
Reply length
Section titled “Reply length”There is no length setting on this page. You define how long an answer should be in the agent’s prompt — for example, “answer in three sentences at most” or “answer in one short paragraph”. Written into the prompt, the model plans the length and finishes its reasoning; enforced as a technical limit, it only cut the answer off mid-sentence. Short answers also do not lower cost on their own: billing follows the text the model actually generates.
Maximum tool calls
Section titled “Maximum tool calls”Limits how many tools the agent can chain in one turn before its final wrap-up. Each knowledge-base query, API call, transfer, or other tool counts as one call. The runtime reserves one additional step for the final answer and clamps legacy values above 20 to 20. The turn’s total time limit can still stop a flow before it reaches the selected number.
Replies on external channels
Section titled “Replies on external channels”Group messages
Section titled “Group messages”When you enable Group messages, choose a window from 10 to 60 seconds. WhatsApp QR, Z-API, Uazapi, Evolution, WhatsApp Official, Telegram, and the async API wait for the sequence and process incoming messages as one request. Each new message resets the wait, with a ceiling of three times the window measured from the first message.
When disabled, those channels still pass through the serialization queue, but each message forms its own group and is processed without the wait window. This setting does not apply to the Hub, public page, widget, Instagram Direct, or the sync API.
Split response into multiple messages
Section titled “Split response into multiple messages”When enabled, splitting turns each paragraph separated by a blank line into an independent delivery. It applies to Telegram, Instagram Direct, WhatsApp Official, and WhatsApp QR, Z-API, Uazapi, and Evolution connections. The Hub, public page, widget, and API ignore the setting.
Example of a reply delivered as three messages:
Sure, I can help.
2 PM is available.
Would you like me to confirm it?Sending photos does not depend on this setting. When the agent includes an image from a public URL in its reply, SquadOS delivers it as a photo on these external channels. With splitting off, the text accompanies the first photo; each additional image is sent as a separate photo. With splitting on, text is still split by paragraph. An ordinary link remains a link: the agent must choose to show the image rather than simply cite its address. Audio, video, and files do not receive this treatment.
You can say when the agent should show photos in its prompt without writing formatting instructions. AgentMaker can help write that rule. Between separate messages, the channel may show a typing indicator and apply a short pause; do not promise an exact cadence to the customer.
Delete Agent
Section titled “Delete Agent”The Danger Zone appears only to people with the agents.delete permission. The visible button is Delete Agent, but the operation retains the record and message history for analytics: it marks the agent as archived and inactive, deactivates active triggers, and removes its team links.
The dialog shows how many triggers will be deactivated and how many teams will lose the agent. To confirm, copy or type the agent name exactly, including capitalization and spaces, then choose Delete permanently.
The current interface has no restore action. Before confirming, record any configuration that must be rebuilt and check the effect on journeys that depend on the agent.
Validation checklist
Section titled “Validation checklist”After saving:
- leave the tab and return to confirm the persisted values;
- test one short reply and one that uses tools;
- if you changed memory or earlier-conversation search, validate an individual Hub conversation;
- if you changed grouping or splitting, test the matching external channel;
- check cost, timing, and format before releasing the agent to customers.
Continue with System Prompts, Models, and Testing Your Agent to validate the complete configuration.