> ## Documentation Index
> Fetch the complete documentation index at: https://docs.callivox.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Creating an agent
> Create a chatting agent, fill in the General tab, pick an effort level, and try it out with the single-turn Test agent dialog.
You create chatting agents from **AI → Chatting Agents**. Creating one takes a name and a choice
of reply mode; everything else can be tuned afterwards.
## Create the agent
A menu offers three starting points.
| Option | What it does |
| ------------------------- | --------------------------------------------------- |
| **Prompting Agent** | "Free-form replies driven by a system prompt." |
| **Flow Agent** | "Script the conversation step by step on a canvas." |
| **Start from a template** | "Pick a curated agent and customize it." |
**Prompting Agent** and **Flow Agent** open a short dialog with a single required **Name**
field (for example, `Sales Assistant`). Click **Create**.
Nothing is created until you confirm, so a stray click can't leave an empty agent behind.
A Prompting Agent opens on its **General** tab. A Flow Agent opens straight onto its
[flow canvas](/ai-agents/flows).
### Starting from a template
**Start from a template** opens the template gallery. Filter by type — **All**, **Voice**, **Chat**
or **Assist** — or type into **Filter by category**, then click **Use template** on a card.
Callivox creates a new agent from that template and drops you into its editor with a reminder:
> This agent was created from a template — connect your tools and knowledge base to finish setup.
The gallery has no permanent sidebar entry; reach it from the **+ New agent** menu.
## The General tab
| Field | What it does |
| ------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Name** | What you and your team call the agent. It also appears in handover messages between teammates. |
| **Enabled** | The on/off switch. The helper text reads "Agent is active" or "Agent is turned off". A turned-off agent shows an amber **Disabled** pill in the header and stops replying everywhere. |
| **Description** | One line on what this agent handles. Keep it — teams use it to route conversations between agents. |
| **Let AI handle off-script messages** | Flow agents only. See [Flows](/ai-agents/flows). |
| **Effort** | Which tier of model runs this agent. See below. |
| **Creativity (temperature)** | A slider from 0 to 2. "Lower (near 0) = focused, consistent, predictable answers. Higher (toward 2) = more varied and creative, but less reliable. 0.2 is a good default for support." |
| **Max reply length (max tokens)** | "The longest reply the agent can produce in one turn. \~4 characters per token (≈750 words per 1,000 tokens). Higher allows longer answers but costs more." |
### Media input
The **Media input** group controls what a customer may attach: "Allow customers to attach media to
their messages."
* **Accept images** — the agent can look at photos and screenshots the customer sends.
* **Accept audio** — "Voice notes are transcribed to text automatically." This is always available.
* **Accept documents** — the agent can read files the customer attaches.
If images or documents aren't supported at the effort level you picked, the switch is greyed out
with a note saying so.
## Choosing an effort level
Callivox never asks you to pick a provider or a model. You pick how much thinking the agent should
do, and the platform runs that tier on the best available model.
| Effort | What it's for | Cost |
| ---------- | ----------------------------------------------------------------- | ------------------------- |
| **Low** | "Fast model for everyday bookings, FAQs and follow-ups." | 1 credit / conversation |
| **Medium** | "Stronger model for nuanced sales and support conversations." | 3 credits / conversation |
| **High** | "Top model for complex reasoning and heavy multi-tool workflows." | 10 credits / conversation |
New agents start on **Medium**. The footnote under the cards puts it plainly:
> The platform automatically runs each tier on the best available model — no provider or model
> setup needed.
Effort is charged per conversation, not per message. Start on **Medium**, watch a week of real
conversations, then move down to **Low** if the answers hold up. See
[How credits are spent](/billing/how-credits-are-spent).
## Test the agent before you bind it
The **Test** button in the editor header runs the agent once, against one made-up message, without
touching a real conversation.
The dialog reads "Send a message to this agent. Costs apply — this hits your configured LLM
provider."
It comes pre-filled with `Hello, how do I reset my password?`. Replace it with something a real
customer would send you.
The button shows **Running…** while it works.
You get the agent's **Reply**, plus a metrics row showing how many tools it called, how many
knowledge-base passages it pulled in, the tokens used, and the cost of the run. Any knowledge
it retrieved is listed underneath with the source document name and a match score.
A test run is a real AI call and costs credits, the same as a live reply.
This is a **single-turn** test — it sends one message and shows one reply. It won't hold a
back-and-forth conversation, so use it to sanity-check tone, tools and knowledge retrieval, then
bind the agent to a channel and try it for real.
Moving between tabs with unsaved edits raises **Discard unsaved changes?** — "You have unsaved
changes. If you leave now, they will be lost." Choose **Keep editing** to go back and save.
## Next steps
Give the agent its role, tone and rules — plus documents and tools.
Decide when the AI hands the customer to a person.
An agent replies only where you bind it.
Let specialists hand conversations to each other.