Agents

Agents are the core building block of Callem Studio. An agent is an AI-powered voice assistant configured with a system prompt, a voice, a language model, and optional integrations. The agent configuration is split across multiple tabs, each controlling a different aspect of its behavior.

Creating an Agent

Navigate to Build > Agents
Click New Agent (for prompt-based) or New Workflow Agent (for flow-based)
Name your agent and start configuring

Organizing with Folders

As your agent library grows, you can group agents into folders for easier navigation.

Create a folder: click the + button in the agent sidebar and select Folder
Move an agent: drag and drop an agent onto a folder, or use the folder icon on hover to pick a destination
Rename / delete: right-click (or hover) a folder header to rename or delete it

Folders are flat (one level deep). Deleting a folder moves its agents back to the root. The collapsed/expanded state of each folder is remembered across sessions.

Agent Tabs

Each agent has the following configuration tabs:

Tab	Purpose
Model	System prompt, LLM provider/model, temperature, knowledge bases, tools
Voice	TTS voice selection, STT configuration, VAD, interruptions, background sound
Call Analysis	Post-call analysis fields and prompt
Advanced	Safety features, privacy, voicemail detection, observability

Model Tab

The Model tab controls the agent’s “brain” — what it says, how it reasons, and what data it has access to.

Welcome Message

The first thing the agent says when a call begins. Leave empty for the agent to wait for the caller to speak first.

System Prompt

The most critical configuration. It defines the agent’s identity, instructions, tone, and boundaries.

Write your system prompt as if you were briefing a real employee. Be specific about scenarios, responses, and what the agent should avoid. The more precise you are, the more reliable the agent’s behavior will be.

Example System Prompt

You are Sophie, a friendly receptionist at Acme Dental Clinic.
Your role is to answer incoming calls, schedule appointments, 
and answer questions about our services.

Rules:
- Always greet the caller warmly
- Ask for their name and reason for calling
- If they want an appointment, use the book_appointment tool
- Never provide medical advice
- If unsure, offer to transfer to the office manager

LLM Configuration

Parameter	Description	Default
Provider	The LLM provider (e.g. OpenAI, Anthropic, Azure)	—
Model	Specific model version (e.g. gpt-4o, gpt-4o-mini)	—
Temperature	Controls response randomness. `0` = deterministic, `1` = creative. Lower values are recommended for consistent voice agents.	`0.7`
Max Tokens	Maximum number of tokens the LLM can generate per response. Higher values allow longer answers but increase latency and cost.	`1024`

For voice agents, a temperature between 0.3 and 0.5 usually gives the best balance between natural-sounding and reliable responses. Higher values can cause the agent to go off-script.

Knowledge Base

Link one or more knowledge bases to give the agent access to domain-specific content. When a caller asks a question, the agent retrieves the most relevant content from the linked knowledge bases and uses it to answer. Retrieval Settings (available when at least one knowledge base is linked):

Setting	Description	Default
Max documents	Maximum number of text chunks to retrieve per query (1-10). Higher = more context but more tokens.	`6`
Relevance threshold	Minimum similarity score (0-1) for a chunk to be included. Higher = fewer but more relevant matches.	`0.6`

Tools

Link tools (custom functions) that the agent can invoke during a call. When the LLM determines that a tool should be called based on the conversation context, it passes the extracted parameters to the tool’s endpoint and uses the result to continue the conversation.

Voice Tab

The Voice tab controls how the agent sounds and how it processes caller speech.

Text-to-Speech (TTS)

Choose the voice the agent uses to speak. The available voices are loaded dynamically from configured providers. You can filter voices by language, gender, and provider. Some voices offer additional settings (like model selection) that appear automatically when relevant.

Speech-to-Text (STT)

Configure how caller speech is transcribed:

Setting	Description
Provider	The STT engine used for transcription
Language	Primary language for transcription accuracy

Voice Activity Detection (Semantic VAD)

Semantic VAD uses the LLM to determine when the caller has finished speaking, rather than relying solely on silence detection. This produces more natural conversations, especially when callers pause mid-sentence.

Setting	Description	Default
Enabled	Toggle semantic VAD on/off	Off
Config	Additional VAD configuration parameters	—

Enable Semantic VAD for complex conversations where callers may pause to think. Disable it for simple, fast-paced interactions (e.g. appointment confirmations) where silence-based detection is sufficient.

Silence Confirmation Delay (End of Speech Threshold)

The silence duration (in seconds) before the system considers the caller has finished speaking. Lower values make the agent more responsive but may cut the caller off. Higher values are more patient but introduce latency.

Setting	Value
Minimum	`0.5s`
Maximum	`5s`
Default	`1.5s`

Range	Behavior
0.5–1.0s	Very responsive, risks interrupting pauses
1.0–2.0s	Good balance for most use cases
2.0–5.0s	Very patient, best for elderly callers or complex topics

Interruption Config

Controls whether and how the caller can interrupt the agent while it’s speaking.

Setting	Description	Min	Max	Default
Enabled	Allow caller to interrupt the agent	—	—	Off
Minimum words	Minimum words the caller must say before the interruption is registered	`1`	`10`	`3`
Minimum duration	Minimum duration (in seconds) of caller speech before interruption triggers	`1`	`60`	`15`

Inactivity Timeout (Reminder Message)

Time in seconds before the agent sends a reminder message if the caller remains silent.

Setting	Value
Minimum	`6s`
Maximum	`30s`
Default	`15s`

Voice Speed

Adjust the speaking speed of the agent’s voice. 1.0 is normal speed. Available when the TTS provider supports speed adjustment (displayed dynamically based on provider settings).

Background Sound

Add ambient background audio to make calls feel more natural (e.g. office ambiance, call center sounds).

Setting	Description	Default
Enabled	Toggle background sound on/off	Off
Sound	Select from a library of pre-configured ambient sounds	—
Volume	Adjust the volume level (0–100%)	`50%`

Call Analysis Tab

Call Analysis is a post-conversation processing feature that uses an LLM to extract structured data from conversation transcripts after the conversation ends. It runs for both voice calls and chat sessions. This is useful for automatically categorizing conversations, extracting key information, and feeding data into your analytics dashboards.

How It Works

After a call ends, the full transcript is sent to an LLM along with your analysis prompt
The LLM extracts the requested fields based on the prompt and field definitions
The extracted data is stored as callAnalysis on the call record
This data can be used in analytics charts, alert rules, and API responses

Analysis Fields

Define the fields you want to extract from each call. Each field has a type:

Type	Description	Example
Text	Free-form text extraction	Summary, key takeaways, caller concerns
Selector	One value from a predefined list	Sentiment (`positive`, `neutral`, `negative`), Lead quality (`hot`, `warm`, `cold`)
Number	Numeric value extraction	NPS score, satisfaction rating (1-5)
Boolean	True/false determination	Appointment booked, issue resolved, callback requested

Field names cannot be changed after creation because they serve as identifiers in dashboards, filters, and alert rules. Choose descriptive, stable names.

Analysis Prompt

A custom prompt sent to the LLM along with the call transcript. Use it to give the LLM context about your business and instructions on how to analyze each field.

Minimum Duration

Calls shorter than this duration (in seconds) will not be analyzed. This avoids wasting LLM calls on hang-ups, wrong numbers, or very short interactions.

Advanced Tab

LLM Safety Features

Feature	Description
Guardrails	Enables safety filters on LLM responses to prevent harmful, inappropriate, or off-topic content

Privacy

Feature	Description
Anonymization	Automatically anonymizes personal data (names, phone numbers, addresses) in stored conversations

Voice Mail Detection

Automatically detects when a call reaches a voicemail or IVR system and hangs up to avoid wasting resources.

Setting	Description	Default
Enabled	Toggle voicemail detection on/off	Off
Initial detection delay	Seconds to wait before first detection attempt	`5`
Detection retry interval	Seconds between each detection retry	`5`
Max detection retries	Maximum number of detection attempts before giving up	`60`

Observability

Connect external observability platforms to trace and debug your agent’s LLM interactions:

Provider	Fields
Langfuse	Public Key, Secret Key, Base URL
Langsmith	API URL, API Key

This sends all LLM calls (prompts, responses, tool calls) to your observability platform for detailed tracing and debugging.

Best Practices

Write specific, actionable prompts

Vague prompts like “be helpful” lead to inconsistent behavior. Describe exact scenarios: “When a caller asks about pricing, quote from the attached knowledge base. Never invent prices.”

Lower the temperature for production agents

A temperature of 0.3-0.5 gives reliable, consistent responses. Only use higher values for creative or exploratory use cases.

Use call analysis to measure quality

Define analysis fields like sentiment, issueResolved, and callbackRequested to automatically track call quality at scale.

Test with real conversations

After configuring your agent, call the assigned phone number yourself. Listen for unnatural pauses, incorrect responses, or missed instructions. Use the built-in chat or webcall features for faster iteration.

Start simple, iterate

Begin with a minimal prompt and a single knowledge base. Add tools, analysis fields, and advanced settings once the basic flow works well.

Getting Started

Build

Deploy

Monitor

Settings

Agents

Agents

Creating an Agent

Organizing with Folders

Agent Tabs

Model Tab

Welcome Message

System Prompt

LLM Configuration

Knowledge Base

Tools

Voice Tab

Text-to-Speech (TTS)

Speech-to-Text (STT)

Voice Activity Detection (Semantic VAD)

Silence Confirmation Delay (End of Speech Threshold)

Interruption Config

Inactivity Timeout (Reminder Message)

Voice Speed

Background Sound

Call Analysis Tab

How It Works

Analysis Fields

Analysis Prompt

Minimum Duration

Advanced Tab

LLM Safety Features

Privacy

Voice Mail Detection

Observability

Best Practices

Getting Started

Build

Deploy

Monitor

Settings

​Agents

​Creating an Agent

​Organizing with Folders

​Agent Tabs

​Model Tab

​Welcome Message

​System Prompt

​LLM Configuration

​Knowledge Base

​Tools

​Voice Tab

​Text-to-Speech (TTS)

​Speech-to-Text (STT)

​Voice Activity Detection (Semantic VAD)

​Silence Confirmation Delay (End of Speech Threshold)

​Interruption Config

​Inactivity Timeout (Reminder Message)

​Voice Speed

​Background Sound

​Call Analysis Tab

​How It Works

​Analysis Fields

​Analysis Prompt

​Minimum Duration

​Advanced Tab

​LLM Safety Features

​Privacy

​Voice Mail Detection

​Observability

​Best Practices

Agents

Creating an Agent

Organizing with Folders

Agent Tabs

Model Tab

Welcome Message

System Prompt

LLM Configuration

Knowledge Base

Tools

Voice Tab

Text-to-Speech (TTS)

Speech-to-Text (STT)

Voice Activity Detection (Semantic VAD)

Silence Confirmation Delay (End of Speech Threshold)

Interruption Config

Inactivity Timeout (Reminder Message)

Voice Speed

Background Sound

Call Analysis Tab

How It Works

Analysis Fields

Analysis Prompt

Minimum Duration

Advanced Tab

LLM Safety Features

Privacy

Voice Mail Detection

Observability

Best Practices