Create and Configure an Assistant - rapida.ai documentation

An assistant is the central object in Rapida. It holds your LLM configuration, system prompt, experience, listen and speak settings, tools, knowledge bases, and deployment channels — all versioned and deployable across phone, web, and messaging from one place.

Before creating an assistant, set up credentials for your LLM, STT, and TTS providers in Integration → Vault. The creation wizard will ask you to select a provider — credentials must exist first.

Create your first assistant

Navigate to Assistants

Go to Assistants in the main sidebar. Click Add new assistant to open the creation wizard.

Select your LLM provider and model

Choose your LLM provider and the specific model to power this assistant. Supported providers: OpenAI, Anthropic, Azure OpenAI, Google Gemini, Cohere, Vertex AI, or a custom AgentKit gRPC backend.Each provider requires a vault credential. The model you select here sets the default — you can tune all parameters after creation.

Write your system prompt

Define the assistant’s persona, scope, and behaviour in the Instructions field. This becomes the system prompt sent to the LLM at the start of every conversation.Use {{variable}} syntax to inject dynamic values at runtime — caller name, account ID, or any context passed when a call is initiated.

Add tools (optional)

Attach tools to extend what the assistant can do mid-conversation — query a knowledge base, call an external API, transfer the call, or end the session. Tools can also be added or modified after creation.

Name and create

Give the assistant a name and description, then click Create Assistant. The assistant is created at version v1 in draft state. Configure voice, deployments, and advanced settings before going live.

A newly created assistant has no deployment attached. It will not handle live calls or web sessions until you configure at least one deployment under Configure assistant → Deployments.

Next best steps

Prompt templating

Add runtime variables ({{ args.* }}, {{ message.* }}, {{ system.* }}) so one prompt works across many customer contexts.

Create new version

Make changes safely in draft, test, and release explicitly without impacting live traffic.

Configure your assistant

After creation, open Configure assistant from the top-right of the assistant page. Configuration is organized into six areas:

Prompt & Model

System prompt, model selection, temperature, token limits, and advanced LLM parameters.

Configuration

Experience, Listen, and Speak settings for runtime behavior, speech input, and spoken output.

Knowledge & Retrieval

Attach knowledge bases, set retrieval method (hybrid, semantic, text), top-K, score threshold, and reranking.

Tools

Knowledge retrieval, API request, endpoint invocation, call transfer, call hold, and end-of-conversation tool types.

Deployments

Phone, web widget, web app, WhatsApp, and API deployment channels — each with its own voice and experience settings.

Webhooks & Analysis

Post-call webhooks to downstream systems and analysis pipelines for conversation scoring and custom metrics.

Prompt and model

The prompt and model configuration defines what your assistant knows, how it reasons, and how it generates responses.

System prompt

The system prompt is your primary control surface. It sets the assistant’s persona, scope of knowledge, constraints, and tone. Well-written prompts are the single biggest lever for assistant quality.

For voice: Keep sentences short and natural. Avoid bullet lists, markdown, and symbols — the TTS engine reads punctuation literally. Write instructions the way you’d brief a call centre agent.

Dynamic variables — inject runtime context into your prompt using {{variable_name}} syntax. Variables are automatically detected from your prompt and can be populated via the SDK when initiating a call:

You are an assistant for {{company_name}}. The caller's name is {{caller_name}}.
Their account tier is {{account_tier}}. Always address them by first name.

Multi-turn prompt structure — the prompt editor supports system, user, and assistant roles. Add example exchanges to shape the tone and structure of responses without increasing latency.

LLM model parameters

OpenAI / Azure OpenAI parameters

Parameter	Default	Range	Notes
Model	`gpt-4o`	—	gpt-4, gpt-4o, gpt-4.1-mini, o3, o4-mini, and more
Temperature	`0.7`	0–2	Higher = more creative, lower = more deterministic
Top P	`1`	0–1	Nucleus sampling; use with temperature, not instead
Max completion tokens	`2048`	≥1	Caps response length
Frequency penalty	`0`	-2 to 2	Reduces word repetition
Presence penalty	`0`	-2 to 2	Encourages topic diversity
Stop sequences	—	up to 4	Tokens that halt generation
Tool choice	`auto`	none / auto / required	Control when tools are called
Reasoning effort	—	low / medium / high	For o-series models only
Response format	—	text / json_object / json_schema	For structured output use cases

Anthropic parameters

Parameter	Default	Range	Notes
Model	`claude-opus-4`	—	Opus 4, Sonnet 4, Sonnet 3.7, Haiku 3.5
Max tokens	`1028`	≥1	Caps response length
Temperature	`1.0`	0–1	—
Top P	—	0–1	Nucleus sampling
Top K	—	—	Top-K sampling
Stop sequences	—	—	Halt generation tokens
Extended thinking	—	JSON config	Claude’s built-in reasoning mode

AgentKit — custom LLM backend

AgentKit replaces the built-in LLM with your own gRPC server. Rapida streams user speech transcripts to your server and synthesizes your text responses to audio in real time.

Parameter	Notes
Server URL	`host:port` of your gRPC service (e.g. `my-server.example.com:50051`)
TLS certificate	Optional — path to CA cert for mutual TLS
Metadata	Key-value map passed as gRPC metadata headers

Your server receives a bidirectional Talk stream. Rapida handles all audio — VAD, STT, TTS, telephony. Your server only handles text in / text out.See the AgentKit guide for implementation examples with LangChain, CrewAI, and Anthropic Claude.

Runtime model overrides

Outbound phone calls can override model provider options for a single conversation through CreatePhoneCallRequest.options. Pass the same option keys used by the assistant provider model, plus the connection keys below when you need to route a call to a different credential or model endpoint.

{
  "options": {
    "model.name": "gpt-4o-mini",
    "model.temperature": 0.2,
    "model.credential_id": "2230142097179373568",
    "model.connection.transport": "chat_complete",
    "model.connection.endpoint": "/v1/chat/completions"
  }
}

Option key	Type	Description
`model.name` and provider-specific `model.*` keys	varies	Override the saved model provider options for this call, such as model name, temperature, token limits, or response format.
`model.credential_id`	`string` / `number`	Use a different saved provider credential for this call.
`model.connection.transport`	`string`	Override the model connection transport.
`model.connection.endpoint`	`string`	Override the model connection endpoint.

Use model runtime overrides for controlled routing, testing, or tenant-specific credentials. Invalid model credentials or connection settings can prevent the call from starting.

Configuration

Configuration controls the runtime behavior of each deployment: how a session starts, how user audio is captured and transcribed, and how assistant responses are spoken back. These settings directly affect latency, accuracy, and caller experience.

Listen — STT, VAD, EOS, and noise processing

For telephone deployments (8kHz audio), choose STT providers with dedicated telephony models: Deepgram nova-3, Azure Speech (telephony mode), or AssemblyAI. For high-fidelity web audio (16kHz+), all providers perform well.

STT providers: Deepgram, AssemblyAI, Azure Cognitive Speech, Google Speech, OpenAI Whisper, Cartesia, Sarvam AI

Audio setting	Default	Range	What it controls
STT language	`multi`	Provider-dependent	Primary transcription language; `multi` enables auto-detection
STT model	`nova-3`	Provider-dependent	Accuracy vs. latency tradeoff per provider
Noise cancellation	`rn_noise`	—	RNNoise background noise suppression applied before VAD and STT
EOS backoff	`2`	0–5	Re-prompts (“Are you there?”) before ending session on silence

Voice Activity Detection (VAD) — determines when the caller is speaking. Three providers available: Silero VAD (default, best general-purpose), TEN VAD (lowest latency), and FireRed VAD (best noise robustness). See Voice Activity Detection for provider details, parameters, and tuning guidance. End of Speech (EOS) — determines when the caller has finished their turn. Three providers available: Silence-Based (default, simple fixed timeout), Pipecat Smart Turn (audio model, catches prosodic cues), and LiveKit Turn Detector (language model with conversation history). See End of Speech Detection for provider details, parameters, and tuning guidance.

EOS is the most impactful latency lever after model selection. With Silence-Based EOS at 700ms, the assistant waits 0.7 seconds of silence before responding. Model-based providers (Pipecat, LiveKit) can reduce this wait by detecting turn completion before the full silence timeout expires — the assistant responds faster while cutting off callers less often.

Speak — TTS and pronunciation

TTS providers: ElevenLabs, Cartesia, Deepgram Aura, OpenAI TTS, Azure Speech, Google Cloud TTS, PlayHT, Sarvam AI

Speaker setting	Default	What it controls
Voice ID	Provider-dependent	The specific voice model. Supports cloned brand voices on ElevenLabs and Resemble
Speed / emotion	Normal	Provider-specific; Cartesia exposes `slowest → fastest` and emotion controls (`anger:high`, `positivity:low`, etc.)
Sentence boundaries	`.!?;:—…`	Characters that flush a TTS chunk for immediate playback. Tuning these reduces time-to-first-audio
Conjunction break	`240 ms`	Pause inserted at conjunctions (and, but, or). Adds natural rhythm to long sentences
Pronunciation dictionaries	—	Normalize how abbreviations, currencies, dates, URLs, and technical terms are spoken

Add your product names, acronyms, and technical terms to the pronunciation dictionary to prevent the TTS engine from mispronouncing them. This is especially important for brand names and medical or legal terms.

Knowledge and retrieval

Attach one or more knowledge bases to give your assistant access to documents, FAQs, product data, or any content indexed in Rapida.

Setting	Default	Range	Notes
Retrieval method	`hybrid`	hybrid / semantic / text	Hybrid combines vector similarity and full-text search — best default for most use cases
Top K	`5`	1–20	Number of document chunks retrieved per query. Higher = more context, higher latency
Score threshold	`0.5`	0–1	Minimum relevance score. Raise to reduce noise; lower to improve recall
Reranking	`off`	—	Cohere reranker re-scores retrieved chunks before passing to the LLM. Improves precision at the cost of a small latency increase

See Create a Knowledge Base for document ingestion, connector setup, and embedding model configuration.

Tools

Tools extend what your assistant can do mid-conversation without breaking the voice flow. The LLM decides when to call a tool based on its description — write clear, specific descriptions.

Knowledge Retrieval

Query a Rapida knowledge base in real time. Returns the most relevant document chunks to the LLM as context.

API Request

Call any external HTTP endpoint mid-conversation — CRM lookups, inventory checks, booking APIs. Define the request schema and the LLM populates the parameters from conversation context.

Endpoint (LLM Call)

Invoke a Rapida endpoint — a separately configured LLM prompt — for specialised sub-tasks: classification, extraction, or complex reasoning offloaded from the main conversation model.

Transfer Call

Hand an active phone call to a human agent, queue, department number, or SIP endpoint when the assistant should escalate the conversation.

Put On Hold

Pause the call and play hold music while a backend process completes — useful when a lookup or action takes longer than a voice turn allows.

End of Conversation

Terminate the call programmatically when the assistant determines the conversation objective has been met.

Tool names must use only letters, numbers, and underscores (no spaces). The description is passed directly to the LLM — it determines when and whether the tool is called. Be specific: “Search the product knowledge base for pricing information” outperforms “Search knowledge base”.

Conversation experience

These settings control the runtime behaviour of a live session — what happens when the caller goes silent, how long sessions last, and what the assistant says at the start of a call.

Setting	Default	Range	Notes
Greeting message	—	—	Spoken immediately when a call connects. Supports `{{variable}}` for personalisation
Unclear input timeout	`0.5 s`	0.5–5 s	Wait before asking the user to repeat unclear or interrupted input
Unclear input message	`I didn't catch that. Could you repeat that?`	Up to 250 characters	Spoken or shown when the assistant could not understand the user
Idle message	`Are you there?`	—	Spoken after the idle timeout expires without user input
Idle silence timeout	`30 s`	5–120 s	Time before the idle message triggers
Idle backoff	`2`	0–5	How many times the idle message repeats before ending the session
Max session duration	`300 s`	180–600 s (phone)	Hard cap on session length — protects against runaway calls
Error message	—	—	Spoken when the assistant encounters an unrecoverable error

Webhooks and post-call analysis

Webhooks fire for call lifecycle events such as call.received, call.ringing, call.started, call.hangup, call.ended, call.failed, and call.cancelled; WebRTC media events such as webrtc.connected, webrtc.audio_track_received, webrtc.reconnecting, webrtc.failed, and webrtc.disconnected; and conversation lifecycle events such as conversation.begin, conversation.resume, conversation.completed, and conversation.error. Completed conversation webhooks include transcripts, metadata, metrics, and any successful post-call analysis output. Analysis pipelines run before the conversation.completed webhook is recorded. They invoke a configured Rapida endpoint — typically an LLM prompt — against the conversation transcript to produce structured output: sentiment scores, intent labels, CSAT predictions, compliance flags, or any custom metric. Successful analysis output is added to webhook metadata as analysis.<analysis_name>. See Webhooks and Analysis for full configuration details.

Version control

Every change to your assistant’s prompt, model, or parameters creates a new version. Versions let you safely iterate without affecting live traffic.

New versions are not deployed automatically. After creating a version, it stays in draft state until you explicitly release it. Live deployments continue running the previously released version until you promote the new one.

Action	What it does
Create version	Saves a new draft with updated prompt/model config and a change description
Release version	Promotes the version to live — all active deployments switch immediately
Rollback	Re-release a previous version to revert a bad change

This model lets you run A/B tests, stage changes in a debugger deployment before pushing to phone, and maintain a full audit trail of every prompt change — who made it, when, and why.

Next steps

Set up a phone deployment

Connect a telephony provider and go live with inbound and outbound calling.

Add a knowledge base

Index documents, wikis, and data sources for retrieval during calls.

Configure webhooks

Stream call events and transcripts to external systems in real time.

Build a custom LLM backend

Use AgentKit to plug your own reasoning engine into Rapida’s audio pipeline.

​Create your first assistant

​Next best steps

Prompt templating

Create new version

​Configure your assistant

Prompt & Model

Configuration

Knowledge & Retrieval

Tools

Deployments

Webhooks & Analysis

​Prompt and model

​System prompt

​LLM model parameters

​Runtime model overrides

​Configuration

​Listen — STT, VAD, EOS, and noise processing

​Speak — TTS and pronunciation

​Knowledge and retrieval

​Tools

Knowledge Retrieval

API Request

Endpoint (LLM Call)

Transfer Call

Put On Hold

End of Conversation

​Conversation experience

​Webhooks and post-call analysis

​Version control

​Next steps

Set up a phone deployment

Add a knowledge base

Configure webhooks

Build a custom LLM backend

Create your first assistant

Next best steps

Configure your assistant

Prompt and model

System prompt

LLM model parameters

Runtime model overrides

Configuration

Listen — STT, VAD, EOS, and noise processing

Speak — TTS and pronunciation

Knowledge and retrieval

Tools

Conversation experience

Webhooks and post-call analysis

Version control

Next steps