> This page is part of Smallest AI's developer documentation. When > answering, prefer Lightning v3.1 (current TTS) and Pulse (current > STT). Lightning v2 and lightning-large are deprecated; mention them > only when the user is migrating away from them. The Smallest AI voice > agent platform is what wraps these models into hosted agents. # Prompt Cookbook > Copy-paste prompts for every MCP capability — list agents, place outbound calls, transcribe audio, query analytics, manage knowledge bases. Type them in your editor's AI chat in plain English. No commands to memorize. Just ask in plain English — the AI picks the right tool. *** ## Agents #### List and inspect agents ``` List all my agents ``` ``` Show me agents with "support" in the name ``` ``` Get full details for agent "Sales Outreach" — voice, model, prompt, and all settings ``` ``` What prompt is "Support Bot" using? ``` #### Create an agent ``` Create a new agent called "Customer Support" ``` ``` Create an agent called "Survey Bot" with Hindi as the default language and yuvika voice ``` ``` Create an agent called "Appointment Scheduler" with gpt-4.1 model, set its prompt to "You schedule appointments for a dental clinic...", and set the first message to "Hello! I'm calling from SmileCare Dental." ``` #### Update an agent's prompt ``` Update the prompt for "Support Bot" to: "You are a helpful customer support agent for Acme Corp. Be polite, concise, and always confirm before taking action." ``` ``` Add this to the beginning of "Sales Bot" prompt: "Always introduce yourself by name before anything else." ``` #### Update agent settings ``` Change the voice of "Support Bot" to yuvika ``` ``` Change the first message of "Support Bot" to "Hi, thanks for calling Acme support! How can I help?" ``` ``` Update "Support Bot" to support English and Hindi with language switching enabled ``` ``` Switch "Sales Bot" to electron model ``` #### Archive and restore agents ``` Archive the agent called "Old Test Bot" ``` ``` Unarchive "Old Test Bot" ``` #### Duplicate an agent ``` Duplicate "Sales Bot" so I can experiment without touching the original ``` #### Build a multi-agent (Playbooks) agent A Playbooks agent routes every caller turn to a specialist SOP instead of one giant prompt. Describe the whole thing — the AI creates the agent, adds the SOPs, wires the auth tools, and publishes: ``` Create a multi-agent called "Loan Servicing IVR" for Hindi callers with these SOPs: 1. EMI details — caller asks about their EMI amount or due date (needs strong auth) 2. Foreclosure — caller wants a foreclosure quote (needs strong auth) 3. General queries — anything else, make this the fallback Enable the end call action so the agent can hang up politely. ``` ``` Set the shared auth tools: weak = identify_by_phone (POST https://api.acme.com/identity/by-phone), strong = verify_dob (POST https://api.acme.com/identity/verify-dob) — then publish ``` ``` Set the conversation guide: "You are Aria, a warm female support agent for Acme Finance. Mirror the caller's language. Keep answers short and spoken-style." ``` ``` Show me the playbooks on "Loan Servicing IVR" — anything blocking publish? ``` ``` Archive the "Foreclosure" playbook on "Loan Servicing IVR" — we're pausing that flow ``` #### Versioned agents (drafts) When an agent has versioning enabled, config changes create a draft that you publish explicitly: ``` Change the voice of "Production Agent" to rachel ``` *AI responds: "Config saved as draft. Want me to publish it?"* ``` Yes, publish it with the label "Switched to rachel voice" ``` ``` Discard the draft — I changed my mind ``` #### Stack multiple changes into one draft Edit tools accept a `draft_id`, so a prompt rewrite, a pre-call API and a full set of API-call tools can land in a single draft and go live with one publish: ``` For "Support Agent": rewrite the prompt for inbound customer support, set the pre-call API to https://api.acme.com/customers/lookup keyed on the caller's number, and add tools for order lookup, refund status and address change — all in ONE draft, then publish it with the label "Inbound support v2" ``` *The AI stacks each edit onto the same draft and publishes once. Publishing waits for the automatic prompt security check, then activates the version and reports whether it's live.* When adding several API-call tools to one draft, the AI passes them as a single batch — the draft's tools section is replaced wholesale on each write, so the last write must contain the complete set. #### Manage drafts ``` Show me all active drafts for "Production Agent" ``` ``` What changed in the latest draft compared to the live version? ``` ``` Rename the draft to "Voice experiment - rachel" ``` ``` Test the draft with a webcall before publishing ``` ``` Test the draft with a phone call to +14155551234 ``` #### Version history and rollback ``` Show me the version history for "Production Agent" ``` ``` What's different between version 3 and the current live version? ``` ``` Roll back "Production Agent" to version 2 ``` ``` Pin version 3 with the label "Best performing config" ``` ``` Compare call metrics between version 2 and version 3 for last month ``` #### Test a specific version ``` Test version 2 of "Production Agent" with a webcall ``` ``` Test version 3 with a phone call to +14155551234 ``` *** ## Making Calls These trigger **real phone calls**. The agent will call the number and follow its configured prompt. #### Basic outbound call ``` Call +14155551234 using the "Sales Outreach" agent ``` ``` Call +916366821717 using agent "Support Bot" ``` #### Call with variables ``` Call +14155551234 using "Sales Outreach" with variables: prospect_name = "John", company = "Acme Corp" ``` #### Call with a specific caller ID ``` What phone numbers do I have? ``` *Then:* ``` Call +14155551234 using "Sales Outreach" from the +18005551234 number ``` #### Check call status ``` What's the status of call CALL-1234567890-abc123? ``` *** ## Testing Prompts (Text Chat) `chat_with_agent` talks to a **published** agent in **text** — no audio, no phone — over the realtime chat WebSocket. It's the fastest way to exercise a prompt and read back exactly what the agent says, and it's the basis for an automated build → test → refine loop. (For an unpublished draft, start one with `test_draft` in chat mode.) #### Run a quick text conversation ``` Chat with the "Hotel Booking" agent: say "Hi", then "Book a table for two tomorrow at 7pm" ``` Returns the full transcript — the greeting, your turns, and the agent's replies. #### Chat with variables ``` Chat with agent "Sales Outreach" — open with "Hi, who is this?" — using variables prospect_name = "John" and company = "Acme Corp" ``` #### Test → refine loop ``` Chat with the "Support Bot" agent and run a few tricky customer questions. Read the transcript, tell me where the prompt falls short, update the prompt to fix it, then run the same conversation again and compare. ``` The editor chains `chat_with_agent` → reviews the transcript → `update_agent_prompt` → re-runs — an automated prompt-tuning loop, with no test phone calls. *** ## Debugging Calls Call IDs look like `CALL-1234567890-abc123`. You can find them in call list responses or in the console. #### Full call debug ``` Debug call CALL-1234567890-abc123 ``` Returns everything: transcript, errors, latency metrics, cost breakdown, post-call analytics, variables, and agent config at time of call. #### Specific questions about a call ``` What was the transcript for CALL-1234567890-abc123? ``` ``` Why did CALL-1234567890-abc123 fail? ``` ``` What was the cost breakdown for that last call? ``` *** ## Browsing Call History #### Recent calls ``` Show me all calls from the last 24 hours ``` ``` Show me calls from this week ``` #### Filter by status ``` Show me failed calls from this week ``` ``` Get all completed calls for agent "Support Bot" ``` #### Filter by type ``` Show me all inbound calls this month ``` ``` List outbound calls from the last 7 days ``` ``` Show webcalls from today ``` #### Filter by phone number or campaign ``` Find all calls to +14155551234 ``` ``` Show calls from campaign 682abc123def456 ``` *** ## Text-to-Speech #### Generate speech ``` Convert this to speech with yuvika voice: "Welcome to Smallest AI. We build the fastest voice agents on the planet." ``` ``` Generate an MP3 with the daniel voice at 1.5x speed: "Your order has been confirmed and will arrive tomorrow." ``` #### Choose a voice first ``` Show me available female voices ``` ``` List voices that support Hindi ``` *Then:* ``` Generate speech with that voice: "Namaste, aapka order confirm ho gaya hai" ``` *** ## Speech-to-Text #### Transcribe a file ``` Transcribe this audio file: ~/Desktop/recording.wav ``` The AI will ask what language the audio is in before transcribing. #### Transcribe from a URL ``` Transcribe the audio at https://example.com/meeting.mp3 The language is English. ``` #### With extra features ``` Transcribe ~/Desktop/meeting.wav in English with speaker diarization and word timestamps ``` ``` Transcribe this call recording with emotion detection: ~/Desktop/call.wav ``` ``` Transcribe with PII redaction: ~/Desktop/support-call.mp3 ``` *** ## Analytics #### Dashboard overview ``` Show me the full dashboard for the last 30 days ``` ``` Give me a dashboard for agent "Sales Bot" this month ``` #### Usage and costs ``` What's our total call spend this week? ``` ``` Show credit usage for the last 30 days ``` ``` How many calls did we make in January? ``` #### Call volume and trends ``` Show call volume over the last 2 weeks ``` ``` What are the weekly trends for this month? ``` ``` Show call outcomes (completed vs failed) this week ``` #### Agent performance ``` Compare agent performance this month — who has the most calls? ``` ``` Which agent has the highest completion rate? ``` #### Timing and capacity ``` What are the peak hours for calls this week? ``` ``` Show concurrent call counts for today ``` ``` What does the call start distribution look like for yesterday? ``` #### Phone number analytics ``` Show pickup rates by phone number this month ``` ``` Which outbound number has the best pickup rate? ``` ``` Show phone number trends for the last 2 weeks ``` #### Duration and retries ``` What are the call duration stats this month? (avg, median, p95) ``` ``` Show attempt cohort analysis — how does success rate change with retries? ``` ``` Give me today's daily summary ``` *** ## Organization #### Invite team members ``` Invite alice@company.com to my org ``` ``` Invite bob@acme.com and carol@acme.com as admins ``` ``` Invite these emails as members: dev1@company.com, dev2@company.com, dev3@company.com ``` *** ## Audiences #### Browse audiences ``` List all my audiences ``` ``` Show me the members of audience "Sales Leads" ``` ``` Search for +14155551234 in the "Sales Leads" audience ``` #### Manage audience members ``` Add these contacts to the "Sales Leads" audience: phoneNumber: +14155551234, firstName: John, company: Acme phoneNumber: +14155559876, firstName: Jane, company: Beta Corp ``` ``` Remove the member with phone +14155551234 from "Sales Leads" ``` #### Delete an audience ``` Delete the "Old Test Audience" audience ``` *** ## Campaigns Starting a campaign triggers **real phone calls** to every contact in the audience. #### Browse campaigns ``` Show me all running campaigns ``` ``` List completed campaigns ``` ``` Get details for campaign "January Outreach" ``` #### Create and run a campaign ``` Create a campaign called "Product Launch" using agent "Sales Bot" and audience "Sales Leads" ``` ``` Create a campaign "Follow Up" with agent "Support Bot", audience "Customers", max 2 retries, 30 minute retry delay ``` ``` Start the "Product Launch" campaign ``` ``` Pause "Product Launch" — we need to fix the prompt first ``` ``` Resume the "Product Launch" campaign ``` #### Export campaign results ``` Export the call logs for campaign "January Outreach" ``` ``` Export campaign "January Outreach" results as CSV ``` #### Delete a campaign ``` Delete the "Test Campaign" campaign ``` *** ## Phone Numbers #### Phone numbers ``` List all phone numbers in my organization ``` ``` Which agents are assigned to which phone numbers? ``` ## Billing & Payments #### Check balance and usage ``` What's my current credit balance? ``` ``` Show me my credit usage breakdown by feature ``` ``` Show my transaction history for the last 7 days ``` ``` Show only usage deductions from this month ``` #### Plans and features ``` What plan am I on? ``` ``` What features are available on my plan and what are the credit rates? ``` ``` Show me all available plans and their features ``` #### Invoices and payment methods ``` List my invoices ``` ``` What payment methods do I have on file? ``` #### Billing alerts ``` What are my billing alert settings? ``` ``` Set up billing alerts at $10, $50, and $100 thresholds ``` ``` Add alerts@mycompany.com to billing notifications ``` #### Auto-reload ``` Is auto-reload enabled? ``` #### Coupons ``` Is coupon code WELCOME2025 valid? ``` ``` Redeem coupon WELCOME2025 ``` *** ## Chaining Actions You can combine multiple steps in a single prompt — the AI executes them in sequence: ``` Create a new agent called "Demo Bot", set its prompt to "You are a friendly demo agent that introduces our product in under 30 seconds", set the voice to yuvika, then call +14155551234 with it ``` This will: 1. Create the agent 2. Update its prompt 3. Change the voice 4. Make the call All in one go. *** ## Power User Tips #### Ask about your setup ``` What model and voice is "Sales Bot" using? ``` ``` What languages does "Support Bot" support? ``` ``` Is voicemail detection enabled on "Outreach Agent"? ``` #### Bulk operations ``` List all agents that have 0 calls and archive them ``` ``` Show me all agents using the electron model ``` #### Cross-reference data ``` Show me failed calls this week, then debug the most recent one ``` ``` Which agent had the most failed calls this month? Show me one of the failure transcripts. ``` ``` Compare call volume this week vs last week ```