Product · Agent builder

Build agents for every customer workflow.

Create specialized phone agents for sales, support, collections, reminders, feedback, and operations. Configure prompts, voices, accents, welcome messages, timezone context, and call behavior from one builder.

Book a demo View API docs

28 Thunder Emotion voices30+ Indian languages100+ accents & dialectsSub-300ms responses

app.ravan.ai — agent builder

Agni agent builder: prompt, voice and accent selection, tools, and test call

Illustrative product view

Configuration

Every behavior, configured per agent.

Each agent is its own operational unit. Set how it speaks, what it says first, how it handles interruptions and silence, and what data every call should produce.

Prompt configuration

Define how the agent speaks, qualifies, resolves, and escalates. Write and manage system prompts per agent — one workflow, one prompt, full control.

Thunder Emotion voice library

Choose from 28 voices in the Thunder Emotion voice library — male and female options across regional accents — and pick the style that fits your audience.

Welcome messages & timezone context

Set the opening line customers hear and give the agent timezone context so greetings, schedules, and follow-ups stay locally correct.

Call behavior controls

Tune interruption sensitivity, voicemail detection, silence handling, ring duration, and maximum call length per agent.

Memory across calls

Enable memory so the agent retains context across multiple calls with the same contact — useful for follow-up sequences and multi-step workflows.

Post-call analysis configuration

Define what every call should produce: summaries, sentiment classification, dispositions, and the structured data fields your team needs.

Safe testing

Test agents safely before they speak to real customers.

Every agent can be tested with live web calls from the browser before it touches a phone number. Iterate on prompts and behavior, review transcripts, and only then move the agent to production.

Run live web calls from the browser — no phone number or telephony setup required
Iterate on prompts, voices, and behavior, then re-test in seconds
Keep agents in draft until they pass review; nothing reaches customers by accident
Manage active and inactive agents from one dashboard as workflows change

When the agent is ready, deploy it to inbound numbers or outbound campaigns.

Beyond the prompt

Agents are more than a script.

The builder is where each agent starts — knowledge, tools, and analytics make it operational.

Connect knowledge bases

Attach approved FAQs, policies, catalogs, and pricing so the agent answers from your content — not generic AI guesses. Explore knowledge bases →

Attach tools & functions

Equip agents to transfer calls, navigate IVRs, trigger custom API functions mid-call, and hand off to humans with context. Explore APIs & webhooks →

Review every conversation

Each call produces transcripts, summaries, sentiment, and the structured fields you configured in post-call analysis. Explore call analytics →

FAQ

Agent builder questions, answered.

How many voices are available?

Agni offers 28 voices in the Thunder Emotion voice library — including Iris, Brennan, Rowan, Celeste, Theodore, Finn, Vivienne, Patrick, Stella, Luna, Dominic, and Julian — across male and female options with varying regional accents. Each agent can be configured with a different voice.

What functions can an agent perform during a call?

Each agent supports: End Call (graceful termination), Transfer Call — static (to a fixed number) or dynamic (to a number determined at runtime), IVR / press-digit flows (listen for DTMF input and branch), and Custom Functions (execute a webhook or API call mid-call and use the response to continue the conversation).

What is the AI temperature setting?

Temperature controls how creative versus deterministic the agent's responses are. Lower temperature gives more consistent, scripted responses — better for collections and compliance workflows. Higher temperature gives more natural, adaptive conversation — better for telesales and support. You can tune this per agent.

What is the Memory toggle?

Memory allows the agent to retain context across multiple calls with the same contact. When enabled, the agent remembers previous conversation details — useful for follow-up calls, reminder sequences, or multi-step onboarding flows. Available on Scale and Enterprise plans, with a metered charge of ₹2/min when active during a call.

More questions? Read the full FAQ or talk to sales.

Build your first agent this week.

Walk through the agent builder with our team — prompts, voices, testing, and deployment on a live use case from your own workflows.

Talk to sales View API docs

or call our AI agent directly+91 11 4056 6601Available 24/7 · Hindi, Hinglish, EnglishChat on WhatsApp

Book a demo