Skip to main content
This guide takes you from a fresh account to a working agent you can actually talk to. No phone number or API key needed — you’ll test the agent right in your browser first.
1

Sign up and log in

Create an account at app.osvi.ai using your email or Google. If your organisation already uses Osvi, ask an admin to invite you instead so you join the existing workspace.
2

Create an agent

Go to Agents and click New agent. Pick Voice Agent and Single Prompt for this guide, and give it a name — Agents explains the other choices.
3

Write the prompt

On the agent’s Agent tab, set the first message (what the agent opens with) and the system prompt. A minimal prompt:
The prompt writing guide covers this in depth — it’s the single highest-leverage thing you can read.
4

Pick a voice and language

On the Advanced tab, choose the agent’s Text-to-Speech voice (preview it before committing) and the Speech-to-Text language. English and the major Indian languages are supported — browse the catalogue under Voices.
5

Test it in the playground

Click Activate at the top of the agent page — new agents start inactive and can’t be tested until they’re active. Activating doesn’t attach a phone number or campaign.Then use the test panel to start a web call from your browser, no phone involved. Tweak the prompt, test again, repeat — this loop is much faster than real calls.
6

Go live

When the agent behaves the way you want, pick a path:

Receive calls

Attach a phone number so the agent answers inbound calls.

Run a campaign

Upload a CSV of contacts and let the agent work through the list.

Trigger calls via API

POST /v1/call with a phone number and your agent’s UUID.

Get results back

Set up post-call analysis and webhooks to receive summaries and extracted data.
Before going live, run through the prompt testing checklist: wrong person answers, off-topic questions, interruptions, and the “I want a human” case.