Quickstart — Deploy Your First Agent

By the end of this page an agent you own, as editable TypeScript, is answering messages on one of your channels.

Prefer to send messages from your own backend instead of deploying code here? Start with the messaging quickstart.

1. Install the CLI

# No install step. Always runs the current version.
npx zavudev@latest --version

npm install -g zavudev
zavudev --version

# Download the binary for your platform from
# https://github.com/zavudev/zavu-cli/releases
# Then:
chmod +x ./zavu-macos-arm64
sudo mv ./zavu-macos-arm64 /usr/local/bin/zavudev

Working with a coding agent? Install the skills first and it will know every command on this page, plus defineAgent and defineTool:

npx skills add zavudev/zavu-skills

2. Log in

npx zavudev login

Your browser opens, you sign in, pick the project this agent will live in, and authorize. The CLI stores the key in ~/.zavu/credentials.json with mode 0600. Confirm which project you are pointed at:

npx zavudev whoami

3. Scaffold an agent

agents init is the guided path. It picks a factory agent, finds or creates the sender it runs on, writes the files, and registers the function.

npx zavudev agents init

To see what you can start from first:

npx zavudev agents catalog

Seven factory agents ship today, across sales, support and front desk. Some are voice agents that answer the phone; all of them also run on text channels.

Pull a specific agent

npx zavudev agents pull fermi --sender <senderId>

Scaffolds into ./fermi, registers the function, and sets the SENDER_ID secret from the sender you passed. Use --dir to scaffold elsewhere.

Start from an empty function instead

npx zavudev fn init

Gives you a bare index.ts to write defineAgent yourself. The Functions quickstart walks that path in full.

I have no sender yet

An agent answers on a sender, and a sender needs at least one channel. The fastest channel to turn on needs no phone number and no external account:

npx zavudev senders create --data '{"name":"Agent","enableSmsOneway":true}'

Recipients cannot reply on one-way SMS, so use it to verify the deploy works, then add a real channel. npx zavudev agents init --buy-number buys a number and creates the sender for you instead.

4. Install dependencies

cd fermi
npm install

Deploy works without this, but every local check does not: fn invoke, tsc --noEmit, and your editor all need the dev dependencies installed.

5. Look at what you got

The scaffold is one file, and it is the whole agent. (You can split it up later — imports between your files are resolved on deploy.)

index.ts

import { defineAgent, defineTool } from "@zavudev/functions"

defineAgent({
  senderId: process.env.SENDER_ID!,
  name: "Fermi",
  provider: "zavu",
  model: "openai/gpt-4o-mini",
  prompt: "You are Fermi, a qualification agent...",
  channels: ["voice", "whatsapp"],
})

defineTool({
  name: "lookup_account",
  description: "Find an existing account by phone number.",
  parameters: {
    type: "object",
    properties: { phone: { type: "string" } },
    required: ["phone"],
  },
  handler: async ({ phone }) => {
    // replace with your real lookup
    return { found: false }
  },
})

provider: "zavu" is our managed AI gateway. No API key of your own required; model usage is billed from your Zavu balance. Bring your own key by setting provider to openai, anthropic, google or mistral.

Any secret the agent needs beyond SENDER_ID is listed by agents pull when it finishes. Set each one before deploying:

npx zavudev fn secrets set CALENDAR_WEBHOOK_URL "https://..."

6. Try a tool without deploying

npx zavudev fn invoke --tool lookup_account --args '{"phone":"+14155551234"}'

This runs the handler on your machine, with no cloud round-trip and nothing charged. Use it to get the business logic right before anyone can talk to the agent.

7. Deploy

npx zavudev deploy

› status: bundling
› status: uploading
› status: publishing
› status: active
✓ Deployed in 14s
  Agents synced:
    + Fermi
  Tools synced:
    + lookup_account

Read the lines above the checkmark. Deploy prints its warnings before the success line, and they cover the cases where a green deploy did not do what it looks like: tools attached to an agent whose channels will never call them, or a second agent landing on a sender that already has one.

Your code is now the source of truth. Every deploy reconciles the live agent to match the file, so a defineAgent you delete deletes the agent.

8. Talk to it

Message the sender’s number from your phone, or call it if the agent has voice enabled. To check the reply without touching a real channel:

npx zavudev agents test --sender "$SENDER_ID" --message "what do you do?"

A dry run never executes tools, because a test must not cause real side effects. It tells you so in its warnings. Live conversations on every channel do call them.

9. Watch it run

# What the agent did: tools called, tokens, cost, latency
npx zavudev agents executions --sender "$SENDER_ID"

# Your handlers' console output, live
npx zavudev fn logs --tail

# Every message in and out
npx zavudev messages list --limit 10

Next steps

How agents work

What a deploy actually does, and what happens when a message arrives

Defining agents

Every field of defineAgent, including voice

Defining tools

Give the agent access to your systems

Knowledge bases

Ground the answers in your own documents

Voice agents

Answer and place phone calls with the same agent

Bring your framework

Deploy an eve project without restructuring it

Getting Started

Build agents

Send & receive

Operate

Developer tools

Integrations

Quickstart — Deploy Your First Agent

1. Install the CLI

2. Log in

3. Scaffold an agent

4. Install dependencies

5. Look at what you got

6. Try a tool without deploying

7. Deploy

8. Talk to it

9. Watch it run

Next steps

How agents work

Defining agents

Defining tools

Knowledge bases

Voice agents

Bring your framework

​1. Install the CLI

​2. Log in

​3. Scaffold an agent

​4. Install dependencies

​5. Look at what you got

​6. Try a tool without deploying

​7. Deploy

​8. Talk to it

​9. Watch it run

​Next steps

How agents work

Defining agents

Defining tools

Knowledge bases

Voice agents

Bring your framework

1. Install the CLI

2. Log in

3. Scaffold an agent

4. Install dependencies

5. Look at what you got

6. Try a tool without deploying

7. Deploy

8. Talk to it

9. Watch it run

Next steps