Tenzro CloudDocs

Quickstart

Get up and running with Tenzro Cloud in under 5 minutes. This guide walks you through creating your first project, obtaining an API key, and making your first API call.

1. Create an Account

Visit console.cloud.tenzro.com and sign in with your Google account. Your first project will be created automatically.

2. Get Your API Key

Navigate to API Keys in the sidebar and click Create API Key. Copy your key - you'll need it for authentication.

3. Install the SDK

npm install @tenzro/cloud

4. Initialize the Client

index.ts
import { Tenzro } from '@tenzro/cloud';


const client = new Tenzro({
  apiKey: process.env.TENZRO_API_KEY!,
  projectId: process.env.TENZRO_PROJECT_ID, // optional - sets default project
});

5. Make Your First AI Call

Simple chat - just provide a prompt:

chat.ts
// Simple API - uses default model (gemini-2.5-flash)
const response = await client.ai.chat('What is Tenzro Cloud?');
console.log(response);


// With options
const answer = await client.ai.chat('Explain vector databases', {
  temperature: 0.7,
  model: 'gemini-2.5-pro',
});

6. Store and Retrieve Data

Use the key-value store:

kev.ts
// Get a key-value store by name
const store = await client.kev.store('sessions');


// Set a value
await store.set('user:123', { name: 'John', role: 'admin' });


// Get the value
const user = await store.get('user:123');
console.log(user.name); // "John"


// Delete the value
await store.delete('user:123');

7. Vector Search

Semantic search with automatic embeddings:

vec.ts
// Get a vector database by name
const vectors = await client.vec.db('knowledge-base');


// Insert documents (embeddings auto-generated)
await vectors.upsert({
  documents: [
    { id: 'doc-1', text: 'Machine learning transforms data into insights' },
    { id: 'doc-2', text: 'Vector databases enable semantic search' },
  ],
});


// Query with natural language (embedding auto-generated)
const results = await vectors.query({
  text: 'How does ML work?',
  topK: 5,
});


for (const match of results) {
  console.log(match.metadata._text, 'score:', match.score);
}

8. Create an AI Agent

Build agents with tools:

agent.ts
import { Tenzro, tool } from '@tenzro/cloud';


// Define a custom tool
const weatherTool = tool(
  'get_weather',
  'Get current weather for a city',
  {
    city: { type: 'string', description: 'City name' },
  },
  ['city']
);


// Create an agent
const agent = await client.agents.create({
  agentName: 'Weather Assistant',
  endpointId: 'your-endpoint-id', // Create via AI > Endpoints
  systemPrompt: 'You help users check the weather.',
  orchestrationPattern: 'SINGLE',
  tools: [weatherTool],
});


// Chat with the agent
const response = await client.agents.chat(agent.agentId, {
  message: 'What is the weather in Tokyo?',
});
console.log(response.content);

Next Steps