From signup to your first data API,one guide covers it all
Aixdata drives the entire data pipeline with natural language — describe your need, auto-collect, generate APIs. Here's how each step works.
Quick Start
Three steps from signup to your first structured dataset — no scraper code required.
- 1
Create Account
Sign up with your email and log in to the Dashboard to see resource overview and recent tasks.
- 2
Describe Your Need
In the natural language input on the home page or Dashboard, describe your collection target in one sentence, e.g. "Analyze TikTok beauty trends in Paris."
- 3
Get Results
The platform auto-plans the collection strategy, infers the data schema, and generates a callable API — preview, download, or integrate directly.
Create Collection Tasks
Drive collection with natural language; the engine handles resource mapping and field extraction automatically.
- 1
New Task
Go to "Crawler", enter a target site or natural language description, and select Official / Unofficial / AI LLM interface type.
- 2
Confirm Execution Plan
The platform generates a step-by-step plan (resource mapping → schema inference → data extraction) that you can refine before running.
- 3
Run & Reuse
Tasks enter the queue after launch; completed collection schemas can be saved as data sources for future reuse.
Generate Data APIs
One-click packaging of any collection result into a stable, authenticated RESTful endpoint.
- 1
Select Data Source
In "API Builder", select an existing data source and define output fields and query parameters.
- 2
Generate Endpoint
The platform auto-generates /v1-style endpoints with docs, sample requests, and responses.
- 3
Manage Versions
In "APIs", view, test, enable/disable published endpoints and retrieve access credentials.
Data Sources & Proxies
Centrally manage collection sources, proxy pools, and credentials for stability and compliance.
- 1
Data Sources
In "Sources", maintain registered data sources and view health status and field schemas.
- 2
Proxy Pool
In "Proxies", configure proxies to improve scrape success rates and geographic coverage.
- 3
Credentials
In "Integrations", bind third-party accounts / API Keys for sources that require authentication.
Tasks & Monitoring
Track the status, output, and exceptions of every collection and generation task in real time.
- 1
Task List
In "Jobs", view running / completed / failed tasks and their logs.
- 2
Monitor Dashboard
In "Monitor", view throughput, success rate, and latency metrics to detect anomalies quickly.
- 3
Notifications
In "Notifications", receive alerts when tasks complete or fail.
API Calls & Integration
Call generated endpoints over standard HTTP and integrate into your application or data pipeline.
- 1
Get Credentials
Retrieve the Bearer Token from the API detail page — all requests are authenticated over HTTPS.
- 2
Make Requests
Send GET/POST requests to endpoints under /api/v1; responses are standard JSON.
- 3
Integrate into Pipeline
Use Webhooks and scheduled tasks to continuously push structured data to your downstream systems.
Billing & Quotas
Pay-as-you-go billing with clear quota and invoice visibility.
- 1
View Usage
View current call volume, collection quota, and remaining balance in the Dashboard.
- 2
Upgrade Plan
In "Pricing", select a plan on demand — quotas take effect immediately.
- 3
Invoice Details
View billing history and invoices in account settings.
Ready to get started?
Sign up and describe your first data collection need in one sentence.