What does Zatanna do?

Zatanna maps human-only software workflows and exposes them as reliable APIs. Instead of building brittle browser automation scripts, you show the task once and Zatanna reconstructs the underlying request flow into a stable endpoint your AI agents and internal tools can call in production.

How is Zatanna different from web scraping or RPA?

Traditional web scraping replays clicks and waits on page elements, which breaks whenever the UI changes. RPA tools automate screen-level interactions but require constant maintenance. Zatanna reconstructs the actual HTTP request behavior behind a workflow, producing a stable API that doesn't depend on the UI layer at all.

How does Zatanna handle anti-bot detection?

Zatanna manages TLS fingerprinting, proxy rotation, and detection-sensitive request behavior below the API layer. Sessions, cookies, retries, re-authentication, and error recovery are all handled automatically so your integration stays reliable.

What types of workflows does Zatanna support?

Zatanna works best for workflows that are important, repetitive, and stuck behind a UI — including back-office systems with no API, document and record workflows involving uploads, claim forms, and status checks, and AI agent actions in external third-party software.

How do I integrate with Zatanna?

Integration is a three-step process: (1) A human runs the workflow once while Zatanna observes the real behavior, (2) Zatanna builds a request model that reconstructs the calls, state transitions, and recovery logic, (3) Your systems call a single stable API endpoint while Zatanna manages the fragile workflow underneath.

← All articles2025-08-07 · 5 min read

How to Automate Brex Workflows Without Browser Scripts

Brex is a corporate card and spend management platform. Here's how to automate Brex workflows using API-level automation instead of fragile browser scripts that break on every UI update.

TL;DR

Brex is a widely used corporate card and spend management platform in the Finance space. While Brex may offer some API access, many workflows — especially complex multi-step processes — are only available through the web interface. API-level workflow automation captures the actual HTTP requests behind these UI workflows and exposes them as stable endpoints, eliminating the need for brittle browser automation scripts.

The Brex automation challenge

Teams that need to automate Brex workflows typically face a few options: use the official API (if one exists and covers their use case), build browser automation scripts with tools like Puppeteer or Selenium, or hire people to do the work manually.

The problem with browser automation for Brex:

UI updates break selectors — Brex regularly updates its interface, which breaks scripts that depend on specific CSS selectors or DOM structure
Authentication complexity — Brex's login flow, including SSO and MFA, makes automated session management difficult
Rate limiting and detection — Brex employs bot detection measures that block automated browser sessions
Performance — browser-based automation is slow because it renders full pages for every interaction

Where the official API falls short

Even when Brex provides an API, it rarely covers every workflow. Common gaps include:

Multi-step processes that involve validation logic only available in the UI
Bulk operations that the API doesn't support or rate-limits heavily
Legacy features that were never exposed through the API
Admin and configuration workflows that require the web interface

These gaps force teams to build browser automation as a workaround — which then becomes a maintenance burden.

The workflow API approach

Instead of scripting a browser to click through Brex's interface, workflow API automation captures the actual HTTP requests that Brex's frontend makes when a human performs a task. The result is a clean API endpoint that replicates the workflow without a browser.

How it works:

1. A human performs the Brex workflow once — the real network behavior is observed, including authentication, form submissions, and validation calls

2. The request flow is reconstructed — the underlying API calls, headers, cookies, and state transitions are modeled into a reproducible sequence

3. A stable endpoint is created — your systems call this endpoint instead of driving a browser through Brex's UI

What gets handled automatically

The automation layer manages the hard parts that make Brex browser scripts unreliable:

Session management — login flows, token refresh, SSO, and cookie persistence
Request sequencing — multi-step workflows that require calls in a specific order
Error recovery — automatic retries when sessions expire or requests fail
Anti-bot handling — TLS fingerprinting and request patterns that avoid detection

When to use this approach

This approach is ideal for Brex workflows that are:

Not covered by the official API — the workflow is only available through the web interface
Performed frequently — the volume justifies automation over manual work
Business-critical — failures or delays have a real cost
Multi-step — the workflow involves authentication, form navigation, and validation

If you're maintaining browser automation scripts for Brex that break regularly, or paying people to perform repetitive Brex tasks manually, workflow API automation offers a more durable alternative.