SiteLens · Browser Intelligence

Browser Intelligence for real applications.

SiteLens combines browser automation, observability, diagnostics, visual regression, and evidence into one coherent workflow.

Automation — see it, record it, edit it, run it, understand what failed — on real browsers
Record Flow — Playwright Codegen → reusable SiteLens flows for Desktop, CLI, and agents
Observability & diagnostics — console, network, payloads, ranked findings
Evidence & reports — one model: timeline, traces, videos, portable reports

Browser Intelligence Use with MCP Download for macOS Why SiteLens Contact us

What Browser Intelligence includes

Platform

Automation. Observability. Diagnostics. Visual QA. Comparison. Reports—one product, not a screenshot tool or a DevTools wrapper alone.

Automation

Flows, scenarios, profiles — discoverable, editable, runnable across Desktop, CLI, and MCP.

Observability

Console, page errors, network exchanges—structured for agents.

Diagnostics

Deterministic findings with evidence refs and recommended actions.

Visual QA

Labeled screenshots correlated with browser behavior.

Comparison

Passing vs failing runs; new problems and timing regressions.

Reports

Portable evidence packages for humans and AI agents.

See it. Record it. Edit it. Run it. Understand what failed.

Desktop 0.2.1

SiteLens automation is not mystery JSON buried in a project. Desktop turns local flows and scenarios into something humans can discover, understand, author, run, and debug visually — while the same files stay portable for CLI and agents.

RecordConvertReviewSaveEditRunInspect

When a step fails, open the browser evidence already captured for that run — console, network, screenshots — through Browser Intelligence. Don’t just know that the flow failed. Understand what happened in the browser.

Your browser automation shouldn’t be mystery JSON

Discover the flows and scenarios already in your project. See execution order visually, understand profiles and parameters, edit properties, run them, and inspect exactly where they failed.

Desktop Automation →

Turn browser interactions into reusable automation

Record a real browser session with Playwright Codegen. SiteLens converts it into a native flow you can review, edit, run, reuse, and expose to agents — from Desktop, CLI, or MCP.

Record Flow →

Portable by design: record in Desktop, edit visually, run from CLI, hand off to agents via MCP — same .sitelens/flows and .sitelens/scenarios files.

Why this matters

Unified

One run. One evidence model. One diagnostics engine. One timeline. One report.

One run

Automation and capture share a single Chromium execution.

One evidence model

Screenshots, console, network, payloads, bodies, diagnostics, timeline, traces, videos, reports—correlated.

One timeline

Navigate the entire browser execution in order—steps, events, findings, artifacts.

Evidence, not disconnected artifacts

Differentiator

SiteLens correlates screenshots, console, network, request payloads, response bodies, diagnostics, timeline, traces, videos, and reports into one coherent evidence model—so agents retrieve a chain, not a folder dump.

Comparison & Unified Timeline

First-class

Cross-run comparison

Compare a passing run with a failing run; identify new browser problems; detect timing regressions; correlate visual changes with browser behavior.

Learn more

Unified Timeline

Flagship navigation of an entire browser execution—steps, console, network, diagnostics, and artifacts in one correlated timeline.

Learn more

Designed for AI coding agents

MCP

Investigate a failed login. Inspect a network request. Explain a failed assertion. Compare successful and failed runs. Diagnose a visual regression. Help create automation from recorded browser behavior, then retrieve the evidence chain—through SiteLens MCP as the preferred browser workflow platform.

AI Agent Verification MCP Codegen MCP setup

How to use it

Surfaces

Desktop

Visual Automation workspace: explore flows/scenarios/profiles, Record Flow via Playwright Codegen, run with result overlays, and inspect Browser Intelligence evidence.

Download Desktop 0.2.1 →

MCP

Cursor and other hosts—run flows, start Codegen sessions, convert recordings, and inspect evidence. Local free; Cloud when you add a key.

Codegen tools →

CLI

Local QA, sitelens flow codegen, reports, and doctor checks from the terminal.

Hosted

SiteLens Cloud/API for CI and persisted runs.

How you run Browser Intelligence — Local, Cloud/API, and Studio on one engine (plus Theme for design intelligence).

SiteLens Local

Free local browser intelligence on your machine—localhost, staging, and private URLs.

SiteLens Cloud/API

Hosted execution, persisted runs, API-triggered workflows, and CI.

SiteLens Studio

Inspect runs, templates, findings, and evidence—not the whole platform.

SiteLens Local

Free local execution

SiteLens Local is free local execution on your machine—not a limited SaaS tier. SiteLens supports Chromium, Firefox, WebKit, and installed Chrome/Edge channels through Playwright against localhost, staging, and private URLs you can reach from your workstation. No API key required; reuse Playwright-style auth state where supported. Prefer a native macOS app? Download SiteLens Desktop for macOS (version 0.2.1).

Real browser execution

Playwright-powered Chromium, Firefox, and WebKit (plus Chrome/Edge channels) with screenshots and step reports—cloud features are separate; local execution stays free.

Localhost & private URLs

QA apps before they are public: dev servers, VPN staging, and LAN hosts your browser can open.

MCP & editor workflows

Run from terminal, scripts, or SiteLens MCP in Cursor—same Local engine from your IDE.

SiteLens Local vs SiteLens Cloud/API

Two execution modes

Same browser QA semantics—different runtime. SiteLens Local is free on your machine; SiteLens Cloud/API is for hosted runs, persistence, and operational workflows.

SiteLens Local

Free local execution

Runs on your developer machine
localhost, staging, and private URLs
No API key required
Chromium, Firefox, WebKit, and Chrome/Edge via Playwright
Artifacts under your local artifact directory
Ideal for dev loops, pre-push checks, and IDE/MCP workflows

Local setup (MCP)

SiteLens Cloud/API

API key

Hosted Chromium against public reachable URLs
Monitoring, scheduled scans, and alerts (as you adopt them)
Persisted runs, screenshots, and team-visible history
REST API, dashboard, and QA Studio cloud executions
CI/CD and operational workflows
Workspace API keys tie usage to your account

Cloud dashboard

Scenario Runner chains reusable flows in a shared browser session via SiteLens Local and MCP—saved auth profiles, parameterized flows, and multi-step workflow verification for authenticated apps.

Page Intelligence & AI Agent Verification

Shipped

Two capabilities that extend SiteLens beyond smoke tests: structured page understanding for agents and IDE-native verification gates that run real browser flows before you ship.

Page Intelligence

Render a page once and get ranked primaryActions, secondaryActions, navigationActions, and inferred workflowStages—confidence-scored summaries agents can plan against without scraping raw DOM.

REST POST /analyze/page · pairs with Theme for design + intent · feeds agent verification planning.

Page Intelligence details

AI Agent Verification

Keep Cursor (and other MCP hosts) honest: run repo-local flows via sitelens_run_local_flow, compare screenshots, and use prompt-library gates so agents verify in Chromium—not by claiming “looks good.”

Free local execution · project flows under .sitelens/flows · optional Cloud/API when you add a key.

AI Agent Verification

Flagship QA templates

Live in SiteLens Studio

Start from proven flow templates—not blank scripts. Each run produces structured pass/fail summaries, dedicated result panels, and named screenshots you can share with teammates or wire into CI.

Internal Link Health

Check internal links without writing a crawler.

Exercise a bounded set of same-site links after deploys or nav changes—see which pages load, capture lightweight screenshots, and get a clear broken-link rollup in QA Studio.

Mobile Navigation Validation

Verify your mobile menu opens and exposes navigation.

On a phone-sized viewport, find a likely menu control, open it, and confirm nav content appears—with before/after screenshots and plain-language failures when the toggle or drawer is missing.

Deployment Verification

Confirm a deploy loads on desktop and mobile.

Post-deploy smoke on desktop and mobile viewports: page load, visible body, heading or main landmark, stable screenshot slugs, and CI-friendly pass/fail—without clicking through your whole app.

Workflow Verification

Scenario Runner

Most browser QA tools stop at a page. Real applications require setup. SiteLens can reuse saved browser profiles, initialize application state, run setup flows, and verify the workflow your users actually follow.

Scenario Runner

Chain reusable flows together using one browser session.

Login

Reuse a saved auth profile or run a login setup flow.

Initialize state

Select test data, toggle features, or seed application state.

Open workflow

Navigate to the route or feature under test.

Perform actions

Click, fill, and interact across multi-step journeys.

Verify outcome

Assert UI state, capture screenshots, and export artifacts.

Parameterized Flows

Pass IDs, URLs, environment values, and test data into reusable scenarios without rewriting flows. Scenario JSON under .sitelens/scenarios/ accepts params and {{placeholders}} that flow into each chained step.

Shared Browser Sessions

Cookies, local storage, session state, and authentication persist across the workflow. Login once, run setup flows, then verify—without restarting the browser between steps.

Built for Real Applications

Authenticated dashboards and SaaS applications
Admin interfaces and internal business applications
Multi-step workflows and role changes
Feature toggles, setup flows, and onboarding paths
Post-deployment verification beyond page-load smoke

Run scenarios via SiteLens MCP (sitelens_run_local_scenario) or the CLI. See the Scenario Runner guide and QA Studio scenarios.

Browser Intelligence Automation · observability · evidence Platform overview → SiteLens Desktop Automation · Record Flow · v0.2.1 Visual authoring · evidence → SiteLens QA Browser QA engine Local + Cloud/API → QA Studio Run inspection & templates Findings · screenshots → SiteLens MCP SiteLens Local from your IDE Cursor · Local integration → SiteLens Reports Evidence-first portable reports JSON · HTML · local viewer → SiteLens Theme Design intelligence Tokens from live pages →

Proof from real work

Documented investigations and QA stories from shipping SiteLens—screenshots, before/after diffs, and agent verification loops. No hype; evidence you can reproduce locally.

Hall of Investigations

Timeline

Regressions and workflow bugs we found with Compare, flows, and local QA—problem, evidence, outcome.

View investigations

Real QA Stories

Cards

Developer and Cursor workflows: migrations, auth, deploy checks, scenarios, and screenshot comparison.

Read QA stories

Explore SiteLens

SiteLens combines browser automation, observability, diagnostics, visual regression, and evidence into one coherent workflow—Local, Cloud/API, Studio, Reports, and MCP.

Browser Intelligence

Flagship

The umbrella platform: automation, observability, diagnostics, comparison, timeline, and evidence.

One run · one evidence model · one timeline
Built for developers and AI coding agents

Browser Intelligence

SiteLens QA

Live

The QA engine behind SiteLens Local and SiteLens Cloud/API—real browser execution, workflow verification, and structured evidence.

Workflow verification with Scenario Runner and shared sessions
Flagship templates: links, mobile nav, deploy checks
Saved auth profiles, parameterized flows, and step timelines

QA details

SiteLens Reports

Live

Evidence-first reporting — turn run artifacts into portable JSON, Markdown, and offline HTML without uploading evidence.

Canonical report.json + integrity-checked portable ZIP
CLI and MCP tools for bounded inspection
Local Dashboard viewer — no upload

Reports details

QA Studio

Live

Template runs, screenshot review, structured findings, and flow inspection on the shared QA engine (not a separate runtime).

Internal Link Health, Mobile Navigation, Deployment Verification
Structured pass/fail summaries above the step timeline

Open QA Studio

SiteLens Theme

Live

Typography, colors, and confidence-scored tokens from rendered pages—for embeds and match-my-site flows.

Formlyx and adapter-friendly JSON
REST /analyze/theme

Theme details

SiteLens MCP

Live

Integration layer for SiteLens Local in Cursor — install @sitelensapi/mcp from npm; optional Cloud/API tools when you add SITELENS_API_KEY.

Local browser QA workflows from your IDE
Optional Cloud/API run memory via MCP resources

MCP details

Recent QA runs

Live samples from SiteLens Cloud/API when the API persists runs (SiteLens Local runs stay on your machine). Select a row for screenshots and step detail.

Contact SiteLens

Tell us what you are building or what you want SiteLens to validate — localhost apps, staging URLs, deployment checks, MCP workflows, Theme API usage, or Cloud/API runs.

SiteLens Local SiteLens Cloud/API MCP (Local) setup