SentienceAPI sits between your browser and LLM — turning raw webpages into deterministic, action-ready targets.

Build browser agents that can see AND act. Semantic element discovery, realistic mouse/keyboard simulation, and smart waiting. No brittle selectors. No vision retries. Just reliable automation.

Read: Why Web Agents Fail & How Semantic Geometry Helps

Deterministic Action Grounding

Stable, semantic targets instead of probabilistic vision

Sub-Second Execution

Lightweight geometry enables fast observation & execution

Production-Oriented Reliability

Explicit signals for visibility, occlusion, and action priority

*Based on internal benchmarks on common public pages. Results vary by site and configuration.

sentience-sdk-demo.py

The Missing Layer for AI Web Agents

Most tools help agents load pages or read content. SentienceAPI helps agents act — reliably.

Sentience SDK

Structured semantic data + smart filtering = reliable automation (see experiment results)

100%
Consistent Success*
73%
Token Reduction
< 3s
Execution Time

*Based on internal benchmarks on common public pages. Results vary by site and configuration.

button = find(snap, 'role=button text~"Submit"')

click(browser, button.id)

Why not CSS selectors, Vision models, or read-only tools?
❌

CSS Selectors (Playwright)

Breaks on layout changes, requires constant maintenance

❌

Vision Models (GPT-4V)

0% success in our tests, content policy triggers, non-deterministic

❌

Read-Only Tools (Firecrawl)

Great for content, but can't interact with pages

Tested on real production sites:

✓Google Search: 100% success, 73% token savings vs vision (0% success)
✓Amazon Shopping: 5/5 scenes completed, vision failed all runs

Try It Live

Explore the SDK with interactive examples or test the API directly

Navigate to a login page, find email/password fields semantically, and submit the form.

1# No selectors. No vision. Stable semantic targets.
2from sentience import SentienceBrowser, snapshot, find, click, type_text, wait_for
3
4# Initialize browser with API key
5browser = SentienceBrowser(api_key="sk_live_...")
6browser.start()
7
8# Navigate to login page
9browser.page.goto("https://example.com/login")
10
11# PERCEPTION: Find elements semantically
12snap = snapshot(browser)
13email_field = find(snap, "role=textbox text~'email'")
14password_field = find(snap, "role=textbox text~'password'")
15submit_btn = find(snap, "role=button text~'sign in'")
16
17# ACTION: Interact with the page
18type_text(browser, email_field.id, "user@example.com")
19type_text(browser, password_field.id, "secure_password")
20click(browser, submit_btn.id)
21
22# VERIFICATION: Wait for navigation
23wait_for(browser, "role=heading text~'Dashboard'", timeout=5.0)
24
25print("✅ Login successful!")
26browser.close()

🎯 Semantic Discovery

Find elements by role, text, and visual cues - not fragile CSS selectors

⚡ Token Optimization

Intelligent filtering reduces token usage by up to 73% vs vision models

🔒 Deterministic

Same input produces same output every time - no random failures

Why Sentience is production-safe

Studio acts as your trust engine — record, replay, and inspect every agent action

Every step is recorded

Complete execution traces with screenshots, elements, and timing data

Every action is replayable

Step through executions frame-by-frame to understand agent behavior

Every failure is inspectable

Visual debugging shows exactly what went wrong and why

Learn About Sentience Studio

Simple, Credit-Based Pricing

1 credit = 1 SDK snapshot

1 snapshot = 1 agent perception step. Each snapshot returns execution-ready elements with visibility, occlusion, and semantic ranking — optimized for reliable agent actions. Learn more →

100 free credits
No credit card required
No per-seat pricing
Pay for usage, not licenses
No retry tax
Reliable first-time execution
View full pricing
See all tiers & features

The Execution Layer for AI Web Agents

Enterprise-grade performance meets developer-first simplicity

~90% Token Reduction

Transform verbose HTML into efficient geometry data

Standard HTML15,234 tokens
Sentience API1,523 tokens

Sub-Second Response

Lightning-fast processing for real-time AI agents

Processing time<347ms
Average response time across 10,000+ API calls

Visual Grounding

Semantic geometry for stable, intention-level actions

SDK-First Interface

Install via pip or npm, start building in minutes

# Python SDK
snap = snapshot(browser)
btn = find(snap, role="button", text~="Submit")
click(browser, btn.id)

Loading pricing information...

A Few Lines of Code. Infinite Possibilities.

Build production-ready browser agents with our SDK. No brittle selectors. Reduced reliance on vision. Just semantic automation.

1from sentience import SentienceBrowser
2
3# Initialize browser with API key
4browser = SentienceBrowser(api_key="sk_live_...")
5
6# Navigate and take snapshot
7browser.page.goto("https://example.com/login")
8snap = browser.snapshot()
9
10# Find elements semantically (no selectors!)
11email_field = browser.find(snap, "role=textbox text~'email'")
12browser.type_text(email_field.id, "user@example.com")
13
14password_field = browser.find(snap, "role=textbox text~'password'")
15browser.type_text(password_field.id, "secure_password")
16
17submit_btn = browser.find(snap, "role=button text~'sign in'")
18browser.click(submit_btn.id)
19
20# Wait for navigation
21browser.wait_for("role=heading text~'Dashboard'")
22
23print("✅ Login successful!")

Semantic Queries

Find elements by role and text, not CSS selectors

Deterministic

Deterministic selector resolution for reproducible actions

Production Ready

Validated through real-world demos on complex sites

Don't Miss Out on AI Agent Innovations

Join 2,000+ AI developers getting exclusive tips, cost-saving strategies, and early access to new features. No spam, just value.

We respect your privacy. Unsubscribe anytime with one click.