Twin Browser
Platform
OverviewHow it worksREST APIMCP serverIntegrationsDocs
Capabilities
OverviewSemantic dispatch cacheDeterministic replayCross-tenant skill corpusToken-efficient DOMHuman-in-the-loopLive view & videoCredential vault
Solutions
All use casesAI agentsRPA replacementQA & test automationData extraction
Resources
GuidesGlossaryBlogCompareFAQStatus
Pricing
Log inGet an API key
Glossary · Page model

DOM indexed state

A compact, numerically-indexed map of a page’s interactive elements that an agent acts on by index instead of raw HTML.

Start freeAll terms

What is dom indexed state?

DOM indexed state is the output of Twin’s DOM → indexed-state compiler: it scans a live page and emits a numbered list of the elements an agent can actually act on — buttons, inputs, links — under a token budget. The planner and compiled skills reference elements by stable index (“click 12”, “type into 7”) rather than fragile selectors or full markup.

Why it matters

Raw HTML is enormous and noisy; feeding it to a model is slow and expensive. Indexing the page to its interactive surface keeps prompts small, makes plans portable across minor layout changes, and is what lets a 50-step flow fit in a few thousand tokens.

See it in context: read how Twin compiles and replays a run, follow the cost-cutting guide, or browse use cases and comparisons.

Related terms

Token-efficient DOM

A page representation stripped to just the interactive, indexed elements under a token budget — so prompts stay small and cheap.

Skill compilation

Turning a successful agent run into a reusable, replayable skill — a compact program of indexed actions you can call again without re-planning.

Deterministic replay

Re-running a compiled skill as a fixed sequence of indexed actions, with zero LLM calls, so the same goal produces the same path every time.

Browser execution layer

The infrastructure that turns an agent’s goal into deterministic, replayable browser action — the layer between your LLM and a real browser.

Back to the full glossary

Put your agent to work

Give your agent a real browser, connect the accounts you authorize, and keep control of every step. Repeated runs compile into skills that replay at near-zero cost.

Start freeSee pricing