Run with Browser AI · Chapter 02
Run Chapter 02 with Browser AI
Observe the difference between API exposure, operational availability, model acquisition and session readiness.
← Read What Does Built-In Actually Mean?
Execution
Not inspected
Observed state machine
What “built-in” means in this browser
No capability call has been made in this page yet.
- 01Not inspected
- 02Unsupported
- 03Unavailable
- 04Downloadable
- 05Downloading
- 06Available
- 07Session ready
- 08Running
- 09Completed
- 10Failed
Derived from events
Observatory measurements
Missing evidence stays missing. The dashboard never estimates an absent measurement.
Application instrumentation
Cross the boundary without erasing it
The page can validate what it sends. Extension receipt is confirmed only in the attached DevTools panel.
- 01Application SDKBuild a sanitized envelope
- 02Same-origin bridgeValidate schema and size
- 03Extension transportRoute by inspected tab
- 04DevTools panelConfirm receipt and correlate
To test end to end, load the Observatory extension, attach DevTools to this tab and enable instrumentation for this origin.
Shared lifecycle · distinct contracts
Browser AI capability switchboard
No interface has been inspected. Each check will use that interface's declared creation options.
| Interface | Global | Exposed | Availability | Options |
|---|
Canonical fixture · live task API
Summarization contract
Exposed Not inspected
Availability —
Session None
Load the canonical fixture, then inspect the current browser.
Generated artifact
No summary yet.
Contract evaluation
- No evaluation yet.
Ranked evidence · explicit routing policy
Language routing laboratory
Choose a fixture, then inspect Language Detector.
Ranked detector evidence
| Rank | Language | Confidence | Use |
|---|---|---|---|
| No ranked candidates yet. | |||
Translated artifact
No translation yet.
Translation evaluation
- No translation evaluation yet.
Resource state · measured lineage
Session lineage laboratory
Prompt API Not inspected
Availability —
Inspect the current browser before creating a session.
Original session
Not created- ID
- —
- Parent
- None
- Usage
- —
- Quota
- —
- Remaining
- —
- Clone / destroy
- —
No output yet.
Cloned session
Not created- ID
- —
- Parent
- —
- Usage
- —
- Quota
- —
- Remaining
- —
- Clone / destroy
- —
No output yet.
Shared-history acknowledgement
No shared-history run yet.
Lifecycle invariants
- No invariants evaluated yet.
Chapter experiment
What Does Built-In Actually Mean?
Loading the chapter experiment…
No model output yet.
Inspect the context supplied by this chapter
What this experience knows
This experience is grounded in Chapter 02 and its model of browser-managed AI.
Central distinction
Interface exposure asks whether LanguageModel exists in the current JavaScript context. Operational availability asks whether the browser can create a session for a specific set of options. Neither means a session already exists.
Lifecycle
unsupported: the interface is not exposed in this page context;unavailable: the requested session cannot be created here;downloadable: browser-managed assets can be acquired after an explicit user action;downloading: acquisition or preparation is in progress;available: the options are accepted without a required model download;session-ready:LanguageModel.create()resolved and returned a usable session;running: a prompt request is active;completedorfailed: the observed operation reached a terminal state.
Correctness constraints
The same capability options must be supplied to LanguageModel.availability() and LanguageModel.create(). This experiment uses deterministic sampling compatible with speculative decoding: samplingMode: "most-predictable".
Evidence boundary
The lifecycle display is driven by observed calls and events. It does not animate hypothetical states. A replay reconstructs the path contained in a recorded trace and is always labelled as recorded evidence. Browser-managed does not mean permanently installed, instantly ready or tied to one model vendor.
This experience turns Chapter 02’s availability model into an observable state machine. Inspect the current browser, explicitly prepare a session, run a chapter-grounded prompt and see each state supported by the events the page actually receives.
If live Prompt API execution is unavailable, replay the reviewed Chrome trace. Replay is visibly labelled and never presented as evidence from the current browser.