Run with Browser AI · Chapter 08
Run Chapter 08: Language Routing Laboratory
Turn ranked language evidence into an explicit abstain-or-translate decision, then inspect and prepare the selected translation pair.
← Read Language Detection Is a Decision, Not an Answer
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
Language Detection Is a Decision, Not an Answer
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 08 and treats detection as evidence for a product decision.
Decision boundary
The highest-ranked candidate is not automatically a trustworthy source language. The policy checks both its reported confidence and its separation from the second candidate. Failure produces an explicit abstention state.
Capability boundary
Language Detector and Translator are separate browser capabilities. Translator availability is inspected with the source and target pair chosen by the policy. A detector result cannot establish that the pair is installed, downloadable or supported.
Evaluation boundary
The expected language belongs to the fixture evaluator; it never overrides the detector. Automatic translation checks catch narrow failures, while preservation of meaning remains a human review.
User and data boundary
A production product should let the user correct the source language and should disclose any route that moves text away from the device. Local inference describes one segment of the data flow, not the privacy of the complete product.
This laboratory composes two browser-managed capabilities without collapsing them into one magic “translate” button. Detect a ranked candidate list, inspect confidence and margin, apply an explicit selection policy, and only then inspect the exact Translator pair.
The reviewed replay contains Prompt API session evidence only. It remains available as historical evidence and is never presented as a Language Detector or Translator run.