Run with Browser AI · Chapter 06
Run Chapter 06: Summarization Contract Lab
Configure, execute and evaluate a browser-managed summary as a declared compression contract.
← Read Summarization Is a Contract
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
Summarization Is a Contract
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 06 and the claim that summarization is a compression contract.
Declared dimensions
A summary contract specifies its purpose through type, its representation through format, its semantic size class through length, and its runtime trade-off through preference.
Canonical fixture
The source distinguishes browser responsibility from application responsibility. It also says that local execution can improve privacy and latency, while those properties still depend on the complete data flow and measured lifecycle.
Evaluation boundary
Automatic checks can count bullets and find required terms. They cannot determine whether the summary falsely changed “can improve privacy” into “is automatically private.” That faithfulness judgment remains an explicit human check.
Evidence boundary
A resolved Summarizer promise proves operational completion. It does not prove coverage, faithfulness or usefulness. A replay without apiId: "summarizer" events is not evidence about Summarizer behavior.
This laboratory runs the canonical Chapter 06 fixture through the browser’s Summarizer interface. Change the summary type, format, length or preference, then create a session and compare structural checks with the unresolved human rubric.
The reviewed replay predates a successful Summarizer run and contains Prompt API session evidence only. It remains available for provenance, but it is not presented as summarization evidence.