Run with Browser AI · Chapter 03
Run Chapter 03: Browser AI Observatory
Run the smallest useful Browser AI debugger and inspect the evidence produced by every phase.
← Read Build the Smallest Browser AI ObservatoryObserved 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
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
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
Build the Smallest Browser AI Observatory
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 03 and the smallest useful Browser AI Observatory.
Instrument boundary
The page owns the Prompt API session it creates and can truthfully observe that work. It cannot automatically see calls made privately inside another page or application. DevTools placement does not grant magical instrumentation.
Event model
The primary output is a versioned, metrics-only event stream:
capability.inspect.startedandcapability.inspect.finished;session.create.started, download progress andsession.create.finished;prompt.started, zero or moreprompt.chunkevents andprompt.finished;- correlation identifiers connecting session and prompt events.
Measurements
The Observatory derives event count, session-creation duration, time to first chunk, total prompt duration and terminal outcome from events. Missing evidence is shown as unavailable rather than estimated.
Privacy and provenance
Prompt and output bodies are redacted from the trace; sizes and timings remain. A recorded replay preserves its original run metadata and must remain visibly distinct from a live run in the current browser.
This chapter experience is the web-page counterpart of the DevTools extension built in Chapter 03. It runs the same inspect → create → prompt → trace workflow and summarizes the measurements produced by the event stream.
The page observes only work that it initiates. It does not claim access to private Prompt API calls made by other applications. The complete extension source is in the Browser AI Observatory directory.