To repeat a read on the same harmless test page after switching models and compare extracted fields and action boundaries with MAI-Code-1.1-Flash, first confirm that your provider and agent client actually expose the model. Then run a local agent with Tabbit CLI against the Tabbit Browser profile where you signed in. Keep the first pass read-only and leave a named draft for review. MAI-Code-1.1-Flash official source.
This guide separates model access from browser access. A model may be available in one product surface but absent from another client. A browser login also does not grant the model permission to write. Confirm each layer before using real account data.
Key takeaways
Check the exact model route in the provider or supported client. Do not infer third-party availability from a model card or catalog.
Skill discovery, local CLI permission, browser connection, and site login are separate checks.
Use a separate Tabbit task tab so your regular tabs stay available. The local CLI connects to the intended Tabbit Browser environment; it does not send your password to the model.
Start with a harmless read and stop before any submit, save, or message action.
Check access before the first run
GitHub documents the model picker for MAI-Code-1.1-Flash on eligible Copilot CLI plans. Business and Enterprise admins must enable the model policy. If you use Auto, record the model actually selected before comparing runs. The GitHub Copilot app also documents a separate on-device option on eligible Windows hardware. GitHub Copilot · Copilot App.
| Check | What to verify | Stop when |
|---|---|---|
| Model route | MAI-Code-1.1-Flash appears in the selected supported Copilot surface | The model entry is missing |
| Local tools | The chosen agent can run the installed Tabbit CLI locally | Only a remote runner is available |
| Browser session | The intended Tabbit Browser profile is signed in to the test site | The page asks for sign-in |
| Task scope | Only the supplied page and visible fields are in scope | A write or unrelated route is requested |
Microsoft’s official MAI-Code repository says MAI-Code-1.1-Flash is available across GitHub Copilot surfaces and documents access through supported Copilot model pickers. That does not establish a generally available Microsoft API model ID or support in an unrelated agent client. Verify the exact model entry and local tool permissions in your own Copilot surface before planning this workflow.
Skill discovery is separate from launcher reachability. Some clients discover skills through /skills; Pi uses /skill:tabbit. Use the syntax your client documents, then confirm that the same local process can run the installed Tabbit CLI. A remote runner needs a separately supported local handoff. If there is no local route, stop and use a non-sensitive export or ask a person to do the browser read.
Compare a repeatable read
Repeat the same read-only test page after switching models. Compare the extracted fields and note where the model tried to cross the requested action boundary. Keep the same page, fields, and reference values for each run. Record missing fields as missing instead of asking the model to infer them.
| Output to keep | Why it helps | Reviewer check |
|---|---|---|
| Exact page URL | Opens the evidence in the same workspace | Does it point to the approved page? |
| Visible label and value | Makes extraction auditable | Can both be seen on the page? |
| Difference or uncertainty | Prevents guesses from becoming facts | Is the mismatch described without speculation? |
| Action boundary | Records whether the agent stayed read-only | Did it stop before a write? |
Use a named draft and review checkpoint
The following example is a test fixture. Replace the sample reference values with harmless data you are authorized to use. It is not a claim that a particular model-provider client was tested here.
Read the visible fields on the supplied test page. Return each label, value, and page URL. Compare them with the reference values below and list differences. Save the result as “MAI Flash rerun — draft”. Do not submit, edit, message, or navigate outside the supplied test page. Stop before any write action.Review the named draft in Tabbit Browser. Check each value against its source page, then decide whether to use it. Do not let the agent submit a form or alter a live record during the initial test.
Historical note: MAI-Code-1-Flash is retired
MAI-Code-1-Flash is a different, older model ID from MAI-Code-1.1-Flash. GitHub says it deprecated the exact MAI-Code-1-Flash model across Copilot Chat, inline edits, ask and agent modes, and code completions on September 10, 2026. GitHub recommends MAI-Code-1.1-Flash as the replacement. Enterprise admins may need to enable the replacement in model policies. This does not mean the two IDs are interchangeable in every API or client. GitHub's retirement notice.
Before migrating, check the account's Copilot model selector, the organization policy, the exact model ID selected by the client, and whether the target account can read the intended page. Do not assume a saved configuration silently switched versions. First run the read-only named draft above with MAI-Code-1.1-Flash, compare visible fields, and review it in Tabbit Browser. Keep write permission off until the account owner approves a separate change.
Use Tabbit for the browser layer
Tabbit Browser holds the website session you sign in to. A compatible local agent can call Tabbit CLI to work in a separate task tab, leaving your normal browser tabs available. The CLI guide explains task setup; see also connecting an agent to a browser, the first task checklist, and MCP versus CLI.
This is a workflow recommendation, not a native integration claim. The model provider grants model access. The agent client chooses and runs the model. Tabbit provides the browser connection. Website permissions remain governed by the signed-in account. See Codex setup, what an agentic browser does, how browser agents work, and the Tabbit Browser overview.
Sources
FAQ
Does choosing the model connect it to my browser?
No. The model, agent client, local runtime, browser bridge, and website login are separate checks.
Can the agent use my existing login?
Yes, when local Tabbit CLI connects to the Tabbit Browser environment where you signed in. Never give credentials to a model.
Is `/tabbit` the same in every client?
No. Skill discovery varies by client. Some use `/skills`; Pi uses `/skill:tabbit`. Check the client’s actual syntax.
Can a cloud runner reach my desktop browser?
Only through a separately supported local handoff. Do not assume a cloud runner can reach your device.
Should I let the agent submit changes?
Keep the first run read-only. Review the named draft in Tabbit Browser before any write.
What if my client cannot select the model?
Check the provider route, client model list, and runtime support. Public availability does not prove compatibility.