TabbitBlog

Use Inkling with a signed-in browser

Check access on a signed-in preview page with a local agent and Tabbit CLI. Verify the account and status, then leave a named review draft without changing permissions.

In this article
  1. Check the model route before opening work
  2. Choose the right route
  3. Connect the local agent to Tabbit CLI
  4. Keep the first browser pass read-only
  5. Verify each row against its source page

Inkling can help a local agent summarize a visible preview page, but it does not supply browser access or a signed-in session. Use Tabbit Browser with a local agent that currently exposes the exact Inkling route and can run local tools, then use Tabbit CLI to inspect the page you already opened and signed into. Confirm the account, project, title, and status before creating a review draft.

Check the model route before opening work

Thinking Machines introduced Inkling as its first model generation on July 15, 2026. Inkling 2 Small was announced on November 5, 2026, and is a separate newer generation. The original Inkling model card describes text, image, and audio inputs. Treat API/host availability as provider-specific and verify it in the client catalog before wiring tools. Inkling primary source. Inkling model card and Inkling 2 Small announcement show that Inkling and Inkling 2 Small are separate releases. The original release identifies the Tinker model as thinkingmachines/Inkling. Inkling 2 Small was announced later as the second generation and is initially available through Tinker. Verify the current route in the Tinker and agent-client catalogs before configuring tools. Provider lists change. Model availability does not establish that a particular agent client can call the model or run local shell tools. Confirm both before opening a signed-in work page. Read the Tabbit CLI setup guide and existing-browser connection notes.

Choose the right route

model and provider routeWhat must be checkedUse it when
Requested model APIConfirm exact model ID, provider, region, terms, and current availability.The task requires that specific generation.
Current successorUse only if the project explicitly permits a newer model and the client lists it.You are allowed to change model generation.

Connect the local agent to Tabbit CLI

Install Tabbit Browser and follow the CLI quick start. In your local agent, first check its current model/provider catalog. Then check that it discovers the installed Tabbit skill and that its shell tool runs on this computer. In OpenCode, skills are discovered from configured skill locations and invoked as @tabbit; other clients may expose a Skills picker, while Pi documents /skill:tabbit. Do not assume /tabbit works everywhere. Skill discovery does not prove the launcher is reachable. Run the installed CLI’s diagnose, then sign into the intended site in that Tabbit profile yourself. These are three checks: model route, local launcher, and website login. A cloud model may receive page text, so check your organization’s data policy. See first-task checklist, CLI versus Browser MCP, profile and workspace differences, and Codex connection setup.

A local fixture check verified session reuse, not model integration: the first Tabbit CLI task received HTTP 401 before sign-in. After a test cookie was set in the target Tabbit profile, a second named task received HTTP 200 and read “Release notes review” and fixture record “GEO-104” in its own task tab. Both tasks owned one tab; the test cookie and scratch tabs were removed afterward.

Keep the first browser pass read-only

Inspect a preview page and distinguish access denied from a wrong account or project. Use a separate task tab so you can keep working in your other tabs. Ask the agent to read only the visible page and return its URL with each finding. The example below is an illustrative workflow, not a claim that this model-client pairing has been tested.

On the currently open preview page, read only the visible title, status, project name, and account/workspace marker. Do not click approval, edit, publish, or change access. If the page shows a sign-in screen or access denied, stop and report that exact state. In the browser, prepare “Inkling preview access check — 2026-11-10” with the visible fields, URL, and any mismatch. Do not save or publish; show the draft for review.

Verify each row against its source page

CheckpointConfirmStop if
AccountExpected site, account, and workspace markerThe wrong account or tenant appears
EvidenceEach value is visible and its URL opens the same recordA field is hidden, missing, or inferred
DraftThe named draft contains only approved fields and linksThe page differs from the source or asks for a write action

Review the browser task checklist before approving a write. For models with an official browser product, keep that product’s account and data policy separate from this Tabbit workflow. If a page redirects to sign-in or returns access denied, stop; do not ask the model to bypass it.

For task setup, review the Tabbit CLI complete guide and Inkling 2 Small browser guide. Keep the selected browser profile separate from task tabs; see browser profiles and workspaces.

For practical tab cleanup, see how to manage too many browser tabs.

FAQ

Does Inkling open my browser by itself?

No. A local agent runs Tabbit CLI; the model provides reasoning and tool-call output.

Is Inkling 2 Small the same model as Inkling?

No. Inkling 2 Small is a distinct later generation. Confirm its exact model ID before using it.

Where should I sign in?

Sign into the intended website in the Tabbit browser profile yourself and check the account and workspace.

Can the agent send a reply?

Use the named draft as a review checkpoint. Review it, then perform any write action yourself.

What if the model route is unavailable?

Stop and verify provider, exact ID, region, lifecycle, and local tool support in the client catalog.

Take the next step

Let Tabbit work alongside you.

Research across tabs, automate repetitive browser work, and keep every piece of context within reach.