Gemini's composer teardown

Updated June 12, 2026

Gemini keeps one pill composer and one + menu. Uploads, Google Drive, image creation, and Deep research all funnel through that tree, with Flash and thinking on the right. Simple prompts stay simple.

Calm default

Empty pill bar, no chips. + on the left, Flash and mic on the right.

What works

No tool vocabulary on first load. You can just type.
One pill bar centered on the page. Familiar chat shape without mode chips.
+ on the left and Flash on the right keep attach separate from which model answers.

What we would push on

Flash on the bar is shorthand. You do not see 3.5 Flash or Flash-Lite until you open the picker.
Upgrade sits top right, disconnected from the model row in the composer.

Takeaway

Calm entry, one bar. Model nickname on the right is fine for casual use; open the picker when spend or capability matters.

Upload files, Drive, Create image, Canvas, and More tools on the first + screen.

What works

One + menu groups uploads and creation tools. You pick intent, not infrastructure.
Add from Drive on the first screen makes Google context a one-tap attach path.
New badges on Create image flag fresh capability without a separate marketing row.

What we would push on

More uploads and More tools hide overflow behind chevrons. Discovery depends on opening both.
Create image and Canvas sit beside file upload with equal weight. Different jobs, same visual priority — and the product name Canvas reads similarly to Create image, which could confuse first-time users.

Takeaway

The + menu scales Google breadth without a second bar icon. Worth stealing the Drive row on screen one. Push on making overflow paths obvious.

More tools

Deep research, Create music, Guided learning, and Personal Intelligence Labs toggle in the tools flyout.

What works

Flyout keeps the parent + menu open. You do not lose context exploring one level deeper.
Deep research tooltip ("Get detailed reports") teaches the job before you pick it.
Personal Intelligence Labs as a toggle makes an experimental capability explicit before send.

What we would push on

Deep research and Guided learning look like equal rows. Nothing signals that research runs longer.
Create music and Deep research both carry New badges. Badge fatigue when everything is new.

Takeaway

Good flyout pattern for long tool lists. Pair menu toggles with in-bar feedback when something changes how Gemini answers.

Attachments

Image thumbnail with dismiss inside the composer. Filename label confirms what ships.

What works

The image sits inside the composer above the prompt. You see what Gemini will read before send.
Dismiss on the thumbnail fixes mistakes without clearing the whole message.
Filename label (output.jpg) adds metadata the thumbnail alone might not convey.

What we would push on

Attach still starts inside +, not on the bar. Sending a file is not an edge case.
Multiple files may get crowded in the top band; we only see a single-image case here.

Takeaway

Steal keeping multimodal context inside the pill. Preview plus filename beats mystery attachments.

Model picker

Flash-Lite, 3.5 Flash, 3.1 Pro with outcome labels. Thinking level entry at the bottom.

What works

Outcome labels per model (fastest answers, all-around help, advanced math and code) teach the choice in plain language.
Model picker on the right rail stays separate from +. Uploads do not compete with which brain answers.
Thinking level as a row in the same panel groups related send-time controls.

What we would push on

The bar says Flash while the menu lists 3.5 Flash, 3.1 Flash-Lite, and 3.1 Pro. Two naming systems.
New badges on multiple models at once. Hard to tell what actually changed.
Every row looks the same weight. Lite versus Pro cost and latency differences could be sharper.

Takeaway

Outcome labels are worth stealing. Align bar shorthand with picker names so users know what Flash means.

Thinking level

What works

Standard and Extended copy explains the tradeoff: most questions versus complex problem solving.
Flyout keeps the model menu open, same pattern as More tools.

What we would push on

Model and thinking are two levers before send. Similar overlap risk to Claude effort plus thinking.
Extended thinking hides behind model picker then a submenu. Two taps to find a slow mode.
Bar still says Flash only. Thinking level does not surface until you dig in.

Takeaway

Plain-language thinking levels are worth stealing. Show the active level on the bar when Extended changes cost or wait.

Ready to send

Typed prompt with blue send button. Flash and mic stay on the right.

What works

Send appears when there is text to ship. Clear affordance that the message is ready.
Model and mic stay visible while typing. No layout shift when send activates.

What we would push on

No in-bar reminder if a + menu tool (Deep research, PIL) is armed while you type plain text.
Send is the only strong color in the bar. Competes with Upgrade in the header for attention.

Takeaway

Simple send gate works. Add lightweight scope cues when a tool mode is on but the prompt looks like casual chat.

How it fits together

What works

Calm pill first, then + for uploads, Drive, creation tools, and overflow flyouts.
Model and thinking on the right rail, separate from attach and tools in +.
Attachments preview inside the composer before send.

What we would push on

Active tools toggled in + often have no chip in the bar.
Flash shorthand on the bar versus full model names in the picker.
Long + tree (uploads, tools, thinking) for users who only wanted to attach one file.

Takeaway

Gemini bets on one + tree for Google breadth. The split (+ left, model right) works. Visibility and naming need to catch up so armed tools and model choice stay honest before send.