Capabilities
File upload and voice dictation, composer affordances a shopper controls, not the assistant. Both off by default, toggled per agent version.
A version also has capabilities: a second checklist, separate from chat tools. A chat tool is something the assistant itself decides to call. A capability is the opposite: an input the shopper controls directly through the composer, that the assistant never calls and has no way to trigger.
| Capability | What it adds to the composer |
|---|---|
| File upload | An attach button: a shopper can send an image or PDF with their message. |
| Voice dictation | A microphone button: a shopper can dictate their message instead of typing it. |
Both default to off for every agent type, Shopping assistant included: the same explicit-opt-in policy as Web search and Web page reading. A new version enables neither unless you tick it.
File upload
Turn it on and the chat composer shows an attach button, so a shopper can send a file (a screenshot, a photo of a product, a PDF) along with their message.
Uploads are limited to images and PDF: the only file types the assistant's model can actually read, and the safe common set across the supported engine providers. Other file types (a .docx, a .zip) aren't accepted: the file picker filters them out, and dropping one onto the composer is rejected rather than uploaded.
Turned off, the attach button doesn't appear, and if a request tries to send a file anyway, the server drops it before it reaches the model. That holds on both the playground and the public link.
Uploads are capped at 8 MB per file. A larger file is rejected before it's ever added as an attachment: the shopper sees a clear error naming the file and the limit, and nothing is sent. This cap applies unconditionally, on both chat routes, regardless of whether the capability is on: an oversized file is rejected the same way even on a version where attachment is enabled.
Needs a vision-capable engine
An uploaded file only helps if the version's engine can read it. The AISA engines handle images and PDFs; a lighter engine may ignore an uploaded image. The checklist label carries the same reminder. Turning this on lets shoppers attach files today. How much the assistant does with them depends on the engine.
This isn't checked automatically: enabling the capability never verifies the version's pinned engine actually supports vision. Nothing blocks turning it on for a non-vision engine, and nothing warns in the chat itself if an uploaded file is silently ignored by the model. The hint above is the only signal today.
Voice dictation
Turn it on and the composer shows a microphone button. A shopper clicks it, speaks, and the recognized text fills the composer's text input exactly as if they'd typed it; they can still edit it before sending. Recognition runs entirely in the shopper's own browser: no audio and no transcript is sent to iAdvize as part of dictation itself, only the resulting text, on ordinary send.
The button only appears when both are true:
- the version has Voice dictation enabled, and
- the shopper's browser supports native speech recognition (most Chromium-based browsers do; Firefox doesn't).
Either alone isn't enough: a supported browser with the capability off shows no microphone button, and an unsupported browser never shows one regardless of the setting.
This works the same way on the playground, the public link, and the embedded widget. See that guide's voice dictation section for the embedded iframe's own microphone-permission notes.
Off by default for every agent, including existing ones
Voice dictation used to work without any setting. It's now a per-version toggle like every other capability, defaulting off, including for agent versions that already existed before this changed. To bring it back for an agent, create a new version with Voice dictation ticked. See the changelog for background on this change.
Choose a version's capabilities
Capabilities are part of an agent's configuration version, in the same form as its chat tools and connectors.
Open the agent and go to its Capabilities tab. You're already editing its current configuration, no separate "new version" step needed (see Edit or create a version).
Tick the capabilities this version should offer. The list is prefilled from the version you started from.
Save, save as candidate, or publish, as usual. A new version is minted with the capabilities you selected.
Fixed for that version
Which capabilities a version offers is part of that version and can't be changed afterward. Like its instructions, connectors, and chat tools, changing the set means creating a new version.
Chat tools
The built-in tools an agent version can call (product cards, clarifying questions, quick replies, web search, and page reading) and how to choose them per version.
Playground
Chat with any agent version against the live model, compare two versions side by side, and preview the chat panel in another language, all before you promote a version.