GuidesBy featurePeople who are blind or have low vision, and anyone who needs a photo read aloud and explained

Point your phone at anything and hear what it is

For People who are blind or have low vision, and anyone who needs a photo read aloud and explained.

Start here

What this helps you do: Be My AI, inside the free Be My Eyes app, describes a photo in plain spoken language and lets you ask follow-up questions about it. A human volunteer is one tap away for the parts that have to be right.
What you leave with: A repeatable workflow and a starter prompt you can adapt to your own work.
What to check before trusting it: For anything safety-critical, like a medicine dose or legal wording, you get a person to confirm it rather than trusting the description alone

When to use this

You are holding a letter, a medicine box or a restaurant menu, and you want to know what it says without waiting for someone to read it to you.

Takes a photo and describes it back to you in plain, conversational language
Lets you tap Ask More and ask the exact thing you care about, like what colour it is or whether there is an expiry date
Reads labels, documents, menus and the room around you within seconds

Workflow

Open Be My AI in the Be My Eyes app and take a clear photo of what you want described
Listen to the first description, then tap Ask More to ask your real question in words
Add another photo from a different angle if the first one missed the part you needed
For a dose, a payment, a date or legal wording, connect to a human volunteer or ask someone you trust to confirm it
Leave other people's private paperwork alone unless you have their permission to photograph it

Prompts to try

Use it, adapt it, and make it your own.

Describe this photo in plain language, then tell me the expiry date, any dosage or safety instructions, and anything a person should double check before acting on it.

Ask Bit to adapt it →

Human lens

For anything safety-critical, like a medicine dose or legal wording, you get a person to confirm it rather than trusting the description alone
Be My Eyes connects you to a sighted volunteer for the harder requests, and that human check is part of the app, not a fallback you have to arrange
You decide not to photograph other people's private documents without their consent

What to avoid

AI can misread small print, handwriting and numbers, so a confident description is not proof
For a medicine dose or legal wording, confirm with a human, a Be My Eyes volunteer or someone you trust, before you act
Do not photograph other people's private documents without their consent

Related guides

View all →

Giving a persistent agent one job without handing over the keys

Agents that run on their own cloud computer stay signed in to your tools between sessions. That persistence is the point, and it means the thing you are really configuring is access, not prompts.

Using deep research without trusting it blindly

Deep research modes read many sources and return a longer, cited answer. They are powerful for a first pass, and they still need you to check the sources and the reasoning.

Letting an assistant take multiple steps on its own

Agentic modes plan a task, take a sequence of actions such as browsing, running code or editing files, and check their own progress along the way. They can save real time on chores with several steps, and they can also wander off course, so you set the boundaries and check the outcome.

Using projects to keep AI in context, not starting over

Projects or workspaces let you gather files, instructions and past chats in one place, so the assistant carries the right context into every new conversation instead of you repeating it each time.

Reviewed 19 September 2026