For AI agents: a documentation index is available at /llms.txt, and the full corpus at /llms-full.txt. A markdown version of any page on this site is available by appending .md to its URL path — the homepage is at /index.md.

More full carts on with AI Autocomplete

Today

  1. Search “pasta”
  2. Scan 240+ items
  1. Search “pasta”
  2. Pick one of 8 guesses
  3. Compare 24 items
  4. Add to cart

with AI Autocomplete

  1. Add type, pack, dietary
  2. 3 matching items
  1. Add the missing details
  2. 3 matching pastas
  3. Add to cart

Connected to your catalogue

Better search = more groceries in every cart.

Searching “pasta” leaves the details that decide which box fits. AI Autocomplete asks for type, pack and dietary needs while the person is still typing, then hands the completed request to the search Instacart already has.

Your Instacart catalogue

AI Autocomplete choices

TypeSpaghettiPack12 ozDietaryGluten-free

Your own data becomes the vocabulary people use to describe the item they want.

How it works

Quick to add. Works with the search box and data you already have.

01

Connect your data

Give AI Autocomplete the attributes already attached to every item.

02

Guide people as they type

Predict the detail that matters next and show relevant choices inside the search box.

03

Send a richer query to search

Pass the completed text and selected attributes into the backend you already use.

AI Autocomplete works with your search provider.

It only takes five minutes to set up.

  • Your existing search
  • Algolia
  • Custom search backend
Read how it works

The SDK

What is the AI Autocomplete SDK?

AI Autocomplete supercharges your text box. It is an SDK you drop into the search box or prompt box you already have, and it starts guiding people through what they actually meant.

The goal of AI Autocomplete is to hand a more complete phrase to the next step of your stack (your search provider or agent). It is powered by an intent layer: an action engine that pairs the reasoning of an LLM with detection that lands in 150 to 200 ms, so the guidance appears while someone is still typing rather than after they submit.

Drops into the box you have

No migration and no replatform. Your search, your models and your pipeline stay exactly where they are.

Completes the request, not the phrase

Ordinary autocomplete finishes a word. This resolves the attributes the person never said out loud, inside the box, before submit.

150 to 200 ms detection

Fast enough to keep up with typing, so the help arrives in the moment it is useful rather than a beat too late.

The right groceries get into the cart faster.

Set it up
Message Us
How many monthly users does your product have?