Creating the perfect prompt for an AI chatbot is often difficult, which is why startups are creating the role of prompt engineer. Consumer-facing AI apps are increasingly adding features like suggestion buttons and auto-generated recommendations to encourage customers to use chatbots more often and show them what the app can do for them.
Hero, a productivity startup founded by former Meta employees, today announced a new autocomplete SDK that fills in prompts based on context. The SDK is currently invite-only and will allow developers to integrate the technology into their apps.
Here’s how it works: When you book a flight, you may enter “Book a flight” at a prompt. The autocomplete SDK will start filling in fields such as “to”, “from”, “on date”, “at time”, “airline”, and “returning on”. You can stop at any time and send your query to the chatbot.
This is also useful if you are using an AI-powered image or video generator. Autocomplete allows you to specify various parameters such as object, style, location, scenery, camera angle, etc. In particular, the new feature for creating soundtracks in Adobe’s Firefly app allows users to easily create songs by entering keywords such as mood, style, and purpose in different sections of the prompt.
Saharsh Vedi, the hero engineer who worked on the feature, said it usually requires multiple interactions with the AI app to get the desired result. This autocomplete feature allows you to display fewer or only one prompt.
Brad Kowalk, the company’s co-founder, told TechCrunch that the company uses a series of models to predict what users will type into a prompt next.
“AI Autocomplete pulls out all the inputs needed to complete an action, allowing you to complete it 10x faster with fewer interactions. This enables a whole new set of use cases, from travel to commerce, advertising to customer support,” Kowalk said.
tech crunch event
san francisco
|
October 13-15, 2026
He added that companies operating at scale can save on server costs because there are fewer messages involved.
Kowalk and co-founder Soon W. Lee said they wanted to build the technology based on their experience working on AR capabilities at Meta. Due to the screen size limitations of AR glasses, the prompt interface should be simple, including adding parameters to the query.
The startup, which raised $4 million in seed funding last year, has secured $3 million in additional funding led by Forerunner Ventures. Kowalk said Hero plans to raise a larger round in the coming months, depending on the growth of the app and SDK.
Hero is testing a version of this technology in its app that allows users to find meeting times and catch up with friends through autocomplete prompts. This feature will be released to users in the coming months.
The company is also in talks with ad tech startup Koah Labs to build AI-powered ads that allow brands to appear in autocomplete suggestions.
