How Simplify in the Google app makes complex text easier to understand

We've all been there: staring down a dense scientific study or a convoluted legal contract, and your brain just… stalls. You’ve re-read the same sentence four times. Nothing sticks. It’s written by experts for other experts, creating a barrier of jargon that’s hard to get past.
It’s that kind of wall of text a team in Google Research wanted to tear down. Their work recently led to the launch of Simplify, a feature in the Google app on iOS that uses AI to make complex information easier to understand — without leaving the webpage.
When you tap "Simplify," the selected text is sent to a Gemini Flash model, packaged within a specific prompt developed by Google Research. The model generates a simplified version of the text, streamed directly back to your screen in real time.
Its helpfulness lies in what it doesn't do. Summaries cut details out, and explanations might add new context. Simplify does neither. It focuses exclusively on rephrasing for clarity, ensuring the original meaning, details and nuance remain intact.
“Summarization tools aim to condense an article to its main topics, often sacrificing details for brevity,” says Sho Fujiwara, a product manager who helped develop Simplify. “Simplify focuses on making specific passages easier to understand without losing crucial information. This means a simplified version of selected text can sometimes actually be longer than the original.”
Starting Simplify
The path to Simplify began in the specialized world of medicine, where no detail should be spared. "Doctors sometimes use language that's purposefully obscured to reduce patient anxiety or preserve privacy," says Diego Ardila, a Google Research software engineer. "They might say, 'The patient is undergoing emesis,' which just means they're vomiting. Sometimes there's a use for that inside a hospital, but other times it actually gets in the way.”
The team built an internal simplification demo, and started testing it on text outside of medicine. “We found that it just kept working because the underlying AI models are general-purpose,” Diego says. “Seeing its potential for broader applications, we shared it with other teams.”
That demo caught the eye of the iOS Google app team. “The user benefit was immediately apparent,” Sho says. “It performed exceptionally well on technical subjects, but its effectiveness on non-technical topics — like an online discussion about basketball filled with slang — really convinced us of its wider value for anyone exploring unfamiliar subjects.”
Finding fidelity with help from AI
From there, the challenge was to turn a research prototype into a feature for millions. The team focused on fidelity: The model had to rewrite complex ideas without losing the original meaning or omitting critical details. How do you teach AI to do that?
The answer was to have another, more advanced AI act as its teacher. Instead of manually writing rules to define an effective simplification, the team built an automated feedback loop. One Gemini model would attempt to simplify a passage, and a second "evaluator" model would grade how well it preserved the original meaning. That critique was then fed back to the first model, which used it to improve. After repeating this process 824 times, the model effectively trained itself to master the art of simplification.
That training paid off: In research testing, people found the simplified text significantly more helpful than the original text, and better retained the information.
Google Research replaced laborious manual tuning with a novel approach where an AI system autonomously uses one model to iteratively improve another's prompts based on its performance on readability, completeness and entailment.

Building with users in mind
With confidence in the model's accuracy, the team optimized the user experience. To handle lengthy selections without long waits, they designed a streaming system. “We split the text into chunks,” Diego says. “The first section is simplified and streamed immediately. Subsequent sections are processed on-demand as you scroll.”
Trusted testing revealed other opportunities for improvement. “We didn't anticipate this, but people wanted to use it as a dictionary,” Diego says. “They’d highlight a single word, like ‘iOS,’ but the model was like, that’s already very simple, I’ll just say ‘iOS.’ So we updated the prompt — if a single word is selected, it’ll always explain what that word is.”
While you can also paste text into the Gemini app for simplification, the team believes in the power of specialization. “I hope Simplify serves as an example of the value of hyper-optimized, bespoke features in a world of powerful general purpose tools,” Sho says.
Ultimately, the goal is to lower the barrier to understanding. “It’s helping to make expert information more accessible,” Diego says. "We’re dealing with an increasingly complex world, and tools like this can help us better understand society and each other.”