15 Best Gemini Personal Intelligence Prompts (With Examples)

Here's the thing that's been driving me crazy: you've got all your data sitting in Gmail, Photos, Calendar, YouTube — but your AI can't connect any of it. Ask "when did I last go to Tokyo?" and it just... stares back at you.

Hanks here — I test AI tools by breaking them, then seeing which ones actually stick in real workflows.So when Google dropped Personal Intelligence for Gemini on January 14th, 2026, I had one question: Does this actually work with messy real-world data, or does it only look good in demos?

I spent the last week testing it with my actual chaos — 47 unread emails, poorly organized photos, scattered search history. Here's what happened with 15 prompts that should theoretically make cross-app searches useful.

Some surprised me. Others broke exactly where I expected.

Let's see which ones are worth keeping.

Email Prompts (1-4)

Personal Intelligence connects to Gmail and can pull data from email threads, attachments, and confirmations. According to Google's official announcement, it combines reasoning with retrieval across text, images, and video — which sounds promising for email-heavy workflows.

#1: Summarize Emails from [Person]

The Prompt:

Summarize all emails from [person@email.com] in the last month, highlighting key decisions and attachments.

What Actually Happens: Gemini scans your Gmail threads and pulls together bullet points of major discussions, decisions, and attached files. In my test with project emails, it caught the budget approval ($5,000 confirmed) and linked to the contract PDF attachment.

Where It Works Best: Monthly check-ins with clients or team leads where you need a quick recap before meetings.

Where It Breaks: If the person uses multiple email addresses or forwards from different accounts, Gemini might miss threads. Also, it struggles with subtle tone shifts — sarcasm or frustration get flattened into neutral summaries.

#2: Find Flight Confirmations

The Prompt:

Find my latest flight confirmation from Gmail, including flight number, departure time, and any hotel bookings attached.

What I Got:

Reality Check: This worked smoothly for my recent booking. Gemini pulled the airline confirmation email and even caught the hotel reservation in a separate thread. But here's where I got confused: it didn't catch a train booking I made through the same email address. Turns out Gemini can retrieve specific details from text, photos, or videos in your Google apps, but the train confirmation was in a PDF attachment, and Gemini didn't parse it fully.

Pro Tip: If your confirmations are image-based (like screenshots), Gemini can read those too — but text-based emails are more reliable.

#3: Extract Action Items

The Prompt:

Extract action items from my emails with [Team/Colleague] this week, prioritized by deadline.

Output Example:

1. Submit quarterly report (deadline: Jan 25, 2026)
2. Review feedback on design mockups (deadline: Jan 27, 2026)
3. Schedule follow-up call (no deadline specified)

Where It Gets Tricky: Gemini can identify explicit to-dos ("Please submit by Friday"), but it misses implied tasks. For instance, if someone writes "Let me know your thoughts," Gemini doesn't always flag that as an action item. You'll need to manually review for nuanced requests.

#4: Draft Reply Based on History

The Prompt:

Draft a reply to [Person's latest email] based on our email history, keeping a professional tone and referencing our last discussion on [Topic].

Sample Output:

"Dear [Person], thank you for your update. Based on our discussion last month about the Q1 targets, I suggest we align on the revised timeline before proceeding. Looking forward to your feedback."

Honest Take: This is where Personal Intelligence starts feeling useful. It pulled context from our previous exchange (Q1 targets discussion) without me having to dig through threads. But — and this is important — you still need to specify the tone. I tried it without adding "professional tone" and got a weirdly casual draft that didn't match the relationship.

Photo Prompts (5-7)

Google's Personal Intelligence feature connects information from Gmail and Google Photos to provide personalized answers, which theoretically makes photo searches smarter. Let's see if that holds up.

#5: Find Photos from [Trip/Event]

The Prompt:

Find photos from my Tokyo trip last summer in Google Photos, sorted by date.

What Worked: Gemini returned a chronological list:

• Jul 15, 2025: Tokyo Tower photos
• Jul 20, 2025: Kyoto temple visit
• Jul 23, 2025: Osaka street food

What Didn't: It missed photos from a day trip to Nikko because I hadn't tagged the location in Photos. Gemini relies heavily on geotagging and metadata, so if your photo library isn't organized, results get patchy.

#6: "When Did I Last Visit [Place]?"

The Prompt:

When did I last visit [Tokyo], based on my Google Photos? Include any related emails from Gmail.

Gemini's Response:

"You last visited Tokyo on October 5, 2025. Your photos show you at a local restaurant, and related emails include your flight confirmation and hotel booking."

This Is Where It Got Interesting: Gemini connected my photo timestamps with email confirmations automatically. I didn't have to specify which emails to check — it inferred the trip context and pulled relevant messages. That cross-app reasoning is exactly what Google describes as "connecting a thread in your emails to a video you watched" — except with photos instead of videos.

#7: Create Memory Slideshow

The Prompt:

Create a memory slideshow from my [Event] photos in Google Photos, with captions based on dates and locations.

Status: This one's still experimental. Gemini generated an interactive slideshow link with captions, but the interface felt clunky. It's powered by Gemini 3, which supports dynamic views, but I wouldn't call this production-ready yet.

Planning Prompts (8-10)

Here's where Personal Intelligence gets ambitious: combining Calendar, Photos, YouTube, and Search history to plan activities. I was skeptical — how accurate could lifestyle recommendations really be?

#8: Plan Weekend Based on My Interests

The Prompt:

Plan a weekend based on my interests from YouTube history and past photos, within 3 hours of my location.

What Gemini Suggested:

• Saturday: Hiking trail near Mt. Takao (based on outdoor photos in my library)
• Sunday: Museum visit (matched to art documentary I watched on YouTube)

Reality Check: The hiking suggestion was spot-on — I do have a bunch of trail photos. But the museum recommendation felt generic. Turns out Gemini saw one art documentary and assumed I'm into museums. Google warns that the system might struggle with nuances, like seeing hundreds of photos at a golf course and assuming you love golf when you're actually there for your son. Same issue here.

Fix: After I corrected it ("I prefer hands-on experiences, not museums"), future suggestions improved.

#9: Suggest Restaurants I'd Like

The Prompt:

Suggest restaurants I'd like near me, based on my Gmail receipts and YouTube food videos.

Output:

1. Sushi Saito (matches your Japanese cuisine preference from receipts)
2. Ramen Nagi (based on ramen videos you watched)

Where It Works: If you have a clear dining pattern (lots of sushi receipts, ramen video history), Gemini nails the recommendations. Google suggests asking for "5 YouTube channels that match your cooking style or meal prep vibe" based on delivery receipts and watch history, which works on the same cross-data logic.

Where It Doesn't: If your eating habits are all over the place (like mine), recommendations get scattershot.

#10: Find Free Time for [Activity]

The Prompt:

Find free time next week for [Activity], checking my Google Calendar and avoiding travel days from emails.

Gemini's Answer:

"You have free time on Wednesday, Jan 29th, 2:00-4:00 PM. No travel conflicts detected in your emails."

This Worked Seamlessly. Gemini cross-referenced my Calendar and scanned Gmail for flight confirmations to avoid suggesting times on travel days. You can boost accuracy by adding @Google Calendar to your prompt if you want Gemini to prioritize Calendar data.

Shopping Prompts (11-13)

These prompts use Gmail receipts and Search history for budget-aware recommendations. I was curious if Gemini could actually parse purchase patterns.

#11: Product Research Based on Needs

The Prompt:

Research tires for my car based on model from my photos and emails, including pricing.

Output:

How It Worked: Gemini found a photo of my car's license plate, extracted the make/model, then searched for compatible tire sizes and prices. This is the exact use case Josh Woodward, VP of Google Labs, describes in his blog post about using Personal Intelligence at a tire shop.

Where I Got Stuck: Pricing was accurate for Japan but might be off for other regions. Always double-check current market rates.

#12: Compare Options from Past Searches

The Prompt:

Compare phone options from my past Search history, focusing on battery life.

Sample Table:

Limitation: Gemini pulled phones I'd searched for in the past month, but it didn't know which features mattered most to me until I specified "battery life." If you want meaningful comparisons, you need to explicitly state your priority (battery, camera, etc.).

#13: Budget-Aware Recommendations

The Prompt:

Recommend budget-aware laptops under $800, based on my email discussions.

Result: Gemini scanned my Gmail for budget mentions in work emails and suggested laptops within that range. But here's the thing: it recommended models I'd already dismissed in previous emails. The reasoning wasn't sophisticated enough to track "I considered X but decided against it."

Pro Tip: If you've already ruled out options, explicitly tell Gemini: "Exclude models I've mentioned rejecting."

Entertainment Prompts (14-15)

#14: YouTube Channel Recommendations

The Prompt:

Recommend YouTube channels based on my watch history and cooking receipts from Gmail.

Output:

• Binging with Babish (matches your cooking interest)
• Sorted Food (aligns with recipe videos you've watched)

What Surprised Me: Gemini connected my grocery receipts (lots of Japanese ingredients) with my YouTube watch history (ramen tutorials) and recommended channels that matched both. That cross-app reasoning is what Google claims distinguishes Personal Intelligence from basic retrieval: "reasoning across complex sources".

#15: Book/Show Suggestions

The Prompt:

Suggest books or shows based on my Search history and past event photos.

Output:

"Based on your search history for historical novels and photos from museum events, I recommend 'The Name of the Rose' by Umberto Eco and the documentary series 'Civilizations.'"

Reality Check: This felt half-right. The historical novel recommendation was solid (I do search for those), but the museum photos were misleading — as I mentioned earlier, I'm not actually into museums. The suggestions improved after I corrected Gemini's assumptions.

Pro Tips for Better Results

Be Specific About Time Ranges

Always add "last month," "since 2025," or "this week" to your prompts. Vague time frames ("recent emails") give you vague results. Gemini performs better with concrete date boundaries.

Combine Multiple Data Sources

Instead of asking "What's in my Gmail?", try: "Based on Gmail and Photos, when did I last travel to [City]?" Cross-app prompts trigger Gemini's reasoning capabilities. Google explains that Personal Intelligence "combines reasoning with data retrieval across text, images, and video", so use that to your advantage.

Monitor Privacy Settings

Personal Intelligence is off by default, and you can choose specific apps to connect. If you're worried about data access, start with one app (like Photos) and expand only if you trust the results. You can disconnect apps anytime in Settings > Personal Intelligence > Connected Apps.

Expect Nuance Issues

Google acknowledges that Gemini may struggle with timing or nuance, particularly regarding relationship changes or your various interests. If you notice over-personalization (like assuming you love golf because you have golf course photos), correct it on the spot: "I don't actually like golf."

Privacy Reminder

Google states that "Gemini doesn't train directly on your Gmail inbox or Google Photos library" — it trains on specific prompts and responses after filtering personal data. Your photos and emails are only referenced to generate replies, not stored for model training. But if you're uncomfortable with any app access, keep Personal Intelligence disabled.

Where This Is Headed

I've been testing Personal Intelligence for a week now, and here's what I keep coming back to: it's not magic, but it's functional enough to change how I handle cross-app tasks.

The email summarization saves me 10 minutes before meetings. The photo-email connection for travel planning actually works. But the entertainment and shopping recommendations still feel half-baked — they need more context than Gemini currently captures.

At Macaron, we've been exploring how this kind of cross-data reasoning fits into structured workflows — specifically, how to eliminate the friction between "I have an idea in a conversation" and "that idea becomes a trackable task." Personal Intelligence handles the retrieval side well, but it doesn't yet push those insights into actionable systems. That's where we're focused: turning conversation context into execution-ready workflows without losing the thread.

If you're testing Personal Intelligence yourself, start with one app (Gmail or Photos), run your real tasks through it, and track what breaks. The feature's still in beta — you'll find bugs and over-personalization issues — but the cross-app reasoning is worth experimenting with.

Low barrier to entry: enable it in Gemini settings, test it with a few prompts, and you can disable it anytime if it doesn't stick. Results will vary based on how organized your Google data is, but at minimum, it's a useful stress test for how AI handles personal context.

Bookmark this page for updates as Google expands Personal Intelligence beyond the U.S. beta.

Want more AI workflow experiments? Check out our template library with 50+ tested prompts for productivity, research, and automation.