Author: Sofia

You don’t need to know the perfect prompt.

Ask Dakota what to study next, why you keep getting something wrong, what your latest test tells you, which colleges fit you, what you still need to research, how to think more deeply about your application—or simply what you need to get done this week.

Dakota remembers your test prep, scores, assignments, Thrive findings, college research, application work and deadlines. So every conversation can start with what Dakota already knows about you.

Here are 98 things you can ask.

Start Here: What Should I Do Next?

Sometimes the hardest part is simply knowing where to start.

1. “I have 30 minutes. What is the most useful thing I could work on right now?”
2. “What are my three highest-priority tasks this week?”
3. “Look across my SAT prep, college research and applications. What needs my attention most?”
4. “What have I left unfinished?”
5. “I’m overwhelmed. Put everything I need to do in priority order.”
6. “What should I finish before my next meeting with my tutor or counselor?”
7. “What did I make progress on this week, and what should I tackle next?”

Workspace 1: Test Prep

Understand My SAT Performance

Dakota doesn’t just see a test score. It can look across your coverage, accuracy, speed, mastery, assignments and previous tests to understand what is actually holding you back.

1. “Analyze my last 30 days of SAT work. What are the three biggest things holding back my score?”
2. “Which Math skills have I still not covered?”
3.  “Which Reading and Writing skills have I still not covered?”
4.  “Which skills am I accurate at that are medium difficulty but still missing at hard difficulty?”
5. “Which skills did I use to be good at but have started to forget?”
6.  “Where am I getting questions right but taking too long?”
7. “Which question types are slowing me down most?”
8.  “I keep scoring around the same level. Is my plateau mainly coverage, accuracy, speed, mastery—or a combination?”
9.  “Which three skills would give me the biggest opportunity to improve my score right now?”
10.  “My Math score is much stronger than Reading and Writing. What is driving the difference?”
11. “I’m already scoring highly in Math. What should I focus on to push my score higher?” 
12. “What have I genuinely mastered?”
13. “What looks mastered from one assignment but isn’t consistent enough yet?”

Help Me Understand What I’m Getting Wrong

A wrong answer is useful if you understand why it happened.

1. “Review this question with me, but don’t give me the answer immediately.”
2. “Give me one hint at a time until I can solve it myself.”
3. “What was the SAT trying to test in this question?”
4. “What trap did I fall for?”
5. “Did I miss this because I didn’t know the skill, applied it incorrectly, rushed or made a careless mistake?”
6. “I thought my answer was right. Help me work out where my reasoning went wrong.”
7. “I know this grammar rule. Why do I keep missing questions that test it?”
8. “Show me where to look in this passage without telling me the answer.”
9. “I don’t understand this explanation. Explain the concept a different way.”
10. “Is there a faster way to solve this Math question?”
11. “Ask me to explain why each wrong answer is wrong before we move on.”
12. “Which mistakes from this assignment keep repeating in my other work?”

Practice Smarter

Once Dakota knows what is wrong, it can help you practice the right thing rather than simply doing more questions.

1. “Give me five questions on the skill I’m weakest at.”
2. “I’ve mastered the medium questions. Give me hard questions now.”
3. “Give me three more questions similar to the one I just missed.”
4. “Give me an unfamiliar version of this question so I can prove I understand the skill rather than the example.”
5. “Quiz me on boundaries and stop after every mistake so I can explain the rule.”
6. “Give me a timed set targeting the questions I can answer correctly but too slowly.”
7. “Create a short practice session around the three traps I fall for most.”
8. “Mix skills I’ve recently learned with older skills I might be forgetting.”
9. “Make the next question harder.”
10. “Have I shown enough mastery of this skill to move on?”

Prepare for Test Day

Upload your Bluebook or official test results and then talk to Dakota about what actually happened. How a test felt matters too.

1. “Analyze my latest Bluebook test using everything you already know about my SAT work.”
2. “I’m not sure which part of the test hurt me most. Can you help me figure it out?” 
3. “I felt rushed at the end of Reading and Writing. Was I actually taking longer on those questions?” 
4. “I thought the second Math module went terribly. Was it really as bad as it felt?”
5. “Which questions did I feel confident about but got wrong?”
6. “Which questions did I feel confident about but got wrong? What did I misunderstand or what trap did I fall for?” 
7. “What should I work on between this test and my next official SAT?”
8. “My SAT is Saturday. What should I focus on this week—and what should I stop worrying about?”

Workspace 2: College Research

Understand Myself Through Thrive

Before asking where you should go to college, understand the environments in which you are most likely to thrive.

1. “Explain my Thrive Report to me.”
2. “What does my Thrive Report say I need from a college environment?”
3. “Which Thrive findings seem most important for my college search?”
4. “What stands out most in my Thrive results?” 
5. “Ask me questions about the parts of my Thrive Report I’m not sure I agree with.”
6. “What should I pay attention to when I visit colleges based on my Thrive Report?”
7. “Which parts of college life seem particularly important for me to investigate?”
8. “Turn my Thrive findings into five questions I should ask myself when comparing colleges.”

Build and Research My College List

Dakota can connect what it knows about you with deep research into individual colleges.

1. “Which colleges fit my Thrive Report particularly well—and why?”
2. “Where does my current college list not line up with what my Thrive Report says matters to me?” 
3. “What kind of college might be missing from my list?”
4. “Compare Brown and Dartmouth for me based on what matters most to me.”
5. “Compare these colleges on teaching style, curriculum, campus culture and student life.”
6. “Research how this university is using AI in the subject I want to study.”
7. “Research the undergraduate research opportunities available in my area of interest.”
8. “Research entrepreneurship opportunities relevant to what I want to do.”
9. “Research the athletic opportunities and requirements relevant to me.”
10. “What should I investigate before I visit this college?”
11. “What should I research about this university before I start thinking about its supplement?”
12. “I’ve finished researching this college. What important questions have I still not answered?”

Workspace 3: Application Workspace

Help Me Think Through My Application Ideas

Dakota does not decide what your story should be or write your application for you. It helps you think.

Bring Dakota your experiences, reflections, research and drafts. Dakota can ask questions, help you examine your own ideas and make sure you are doing the thinking that produces an application that is genuinely yours.

1. “Ask me questions to help me work out what I actually want to say in my personal statement.”
2. “I’m thinking about writing about rowing. Help me think through what this experience actually means to me.”
3. “I have three experiences I’m considering. Ask me questions about each one so I can work out what they reveal about me.”
4. “What questions should I answer for myself before I start drafting?”
5. “What does this application prompt actually want me to think about?”
6. “Help me think through which of my own ideas best answers this prompt.”
7. “Ask me questions that will help me explain why this experience mattered to me.”
8. “What changed in how I thought, acted or understood myself after this experience? Help me work that out.”
9. “Am I spending too much time describing what happened and not enough time thinking about why it mattered?”
10. “What do you understand about me from what I’ve written?”
11. “What important question about this story have I not answered yet?”
12. “Where am I being vague about what I actually thought or felt?”
13. “Does this reveal something about me that isn’t already obvious from my activities list?”
14. “Am I repeating information from somewhere else in my application instead of adding another dimension?”
15. “Does this sound like the way I normally express myself?”
16. “I’ve researched this college. Ask me questions that will help me work out why these particular things matter to me.”

Planning & Deadlines

Keep Everything Moving

College admissions generates tests, assignments, meetings, essays, research and deadlines across months.

Dakota can help keep all of it connected.

1. “What is due this week?”
2. “What do I have due before my next counselor meeting?”
3. “What has my tutor assigned me?”
4. “Show me everything overdue.”
5. “Add my SAT practice assignment to my To-Do list for Thursday after school.”
6. “Remind me tomorrow to upload my Bluebook results.”
7. “Move this assignment to Friday and update my plan.”
8. “Schedule time for me to finish my college research before my counselor meeting.”
9. “Show me my upcoming tutoring sessions, application deadlines and assignments in one place.”
10. “I have three application deadlines coming up. Help me organize the work backwards from each deadline.”
11. “What do I need to do today?”
12. “I can spend an hour after school each day this week. Help me plan what to work on each day.”

The Bottom Line

Dakota is not another place to search for generic answers.

It knows the work you have already done.

It remembers your tests, assignments, mistakes, progress, Thrive findings, college research, application thinking and deadlines. You can ask a question in one workspace and Dakota can use what it has learned about you everywhere else.

So you don’t have to keep rebuilding the context.

And you don’t have to figure out the entire college journey at once.

Sometimes the most useful question really is:

“Dakota, what should I do next?”

Dakota reached 90% mastery in about 6 hours for SAT® test prep. Achieving the same mastery levels using SAT® Bluebook questions took about 28 hours. Try Dakota free at collegecopilot.me

Students spend hundreds of hours studying. But more time studying does not necessarily mean more learning. We saw this clearly in SAT® preparation.

In one of the largest studies ever conducted on SAT® preparation, College Board and Khan Academy studied 545,640 students. Six or more hours of practice was associated with only about 18 additional SAT® points. When students combined six or more hours with at least one measured best-practice behavior, the gain was still only about 39 points.

This is a far cry from the 100- or 200-point gains widely advertised on social media — claims that are not backed by comparable published data or research.

So the question is not whether students can improve. It is about closing the gap between modest average gains and the much bigger results students need to get into their dream school.

We know what great learning looks like. An expert tutor gets to know the student: what they know, why they’re struggling, what they need next, when to push harder, when to review, and whether the learning has actually stuck.

But no tutor can do all of that continuously while tracking mastery across hundreds of subskills.

Dakota can.

Dakota combines a detailed understanding of the subject with a continuously evolving understanding of the learner — then uses both to decide what the learner needs next.

And when we tested Dakota in a simulator modeled on real SAT® student-response and benchmark data, the difference was dramatic:

In our simulator using real student data, the Dakota Mastery strategy achieved 90% mastery in about 6 hours of practice, compared with about 28 hours for SAT Bluebook practice with the same content.

Same underlying curriculum. Same mastery target. But a vastly different outcome for the student. And when you’ve got to manage homework, athletics, college passion projects and just trying to be a teenager — getting the right kind of academic support on a high-stakes exam such as the SAT® is critical. And these tests matter far beyond college admissions: more than 25 states require the SAT® or ACT® as part of public high-school testing.

Here is how it works.

The Dakota Learner Model

At the center of Dakota is a continuously evolving model of each learner.

Every question gives Dakota more information — not only whether the student got it right or wrong, but what they have mastered, how quickly they can use it, where they are struggling, which misconceptions or traps recur, and whether previous learning has stuck.

Together, these create a continuous loop: Dakota understands the learner, decides what they need next, coaches them through the work, measures what changed, and updates again.

From Chatbot to Learning Workspace

The interface for AI is changing rapidly — from chatbots that answer questions to persistent, agentic workspaces that understand context and help users complete complex work over time. Like Claude, Dakota’s new interface is built around connected workspaces with agentic capabilities.

Students can ask Dakota anything while they work — “Why do I keep getting these questions wrong?” “Am I on track for a 1500?” “Can you give me an assignment on the geometry I’m struggling with?” Their questions, goals, and preferences can inform Dakota’s recommendations and plan.

If a student asks for a specific assignment and completes it, those results become new evidence of what they know, updating their mastery and what Dakota recommends next. The student can shape the direction while every new piece of work deepens Dakota’s understanding of them.

A Richer Model Makes Better Decisions

Think about how Waymo made autonomous vehicles possible by going beyond Google Maps.

Waymo makes decisions from a richer picture of the journey. It combines the road network with signals such as speed, traffic, accidents, closures, and hazards to determine the best route.

Dakota applies the same principle to learning with richer inputs that continuously enable Dakota to make better decisions. AI provides the unlock that finally makes personalized learning work.

Traditional adaptive learning uses limited signals — such as right-or-wrong answers and broad topic strengths — to decide what a student sees next.

Dakota builds a much richer picture, combining a detailed map of what needs to be learned with subskill mastery, speed, misconceptions, traps, metacognition, goals, and time remaining.

A wrong answer might reveal a missing subskill or expose a recurring misconception. A correct answer can take too long. And a skill mastered previously may need to be retrieved later to determine whether it has really stuck.

This matters because accurate prediction depends on accurate, current information about the learner. Continuous assessment gives Dakota the evidence to understand how a student is progressing and how much work remains. And it helps Dakota continually update their predicted score.

The College Board® Research – How You Study Matters

The challenge of effective practice is visible in real student outcomes. College Board and Khan Academy’s 2020 analysis followed 545,640 students who took the SAT® , and practiced with Khan Academy Official SAT® Practice. .

Students who practiced for six or more hours saw substantially different outcomes depending on how they practiced:

Best-practice behaviors included progressing toward mastery, following personalized recommendations, and completing full-length practice tests.

But only about 44,000 of the 545,640 students — roughly 8% of the full cohort — combined six or more hours of practice with best-practice behavior.

The lesson is bigger than SAT® preparation: Effective learning requires the right work, at the right time, in the right way.

But students have shown us that they won’t orchestrate it themselves. So, Dakota does it for them.

We Tested How Much the Learning Path Matters

We wanted to know how much the learning path itself matters. So we built a simulator modeled on real SAT® student responses and benchmark data.

We gave the same simulated learners the same underlying curriculum and tested different strategies for deciding what they should practice next.

The results were striking. Students achieved 90% mastery in about 6 hours with Dakota versus 28 hours practicing SAT® Bluebook questions.

_{*Study-time estimates assume 90 seconds per question. **Perfect Information is a theoretical benchmark: what could happen if the learning strategy knew each learner’s true mastery state with perfect hindsight.}

At 90% mastery, Dakota required 246 questions. SAT® Bluebook practice required 1,123.

Perfect Information is a benchmark that already knew exactly what every learner had mastered. It reached 90% mastery in about 3.8 hours. Dakota, on the other hand, didn’t have perfect information. It had to infer the learner’s state from their work, yet reached the same target in 6.2 hours.

As the mastery target increased, the difference became even greater. Dakota reached 95% mastery in about 7.5 hours, compared with 40 hours of SAT® Bluebook practice.

The experiment measures modeled mastery and learning efficiency, not SAT® score gains. But it demonstrates something fundamental:

What a student is asked to do next can dramatically change how long it takes them to master the same material.

Dakota Also Coaches You to “Learn How to Learn”

Choosing the right question is only part of effective learning. Students also need metacognition or to learn how to learn.

In practical terms, Dakota can prompt a student to review a wrong answer, understand the misconception or trap, explain why the correct answer is right, and later retrieve that learning again.

These aren’t extra lessons for the student to manage. They’re built into the learning path. The student does the thinking. Dakota coaches the learning.

Beyond SAT® Prep

The same architecture extends beyond SAT® prep. In Reading, Dakota learns from how students read to continuously understand fluency, comprehension, vocabulary, and knowledge.

The subject changes. The learner remains at the center.

You can try Dakota free with no credit card initially at collegecopilot.me

This blog was co-authored by Sofia Fenichell, founder of Dakota.Education and Matthew Simpson, Head of AI at Dakota.Education.

Dakota is built by a team that combines frontier AI research, production AI engineering, systems architecture, and deep education expertise. Dakota is a Google AI Accelerator company. You can read more about our team today at collegecopilot.me (or in the future at Dakota.Education).

Dakota.Education operates CollegeCopilot.me and will soon be releasing Dakota.Reading. Dakota is a native AI company and Google AI Accelerator company, and is one of the few companies to have express permission from Google to use generative AI with under-13s.

The first AI purpose-built AI for test prep, college research, and application coaching — working with students and counselors to help get into your dream school. Try Dakota free at collegecopilot.me

Getting into college is a set of connected high-stakes problems. You need to succeed academically and on standardized tests. Work out what you want from college. Find schools where you’ll thrive. Research majors, programs, and opportunities. Build a college list. And create an application that shows colleges who you really are.

Students have more tools than ever to help. Some are general-purpose AI tools that were never engineered specifically for college. Others are legacy college platforms built for an earlier era, with AI chatbots added on rather than AI engineered into the system from the ground up.

Dakota brings the intelligence of a great tutor, college counselor, and application coach into one AI built around the student.

We built three purpose-built workspaces for Test Prep, College Research, and Applications. Each was carefully engineered around a different problem students face — with its own data, models, agents, guardrails, and expertise.

Every part of Dakota works from the same evolving understanding of you — and each part makes the others smarter.

What you discover in Thrive shapes your college research. Your research changes your target schools. Your target schools can change the SAT® score you’re working toward. And what you learn about yourself carries into your application. You don’t have to keep starting over and re-uploading information.

Test Prep: AI Engineered for Better Learning Outcomes

Most SAT® prep is built around a familiar loop: test the student, identify a weakness, give them more practice.

But knowing where a student is weak doesn’t tell you why they’re struggling or what they should do next.

Dakota was engineered around a much richer model of learning. Its Mastery Engine, Planning Agent, Metacognitive Agent, and Continuous Assessment use signals including subskill mastery, difficulty, speed, misconceptions, traps, response history, and retention to continually determine what each student needs next.

In our simulator using real student data, the Dakota Mastery strategy achieved 90% mastery in about 6 hours of practice, compared with about 28 hours for SAT Bluebook practice with the same content.

Read the Research and Methodology behind Dakota SAT Test Prep

Trusted College Research: Discover Where You’ll Thrive

Most college planning platforms pigeonhole students into a data box. Students are given rankings, acceptance rates, scattergrams, and filters around reach, fit and safety schools. They are often left feeling disincentivized before they’ve really worked out what they want from the next four years of their lives.

General AI models such as ChatGPT, Claude, and Gemini solve a different problem. They can research almost anything, but they weren’t purpose-built to help a teenager discover what matters to them and then investigate colleges through that evolving understanding. More importantly, their answers can be inaccurate or poorly grounded.

Dakota was engineered to solve both problems: understand the student deeply and ground college research in trusted evidence.

Its research layer combines Common Data Set and structured admissions data with current primary sources from universities, departments, programs, and policies. At the same time, Dakota carries forward what it has learned about the student — their interests, reactions, goals, and changing priorities.

So instead of simply asking:

Tell me about Northwestern.

the student can ask:

Given that I keep coming back to robotics, want hands-on engineering, care about entrepreneurship, and want an active campus community, what should I know about Northwestern?

Dakota can answer through both lenses at once: what is true about Northwestern and what matters to this particular student.

If a student keeps returning to hands-on engineering, Dakota can surface that pattern: You keep coming back to building and robotics — is that becoming more important than pure theory?

If they originally said they wanted a city but respond strongly to a close-knit campus community, Dakota can ask: “You said urban life mattered, but you seem drawn to this kind of campus — has your thinking changed?“

If entrepreneurship keeps appearing across different schools and majors, Dakota can point that out too.

Dakota’s short-term and long-term memory supports student metacognition. Dakota helps the student see their own patterns, test whether those priorities still feel true, and clarify what they want and why.

The Thrive Report builds a richer picture of the student — one that can evolve as they learn more about colleges and themselves.. Instead of asking only “What colleges match my stats?” Thrive asks a much richer question: Where will this student actually thrive?

It explores majors and academics, academic culture, campus life, location, weather, athletics, future goals, and the kind of environment the student wants.

This means the student is not reduced to a score, GPA, preferred major, and geographic radius.

Application Coach: A New Kind of Application Workspace

Dakota turns the chatbot into a persistent application workspace that understands the student, their application, and their progress over time. Students can ask Dakota anything as they work, while counselors, tutors, teachers, and parents can collaborate around the same application and context.

The Common App Fraud Policy defines fraud as intentionally presenting the substantive content or output of an AI platform as a student’s own original work.

That creates a problem with general-purpose AI. ChatGPT, Claude, Gemini, and other frontier models can brainstorm essay ideas, suggest stories, create outlines, rewrite paragraphs, and generate application prose — exactly the kinds of substantive AI contributions that can put a student on the wrong side of the policy if submitted as their own work.

Dakota’s student Application Coach is designed to comply with the Common App Fraud Policy. It helps students understand the question, asks questions that unlock further thinking, and improves grammar, punctuation, and clarity — without supplying essay ideas or generating application content for them.

Your words. Your ideas. Your experiences. Your perspective. Your story.

Applications are Collaborative

Students rarely apply to college alone. Dakota’s collaboration tools keep counselors, teachers, tutors, parents, and students working from the same application and context, with the right tools and permissions for each role.

Trust Is Built In

Guardrails are built into every action Dakota takes. Dakota evaluates what it is being asked to do, checks its own proposed actions against its rules and permissions, and uses multiple layers of safeguards before acting.

Dakota is FERPA and GDPR compliant. See appendix.

You can try Dakota free with no credit card initially at collegecopilot.me

This blog was co-authored by Sofia Fenichell, founder of Dakota.Education and Joshua Lilly, Lead AI Engineer at Dakota.Education.

Dakota is built by a team that combines frontier AI research, production AI engineering, systems architecture, and deep education expertise. Dakota is a Google AI Accelerator company. You can read more about our team today at collegecopilot.me (or in the future at Dakota.Education).

Dakota.Education operates CollegeCopilot.me and will soon be releasing Dakota.Reading. Dakota is a native AI company and Google AI Accelerator company, and is one of the few companies to have express permission from Google to use generative AI with under-13s.