PHASE 2 OF 5

Ideation

Brainstorm, evaluate, and select ideas that judges love and you can actually build.

The Little Alchemy Method

The ideation methodology behind $100K+ in hackathon prizes. Inspired by the game Little Alchemy — start with basic elements, combine them, and discover winning ideas.

In Little Alchemy, you start with four basic elements — fire, water, earth, and air — and combine them to create new items like steam, lava, or life. You keep mixing your discoveries to unlock hundreds of different things, from windmills to the internet.

Hackathon ideation works the same way. Instead of natural elements, your building blocks are technologies and industries. Combine them, and winning ideas emerge.

TECH ELEMENTS
Your Building Blocks
Single technologies made by various companies or from research papers. Things that do something.
OpenAI 4o (LLM)
Google Veo 3 (Text to Video)
Twilio API (Phone Calls)
SunoAI (Text to Music)

combine

INDUSTRIES
Your Problem Spaces
Industries, domains, and user groups. Things that need something.
Sports
Health
Education
Defense
Finance
Entertainment

The method is simple: Start with 20-30 different elements and just try randomly combining things together. The magic is in the volume of combinations — most won't work, but the ones that do are often brilliant.

Combinations in Action

Here's exactly how the Little Alchemy method produced ideas that won major hackathons. Each winning project started as a simple combination.

CASE STUDY
DispatchAI — UC Berkeley AI Hackathon Grand Prize
How two simple combinations led to a first-place finish.

Step 1

LLMsTwilio APILLM answering phone calls

Step 2

LLM answering phone callsDefenseAI 911 Dispatcher — DispatchAI

Seems simple right? That's the point. The best hackathon ideas aren't complex — they're clear combinations that nobody else thought to make.

Now watch what happens when you swap out a single component. The same base combination spawns entirely different ideas:

SWAP: INDUSTRY
Mental Health AI Agent
LLM answering phone callsHealthMental Health AI Agent

Same tech combination, different industry. One swap turns a 911 dispatcher into a mental health support line.

SWAP: TECH
AI Ad Commercial Creator
LLMsGoogle Veo 3Iterative AI Ad Creator

Swap out the industry for another tech element. LLM directs video generation for rapid ad prototyping.

AdaptED

LA Hacks

Best Use of Google

DispatchAI

UC Berkeley AI Hackathon

Grand Prize

TalkTuahBank

HackUTD

1st Overall + Goldman Sachs

All three projects were born from the same method — list elements, start combining, and let unexpected connections emerge. The method works because it forces you to think across boundaries instead of within them.

Why This Works — The Science of Combinatorial Creativity

The Little Alchemy method isn't just a personal hack — it's backed by decades of research from the world's best thinkers on creativity and innovation.

STEVE JOBS
Connecting Things
“Creativity is just connecting things. When you ask creative people how they did something, they feel a little guilty because they didn't really do it, they just saw something. It seemed obvious to them after a while.”

Jobs argued that broader experiences give you more “dots” to connect. The more diverse your element list, the more unexpected — and powerful — your combinations.

— Wired interview, 1996

ARTHUR KOESTLER
Bisociation
“The creative act is the perceiving of a situation or idea in two self-consistent but habitually incompatible frames of reference.”

Koestler coined “bisociation” to describe creativity as the collision of two independent mental frameworks. That's exactly what happens when you cross “LLMs” with “Defense.”

— The Act of Creation, 1964

STEVEN JOHNSON
The Adjacent Possible
“Good ideas are not conjured out of thin air; they are built out of a collection of existing parts… the adjacent possible.”

Innovation lives at the edge of what's currently feasible. The best hackathon ideas use tools that just became possible — a new API, a freshly released model, a just-opened dataset.

— Where Good Ideas Come From, 2010

PAUL GRAHAM
Notice, Don't Invent
“Live in the future, then build what's missing. The verb you want to be using with respect to startup ideas is not ‘think up’ but ‘notice.’”

The Y Combinator co-founder argues the best ideas come from your own experience. What frustrates you? What gap do you see that others miss? Combine that personal insight with your elements.

— How to Get Startup Ideas, 2012

Building Your Element List

Before you can combine, you need inventory. Here's how to assemble 20-30 high-quality elements before the hackathon even starts.

TECH
Tech Elements
APIs, AI models, hardware, protocols, research papers — things that do something.
  • LLMs (GPT-4o, Claude, Gemini, Llama)
  • Speech APIs (Twilio, Deepgram, ElevenLabs)
  • Vision models (YOLO, SAM, GPT-4V)
  • Generative media (Veo, Suno, Midjourney)

10-15

tech elements minimum

DOMAIN
Domain Elements
Industries, user groups, and problem spaces — things that need something.
  • Healthcare, mental health, eldercare
  • Education, tutoring, accessibility
  • Finance, banking, insurance
  • Defense, emergency services, public safety

5-10

industries minimum

WILD CARD
Wild Card Elements
Unusual constraints, trending topics, and sponsor challenges that add unique angles.
  • Sponsor APIs and required tech (free credits = advantage)
  • Trending topics (what's viral this week?)
  • Personal pain points and hobbies
  • Weird constraints (“What if it had to be voice-only?”)

5+

wild cards for spice

Linus Pauling — Two-Time Nobel Laureate

“The best way to have a good idea is to have a lot of ideas. You aren't going to have good ideas unless you have lots of ideas and some principle of selection.”

Don't filter while building your list. The goal at this stage is volume, not quality. You'll prune later.

The Wandering Mind

The best hackathon ideas don't come from staring at a blank screen. They come when you let your brain wander — and there's hard science behind why.

SECRET WEAPON
TFT Helps Me Win Hackathons
Yes, Teamfight Tactics by Riot Games. Here's why it's a legitimate ideation tool.

Rapid Context Switching

TFT forces you to switch gears constantly. One second you're focusing on your board, the next you're back to your idea list. This rapid mental shift sparks unexpected connections — exactly how the best hackathon ideas emerge.

Built-in Downtime

Unlike Valorant or League, TFT gives you long pauses between rounds — perfect for jotting down quick ideas. Ever tried thinking up a startup idea while mid-clutch in Valorant? Doesn't work.

You don't have to play TFT. The principle is: pair ideation with any activity that keeps your hands busy and your brain free — cooking, cleaning, gymming, walking. Let your brain wander, and the best ideas will come to you.

BARBARA OAKLEY
Focused vs. Diffuse Thinking

Professor Barbara Oakley's research on learning reveals two distinct thinking modes:

Focused Mode

Concentrated, sequential thinking. Good for executing on known problems. This is you at the whiteboard trying to force ideas.

Diffuse Mode

Relaxed, broad, associative thinking. Supports novel connections. This is you walking to the coffee shop when the idea suddenly hits.

“Sometimes backing off can be the best thing you can do when learning something new.”

— Learning How to Learn

JAMES WEBB YOUNG
The Five-Step Process

In 1939, advertising pioneer James Webb Young formalized a repeatable process for idea generation that still holds today:

  1. 1
    Gather Collect raw material — specific knowledge of the problem and general knowledge from other fields
  2. 2
    Digest Actively work the material, examine from different angles, try combinations
  3. 3
    Incubate Set the problem aside. Let the subconscious work while you do other things
  4. 4
    Eureka The idea appears — usually when you're not forcing it
  5. 5
    Verify Shape and test the idea in reality, refine with feedback

Step 3 is the one most people skip — and it's the most important. Building your element list is gathering. Playing TFT is incubation.

— A Technique for Producing Ideas, 1939

Sitting at a desk staring at a blank doc is the worst way to think of ideas. Schedule real breaks during ideation. Walk, cook, play a game, hit the gym. Your subconscious keeps working even when your conscious mind steps away — and it's often better at finding the non-obvious connections.

The Ideation Toolkit

Three additional frameworks to break through creative blocks. Use these when random combining stalls or you want to push ideas further.

SCAMPER
SCAMPER Method
Bob Eberle's structured checklist for expanding any idea in seven directions.
S
Substitute Replace a component
C
Combine Merge two features
A
Adapt Reuse in new context
M
Modify Change scale or shape
P
Put to another use New application
E
Eliminate Remove complexity
R
Reverse Flip the perspective

Run each letter on your top idea. “What if we Substituted the API? Combined with another app? Eliminated the most complex step?”

LATERAL THINKING
Random Input
Edward de Bono's technique for provoking new connections through randomness.
  1. 1Pick a random noun — open a dictionary, use a generator, or point at something in the room
  2. 2Force-connect that word to your problem space. How is your idea like a “lighthouse”?
  3. 3Follow the unexpected associations — the weirder the connection, the more original the idea

When your team is stuck in a loop of similar ideas, random input is the fastest way to break out. De Bono argued the risk is never being too random — it's not being random enough.

MIT MEDIA LAB
Antidisciplinary Thinking
Joi Ito's framework for finding innovation in the white space between fields.

Unlike interdisciplinary work (different fields collaborating), antidisciplinary thinking creates something that doesn't fit any existing category. It's the white space between the dots on a map of knowledge.

Ask Yourself

  • Which field would never normally work on this problem?
  • Does this idea feel uncategorizable? Good — pursue it.
  • What would happen if a musician designed this? A chef? A game designer?

The best hackathon projects often feel weird at first. “An AI 911 dispatcher?” sounded strange until it won grand prize. Lean into the weirdness.

“Creativity is just connecting things.
The broader one's understanding of the human experience, the better design we will have.

— Steve Jobs, co-founder of Apple

In hackathons, the best ideas don't come from staring at a blank screen. They come from having a broad inventory of “elements” — technologies you've explored, industries you understand, problems you've felt — and the courage to combine them in ways nobody else would.

The Little Alchemy method works because it mirrors how creativity actually functions: not as a bolt of inspiration from nowhere, but as the systematic collision of ideas from different worlds. Every element you add to your list is another dot. Every combination is an attempt to connect them.

The more dots you collect, the more connections become possible.

Ideation Checklist

A step-by-step summary you can follow before and during your next hackathon. Print it, screenshot it, or just remember the flow.

Build your element list — aim for 20-30 tech + domain + wild cards

Start combining randomly — don't filter, don't judge, just mix

Step away and let diffuse thinking work — walk, play, cook, gym

Generate volume first — aim for 15-20 unique combinations

Apply SCAMPER to your top 3 ideas — push them in all 7 directions

Pick the idea at the edge of the adjacent possible — what just became feasible?

Validate with your team — does it excite everyone? Can you build it in 24-48 hours?

Remember: The goal of ideation isn't to find the perfect idea on the first try. It's to generate enough raw material that one great idea rises to the surface. Trust the process, trust the volume, and trust your subconscious.