# Ideation > Brainstorm, evaluate, and select ideas that judges love and you can actually build. Canonical: https://thehackathonplaybook.dev/playbook/ideation Last updated: 2026-06-24 --- ## The Little Alchemy Method The ideation methodology behind $100K+ in hackathon prizes. Inspired by the game Little Alchemy, you start with basic elements, combine them, and discover winning ideas. TL;DR Combine technologies with industries the way Little Alchemy combines elements, and winning ideas emerge. In Little Alchemy you start with four elements (fire, water, earth, air) and combine them into steam, lava, or life. Keep mixing your discoveries and you unlock hundreds of things, from windmills to the internet. Hackathon ideation works the same way. Your building blocks are technologies and industries. Combine them, and winning ideas emerge. #### Your Building Blocks Tools that do something. Single technologies from companies or research papers. OpenAI 4o (LLM) Google Veo 3 (Text to Video) Twilio API (Phone Calls) SunoAI (Text to Music) combine combine #### Your Problem Spaces Spaces that need something. Industries, domains, and user groups. Sports Health Education Defense Finance Entertainment The method is simple: List 20-30 elements and combine them at random. Most pairings flop, but the magic is in the volume: the ones that land are often brilliant. ### Try It Yourself Drag elements into the workspace, then drop them onto each other to discover winning hackathon ideas. 0 / 69discovered Drag elements into the workspace below to combine them TECH LLMs Twilio API Google Veo 3 SunoAI Vision AI Blockchain IoT Sensors INDUSTRIES Health Education Defense Finance Entertainment Sports Climate Legal Drag elements here, then drop them on each other Double-click a workspace element to remove it ## 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. TL;DR Every winning project below started as one simple combination, and swapping a single piece spawns a brand-new idea. #### DispatchAI — UC Berkeley AI Hackathon Grand Prize How two simple combinations led to a first-place finish. Step 1 Step 2 Seems simple? That's the point. The best hackathon ideas aren't complex. They're clear combinations nobody else thought to make. [Live demo](https://dispatchai.art3m1s.me/)[GitHub](https://github.com/IdkwhatImD0ing/DispatchAI)[Devpost](https://devpost.com/software/dispatch-ai) Swap out a single component and the same base combination spawns entirely different ideas: #### Mental Health AI Agent Same tech, different industry. One swap turns a 911 dispatcher into a mental health support line. #### AI Ad Commercial Creator Swap the industry for another tech. An LLM directs video generation for rapid ad prototyping. AdaptED LA Hacks Best Use of Google [Live demo](https://adapted.art3m1s.me/)[GitHub](https://github.com/IdkwhatImD0ing/TeachMe)[Devpost](https://devpost.com/software/teachme-3p7bw1) DispatchAI UC Berkeley AI Hackathon Grand Prize [Live demo](https://dispatchai.art3m1s.me/)[GitHub](https://github.com/IdkwhatImD0ing/DispatchAI)[Devpost](https://devpost.com/software/dispatch-ai) TalkTuahBank HackUTD 1st Overall + Goldman Sachs [Live demo](https://talktuah.art3m1s.me/)[GitHub](https://github.com/aurelisajuan/TalkTuahBank)[Devpost](https://devpost.com/software/talktuahbank) All three projects came from the same method: list elements, combine them, let unexpected connections emerge. It works because it forces you to think across boundaries, not within them. ## Go Deeper Optional theory and prep for when you want more. The essentials are above; expand only what you need. ### TL;DR Decades of creativity research agree: new ideas are old parts recombined, not invented from scratch. #### 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.” Broader experiences give you more “dots” to connect. A more diverse element list makes your combinations more unexpected and powerful. — Steve Jobs, co-founder of Apple, [Wired interview, 1996](https://www.wired.com/1996/02/jobs-2/) #### Bisociation > “The pattern underlying \[the creative act\] is the perceiving of a situation or idea in two self-consistent but habitually incompatible frames of reference.” “Bisociation” is creativity as the collision of two independent mental frameworks. Exactly what happens when you cross “LLMs” with “Defense.” — Arthur Koestler, Hungarian-British author, [The Act of Creation, 1964](https://en.wikipedia.org/wiki/The_Act_of_Creation) #### The Adjacent Possible > “Good ideas are not conjured out of thin air; they are built out of a collection of existing parts, the composition of which expands (and, occasionally, contracts) over time.” Johnson calls that expanding edge the “adjacent possible,” a term he borrowed from biologist Stuart Kauffman. Innovation lives at the edge of what's feasible. The best hackathon ideas use tools that just became possible: a new API, a fresh model, a just-opened dataset. — Steven Johnson, science writer, [Where Good Ideas Come From, 2010](https://en.wikipedia.org/wiki/Where_Good_Ideas_Come_From) #### 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 best ideas come from your own experience. What frustrates you? What gap do others miss? Combine that personal insight with your elements. — Paul Graham, Y Combinator co-founder, [How to Get Startup Ideas, 2012](https://paulgraham.com/startupideas.html) ### TL;DR Stock 20-30 elements before the event: 10-15 tech, 5-10 domains, 5+ wild cards. #### Tech Elements Things that do something. APIs, AI models, hardware, protocols, research papers. - 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 Elements Things that need something. Industries, user groups, and problem spaces. - Healthcare, mental health, eldercare - Education, tutoring, accessibility - Finance, banking, insurance - Defense, emergency services, public safety 5-10 industries minimum #### Wild Card Elements Things that add a unique angle. Unusual constraints, trends, and sponsor challenges. - Sponsor APIs (free credits = an edge) - Trending topics (what's viral now?) - Personal pain points and hobbies - Weird constraints (“What if it were voice-only?”) 5+ wild cards for spice [Linus Pauling](https://en.wikipedia.org/wiki/Linus_Pauling) — Two-Time Nobel Laureate (Chemistry 1954, Peace 1962) > “The best way to have a good idea is to have a lot of ideas.” — Quoted in Fortune, April 1960 He filled in the other half on PBS's NOVA in 1977: “you aren't going to have good ideas unless you have lots of ideas and some sort of principle of selection…” So don't filter while building your list. Chase volume now, not quality. You'll prune later. ### TL;DR Step away and let your brain wander: diffuse, incubating thinking finds the connections focus can't. #### 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: board, then idea list, then back. That rapid mental shifting sparks the unexpected connections behind the best hackathon ideas. Built-in Downtime Unlike Valorant or League, TFT has long pauses between rounds, perfect for jotting down ideas. Try brainstorming mid-clutch in Valorant: it doesn't work. You don't have to play TFT. Pair ideation with anything that keeps your hands busy and your brain free: cooking, cleaning, the gym, a walk. Let your brain wander. #### Focused vs. Diffuse Thinking Barbara Oakley, professor of engineering at Oakland University, popularized two thinking modes in A Mind for Numbers (2014) and in the Coursera course [Learning How to Learn](https://www.coursera.org/learn/learning-how-to-learn) (2014), which she teaches with neuroscientist Terrence Sejnowski: Focused Mode Concentrated, sequential. Good for executing known problems. You at the whiteboard forcing ideas. Diffuse Mode Relaxed, broad, associative. Surfaces novel connections. You walking to the coffee shop when the idea hits. > “Sometimes we need to lose concentration so we can think more clearly.” — Barbara Oakley and Terrence Sejnowski with Alistair McConville, [Learning How to Learn](https://www.penguinrandomhouse.com/books/563935/learning-how-to-learn-by-barbara-oakley-phd-and-terrence-sejnowski-phd-with-alistair-mcconville/), 2018 #### The Five-Step Process In 1939, advertising pioneer James Webb Young formalized a repeatable process for ideas that still holds: 1. Gather: Collect raw material, both problem-specific and general knowledge from other fields 2. Digest: Work the material, examine from different angles, try combinations 3. Incubate: Set it aside. Let the subconscious work while you do other things 4. Eureka: The idea appears, usually when you stop forcing it 5. Verify: Test it in reality and refine with feedback Step 3 is the one most people skip, and the most important. Building your element list is gathering. Playing TFT is incubation. — [A Technique for Producing Ideas, 1939](https://en.wikipedia.org/wiki/A_Technique_for_Producing_Ideas) Staring at a blank doc is the worst way to find ideas. Schedule real breaks: walk, cook, play, hit the gym. Your subconscious keeps working when your conscious mind steps away, and it's often better at finding 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. TL;DR When random combining stalls, reach for SCAMPER, random input, or antidisciplinary thinking to break the block. #### SCAMPER Method Education author Bob Eberle's [Scamper: Games for Imagination Development](https://archive.org/details/scampergamesfori0000eber) (1971) turned Alex Osborn's brainstorming questions into a checklist that expands any idea in seven directions. Substitute: Replace a component Combine: Merge two features Adapt: Reuse in new context Modify: Change scale or shape Put to another use: New application Eliminate: Remove complexity Reverse: Flip the perspective Run each letter on your top idea. “Substitute the API? Combine with another app? Eliminate the most complex step?” #### Random Input Maltese physician and author Edward de Bono, who coined [lateral thinking](https://en.wikipedia.org/wiki/Lateral_thinking), devised this technique for provoking new connections with randomness, set out in Serious Creativity (1992). 1. Pick a random noun: open a dictionary, use a generator, or point at something in the room 2. Force-connect it to your problem. How is your idea like a “lighthouse”? 3. Follow the unexpected links. The weirder the connection, the more original the idea Stuck in a loop of similar ideas? Random input is the fastest way out, as long as the word is genuinely random. The failure mode isn't picking something too random; it's quietly picking something already connected to your problem. #### Antidisciplinary Thinking Joi Ito, then director of the MIT Media Lab, on finding innovation in the white space between fields, from his 2014 essay [Antidisciplinary](https://joi.ito.com/weblog/2014/10/02/antidisciplinar.html). Interdisciplinary work has fields collaborate. Antidisciplinary thinking creates something that fits no existing category: 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 projects 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, [Wired interview, 1996](https://www.wired.com/1996/02/jobs-2/) The best ideas don't come from staring at a blank screen. They come from a broad inventory of elements (technologies you've explored, industries you understand, problems you've felt) plus the courage to combine them in ways nobody else would. The Little Alchemy method mirrors how creativity actually works: not a bolt of inspiration from nowhere, but the systematic collision of ideas from different worlds. Every element is another dot. Every combination connects 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. TL;DR Build the list, combine, step away, push your top ideas with SCAMPER, then pick the one at the edge of the adjacent possible. Build a list of 20-30+ tech, domain, and wild card elements Combine randomly. No filtering, no judging. Just mix. Step away and let diffuse thinking work: walk, play, cook, gym Chase volume. Aim for 15-20 unique combinations Run SCAMPER on your top 3 ideas, pushing 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, and can you ship it in 24-48 hours? Remember: Ideation isn't about finding the perfect idea on the first try. It's about generating enough raw material that one great idea rises to the surface. Trust the process, the volume, and your subconscious.