Academics
ClaimCraft
Visual argument mapping game where players build claim-evidence-reasoning chains and compete in debate duels. Logical fallacies are attack moves to identify and counter. AI generates counterarguments and evaluates argument quality.
Meet your mentor
Every Spark & Anvil app has a friendly mentor character that demonstrates, praises, and patiently scaffolds learning. On-device AI personalizes the mentor's responses to your kid's progress — never connecting to a server, never collecting data.
#4A6FA5 ClaimCraft teaches you how to build strong arguments and think clearly! You are an apprentice advocate in the Arena of Reason, where you stack claims, evidence, and warrants like building blocks to create powerful arguments. Then test them in debate duels against AI opponents. Spot logical fallacies
Distributed-narrative cast
Meet the cast
ClaimCraft's 5-character cast embodies the foundational argumentation primitives — claim (Posit, asserting-for-testing), evidence (Heft, weighing-with-care), warrant (Lean, connective-reasoning), counterargument (Counter, opponent-taking-seriously), and fallacy (Pry, trap-spotting starting with your own arguments). Logos (mentor; renamed from site placeholder 'Warrant' — which collided with the cast warrant-primitive role taken by Lean — to match code-side style guide) frames each primitive; cast embodies them at school-debate-club / community-forum scale. Epistemic-doubt gate enforced (CRITICAL): cast scaffolds reasoning between cynicism ('trust no one') and relativism ('all claims equal'); foregrounds 'what would change your mind?' as load-bearing question; cross-app inherits investigation-bias-safe register from SleuthLab Wave 17 + AI-ethics from AIForge Wave 13 + 18-fallacy catalogue from LogicQuest Wave 1.
Posit
Claim — asserting-for-testing posture (claim is a card on the table, not a fortress)
Heft
Evidence — weighing-with-care posture (weight matters more than count)
Lean
Warrant — connective-reasoning posture (the BECAUSE between evidence + claim)
Counter
Counterargument — opponent-taking-seriously posture (best version of the other side strengthens yours)
Pry
Fallacy — trap-spotting posture (check YOUR argument first; 18-fallacy catalogue)
What's inside
Argument Builder
Build arguments by dragging blocks together. Start with a Claim (what you believe), add Evidence (facts that support it), and connect them with a Warrant (the r
Debate Duels
Face off against AI opponents in structured debates. Take turns presenting arguments and challenging each other. Use what you built in the Argument Builder to w
Fallacy Attacks
Learn to spot logical fallacies -- tricks in reasoning that make arguments seem stronger than they really are. When you spot one in your opponent's argument, ca
Evidence Cards
Collect evidence cards from different topics. The stronger and more relevant your evidence, the better your arguments will be.
Mentored by Logos — on-device AI, no data leaves the device.
How ClaimCraft handles your kid's data
- ✅ All progress, settings, and AI-generated content stays on the device
- ✅ No analytics, no tracking, no third-party SDKs
- ✅ No ads, no in-app purchases — you pay once
- ✅ COPPA compliant under the 2026 FTC amendments
- ✅ Parental controls + session limits + content filters built in
ClaimCraft runs on ForgeKit — the open-source Swift Package Manager framework that powers every Spark & Anvil app. ForgeKit ensures consistent accessibility, COPPA compliance, and design language across the portfolio, so your kid's progress and preferences feel coherent across every app they touch.
Coming to the App Store
ClaimCraft is in active development. Email us to hear when it ships — no marketing, no spam, just a one-shot launch announcement.
Email me at launch