AI writing detection tool: SKIP, 52/100 | Ideas Lab

AI detection tools address an urgent need but operate in a crowded market with weak defensibility and low willingness to pay.

The pain

Educators, publishers, and content teams cannot reliably tell if text came from ChatGPT or a human. This creates grading uncertainty, plagiarism loopholes, and content authenticity questions. The pain is real and growing as AI tools become mainstream.

The gap

Multiple detection tools already exist, including free options and paid services from established players. Most work at 70-90% accuracy depending on the AI model. The gap is not whether detection is possible, but whether customers will pay enough to sustain a business when free alternatives exist.

Build angle

You can build a working detector in weeks using fine-tuned language models and statistical analysis. The hard part is not the initial build but staying ahead of new AI models, maintaining accuracy as detection techniques become public, and justifying pricing when free tools proliferate.

Strengths

Problem is urgent and growing as AI adoption accelerates in schools and workplaces
Technical barrier to entry is low enough to build an MVP quickly
Multiple customer segments exist: K-12 schools, universities, publishing houses, content agencies
Can integrate into existing platforms like learning management systems for distribution

Risks

Turnitin, Originality.AI, and other established players already have market share and customer relationships
Free tools like GPTZero reduce willingness to pay and compress margins
Detection accuracy degrades as AI models improve, requiring constant retraining and R&D spending
Customers are price-sensitive institutions with tight budgets, limiting revenue per user
No network effects or switching costs once a tool is integrated
AI companies may build detection into their own products, eliminating the market
False positives damage credibility and create legal liability for schools

Fly Labs Method

Is the pain real, is there a gap, is it the right time, can one person build it.

52

Problem clarity: 78
Solution gap: 45
Willingness to pay: 48
Buildability: 38

The problem is real and urgent for educators and publishers, but existing solutions already work reasonably well, customers are price-sensitive, and building a reliable detector requires constant model updates as AI improves.

Value Equation

Dream outcome and how likely it feels, against the time and effort it costs.

41

Schools and publishers need this badly, but they have limited budgets, won't pay much per user, and many free alternatives exist, making it hard to build a sustainable high-margin business.

One-Person Business

Curiosity pull, identity fit, and a path from free value to paid for a solo creator.

55

You can build a working MVP quickly using existing APIs, but you will struggle to differentiate from competitors, the technical moat erodes fast as detection methods become public knowledge, and you cannot easily expand into adjacent markets.

Viral Frameworks

Hook strength, shareability, and how cheaply it can be tested.

48

The market is real but crowded with both free tools and established players like Turnitin, your unit economics depend on volume at low prices, and you need constant R&D spending to stay ahead of new AI models.

Builder Lens

Evidence the problem exists, timing, defensibility, and a model that fits on a napkin.

44

This solves a genuine problem but lacks defensibility, has weak network effects, faces commoditization pressure, and offers limited upside unless you can expand into a broader content moderation platform.

Five lenses, one composite. How scoring works

The angle

You can build a working detector in weeks using fine-tuned language models and statistical analysis. The hard part is not the initial build but staying ahead of new AI models, maintaining accuracy as detection techniques become public, and justifying pricing when free tools proliferate.

No market research recorded for this idea yet.

Semble – Code search for agents that uses 98% fewer tokens than grep

Hey HN! We (Stephan and Thomas) recently open-sourced Semble. We kept running into the same problem while using Claude Code on large codebases: when the agent can't find something directly, it falls back to grep, reading full files or launching subagents. This uses a lot of tokens, and often still misses the relevant code. There are existing tools for this, but they were either too slow to index on demand, needed API keys, or had poor retrieval quality.Semble is our solution for this. It combines static Model2Vec embeddings (using our latest static model: potion-code-16M) with BM25, fused via RRF and reranked with code-aware signals. Everything runs on CPU since there's no transformers involved. On our benchmark of ~1250 query/document pairs across 63 repos and 19 languages, it uses 98% fewer tokens than grep+read and reaches 99% of the retrieval quality of a 137M-parameter code-trained transformer, while being ~200x faster.Main features:- Token-efficient: 98% fewer tokens than grep+read- Fast: ~250ms to index a typical repo on our benchmark, ~1.5ms per query on CPU (very large repos may take longer)- Accurate: 0.854 NDCG@10, 99% of the best transformer setup we tested- MCP server: drop-in for Claude Code, Cursor, Codex, OpenCode- Zero config: no API keys, no GPU, no external servicesInstall in Claude Code with: claude mcp add semble -s user -- uvx --from "semble[mcp]" sembleOr check our README for other installation instructions, benchmarks, and methodology:Semble: https://github.com/MinishLab/sembleBenchmarks: https://github.com/MinishLab/semble/tree/main/benchmarksModel: https://huggingface.co/minishlab/potion-code-16MLet us know if you have any feedback or questions!

AI

BUILD

85FL score

Postgres extension for BM25 relevance-ranked full-text search

Last summer we faced a conundrum at my company, Tiger Data, a Postgres cloud vendor whose main business is in timeseries data. We were trying to grow our business towards emerging AI-centric workloads and wanted to provide a state-of-the-art hybrid search stack in Postgres. We'd already built pgvectorscale in house with the goal of scaling semantic search beyond pgvector's main memory limitations. We just needed a scalable ranked keyword search solution too.The problem: core Postgres doesn't provide this; the leading Postgres BM25 extension, ParadeDB, is guarded behind AGPL; developing our own extension appeared daunting. We'd need a small team of sharp engineers and 6-12 months, I figured. And we'd probably still fall short of the performance of a mature system like Parade/Tantivy.Or would we? I'd be experimenting long enough with AI-boosted development at that point to realize that with the latest tools (Claude Code + Opus) and an experienced hand (I've been working in database systems internals for 25 years now), the old time estimates pretty much go out the window.I told our CTO I thought I could solo the project in one quarter. This raised some eyebrows.It did take a little more time than that (two quarters), and we got some real help from the community (amazing!) after open-sourcing the pre-release. But I'm thrilled/exhausted today to share that pg_textsearch v1.0 is freely available via open source (Postgres license), on Tiger Data cloud, and hopefully soon, a hyperscalar near you:https://github.com/timescale/pg_textsearchIn the blog post accompanying the release, I overview the architecture and present benchmark results using MS-MARCO. To my surprise, we were not only able to meet Parade/Tantivy's query performance, but exceed it substantially, measuring a 4.7x advantage on query throughput at scale:https://www.tigerdata.com/blog/pg-textsearch-bm25-fu

AI

BUILD

85FL score

GlycemicGPT – Open-source AI-powered diabetes management

I'm a Type 1 diabetic and software engineer. Last year I went months between endocrinologists with no clinician reviewing my data. I'm an engineer, so I built the tool I needed — and now I'm open sourcing it. GlycemicGPT is a self-hosted platform that connects continuous glucose monitors, insulin pumps, and existing Nightscout instances to an AI analysis layer running on your own infrastructure. Data sources:Dexcom G7 (cloud API) Tandem t:slim X2 and Mobi pumps (direct BLE) Nightscout (point it at your existing instance and you're running in minutes)What the AI layer does:Daily briefs summarizing overnight and 24-hour patterns Meal response analysis Conversational chat with RAG-backed clinical knowledge Predictive alerting with configurable thresholds and caregiver escalationImportant: this is monitoring and analysis only. GlycemicGPT does not deliver insulin, does not control your pump, and is not a closed-loop system. It reads your data and gives you insight on top of it. Your clinical decisions stay between you and your care team. Architecture:Self-hosted via Docker or K8S — the GlycemicGPT stack runs entirely on your hardware BYOAI — bring your own AI provider. Use Ollama for fully local operation (no data leaves your hardware), or point it at Claude, OpenAI, or any OpenAI-compatible endpoint if you prefer a hosted model. Data flows directly from your instance to the provider you choose; nothing is routed through any centralized service operated by the project. GPL-3.0, no subscriptions, no vendor lock-inStack:Backend API: FastAPI, Python 3.12, PostgreSQL 16, Redis 7 Web Dashboard: Next.js 15, React 19, Tailwind CSS, shadcn/ui AI Sidecar: TypeScript, Express, multi-provider proxy Android App: Kotlin, Jetpack Compose, BLE Wear OS: Kotlin, Wear Compose, Watch Face Push API Plugin SDK: Kotlin interfaces, capability-based, sandboxedLooking for contributors — especially folks with BLE/Android experience or anyone in the diabetes tech spa

AI

BUILD

85FL score

All AI ideas