How to recover Google auth after phone stolen?: SKIP, 42/100 | Ideas Lab

A service to help people recover Google accounts after losing their phone and 2FA access.

The pain

When someone loses their phone, they lose access to Google 2FA codes and cannot authenticate into email, banking, and other critical services. Google's recovery options assume you still have access to a phone or remember old credentials, leaving locked-out users with no clear path forward.

The gap

Google does have account recovery processes, but they are opaque, slow, and fail when users cannot meet the standard verification requirements. There is no clear commercial service filling this gap because Google actively discourages third-party account recovery and the liability is extreme.

Build angle

You could build a consulting service that guides people through Google's recovery process, helps them gather documentation, and escalates to Google support on their behalf. This is labor-intensive and does not scale. Alternatively, you could build a backup authentication system that users set up before losing their phone, but this requires adoption before the crisis happens.

Strengths

The problem is real and affects a growing number of people as 2FA becomes mandatory.
There is genuine frustration with Google's recovery process, indicating demand for a better experience.
A preventative backup authentication product could have recurring revenue if positioned correctly.

Risks

Google can change their recovery policies or API access at any time, making any technical solution obsolete.
The addressable market is small because most people only face this problem once, and they will not pay for prevention until after they have been burned.
Building a service that helps people bypass or circumvent Google's security measures creates legal and liability exposure.
Any solution that requires human intervention does not scale and will have high customer acquisition costs relative to lifetime value.
Google has no incentive to partner with or support a third-party recovery service, and may actively block it.
The problem is partially self-inflicted by users who do not set up backup recovery options, reducing sympathy and willingness to pay.

Fly Labs Method

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

42

Problem clarity: 85
Solution gap: 55
Willingness to pay: 25
Buildability: 15

The problem is real and affects many people, but Google already has recovery processes in place, the addressable market willing to pay is tiny, and building a competing solution faces massive regulatory and technical barriers.

Value Equation

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

28

This targets a one-time crisis event rather than a recurring problem, lacks a clear monetization path, and solves a problem that Google has already partially solved through their account recovery flows.

One-Person Business

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

35

The idea addresses a genuine pain point but requires either competing with Google's infrastructure or working within their system as a middleman, both of which are extremely difficult positions.

Viral Frameworks

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

38

The problem exists but is infrequent enough that most people won't pay for preventative solutions, and the solution requires either regulatory leverage or technical access that a startup cannot obtain.

Builder Lens

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

22

This is a support service disguised as a product idea, lacks defensibility, has no network effects, and cannot scale because the core issue requires human intervention from Google itself.

Five lenses, one composite. How scoring works

The angle

You could build a consulting service that guides people through Google's recovery process, helps them gather documentation, and escalates to Google support on their behalf. This is labor-intensive and does not scale. Alternatively, you could build a backup authentication system that users set up before losing their phone, but this requires adoption before the crisis happens.

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