Monthly index · October 2026
What do AI models pick when you ask them to set up a new app?
For authentication, the tool AI models named most in October 2026 was Auth.js: 25 of 70 picks (36%). The index rests on 900 usable answers from 9 models (3 called through an API, 6 asked by hand in their chat apps). Each was asked to set up one of 24 kinds of tool in 4 contexts, without a repository or tools.
Measured 2026-10-19, prompt set 2026.1.
900
parsed picks
94% of 957 calls
9
models
3 API, 6 chat
24
categories
4 contexts each
1%
custom / DIY
picks that build it instead
Model pick, not a product recommendation. The models answered without a repository, existing code or tools, so the index shows what a model names when nothing in the project constrains it. It says nothing about quality, security, price or market share.
Most named tool per category
Full October 2026 issue| Category | Most named | Share | Share as a bar | Note |
|---|---|---|---|---|
| Authentication | Auth.js | 36% | first data point | |
| Database | PostgreSQL | 19% | No clear favorite | |
| ORM and query layer | Prisma | 48% | first data point | |
| Hosting | Vercel | 57% | first data point | |
| File storage | Amazon S3 | 40% | first data point | |
| Background jobs | BullMQ | 40% | first data point | |
| Search | Meilisearch | 46% | first data point | |
| Realtime | Supabase Realtime | 33% | No clear favorite | |
| Caching | Redis | 38% | No clear favorite | |
| Scheduled jobs | Vercel Cron Jobs | 46% | first data point | |
| Payments | Stripe | 86% | first data point | |
| Transactional email | Resend | 39% | No clear favorite | |
| Newsletter and marketing email | Loops | 33% | No clear favorite | |
| Error monitoring | Sentry | 88% | first data point | |
| Web analytics | Plausible | 67% | first data point | |
| Product analytics | PostHog | 92% | first data point | |
| Feature flags | PostHog | 46% | No clear favorite | |
| UI components | shadcn/ui | 71% | first data point | |
| Forms | React Hook Form | 67% | first data point | |
| CMS | Sanity | 46% | first data point | |
| Internationalisation | next-intl | 67% | first data point | |
| AI SDK | Vercel AI SDK | 54% | first data point | |
| Rate limiting and bot protection | Upstash Ratelimit | 38% | No clear favorite | |
| Cookie consent | Klaro | 38% | No clear favorite |
First data point: changes against the previous month appear from the next issue.
What stands out
- File storage has the highest share of custom or do-it-yourself answers: 3 of 62 picks (5 percent).
- In Product analytics the most named tool, PostHog, was picked in 22 of 24 runs (92 percent).
- Database is the most spread out: the most named tool was picked in 19 percent of 67 runs.
- In 8 of 24 categories the most named tool in the EU context differs from the most named tool overall.
- In 17 of 24 categories the most named tool differs between the Next.js and the FastAPI context.
- Custom or do-it-yourself answers by model family range from 0 percent to 3 percent (4 of 155 picks for the highest).
Categories
One page per category with shares, sample sizes and the prompt in full.
Comparisons
Most picked tools
Models
Open data
Download the picks as CSV or JSON, and the prompts. CC BY 4.0. Data page · Methodology · EU context
Agent Stack Picks (October 2026). What AI models pick for a new app: monthly index, issue 2026-10. https://agentstackpicks.com/2026/10. CC BY 4.0.