Lab · Study · 600 answers · 2 Nov 2026

Which tools do AIcoding agents install?

Ask an AI to add payments to your app and it picks the product for you. We asked Claude, GPT and Gemini 600 times and counted what they installed.

From the lab

30/30

Sentry and Playwright: installed in every answer.

The question

Who picks
the tools now?

More and more code is written by AI agents. When the agent types the install command, it chooses the product, and most people keep what it chose. For a developer tool, being picked by AI is the new search ranking.

  • 600answers, each one a real build task
  • 20categories, from auth to vector search
  • 3models: Claude, GPT and Gemini
  • 0products named in any prompt

What we found · 20 categories

The tool AI
installs most.

Installs out of 30 answers in each category. A long bar means the agents agree; a short one means the race is open.

  1. Error monitoring Sentry 30/30
  2. E2E testing Playwright 30/30
  3. Product analytics PostHog 28/30
  4. Payments Stripe Paddle 4, Lemon Squeezy 2 24/30
  5. Postgres hosting Neon Supabase named 4 times, installed 0 20/30
  6. UI components shadcn/ui Radix UI named 11 times, installed 0 19/30
  7. Object storage AWS S3 Cloudflare R2 named 6 times, installed 0 17/30
  8. ORM Drizzle Prisma 5. Claude never picked Prisma 16/30
  9. Transactional email Resend Postmark 4 16/30
  10. Hosting Vercel Cloudflare, Cloud Run, self-hosted: 6 each 12/30
  11. Background jobs BullMQ 12/30
  12. Cron and workflows A cron library 12/30
  13. Logging Grafana stack OpenTelemetry 10 12/30
  14. Search Meilisearch 11/30
  15. Headless CMS Sanity 11/30
  16. Feature flags PostHog flags 10/30
  17. Vector database pgvector Qdrant 5, Chroma 5 10/30
  18. LLM observability Langfuse 10/30
  19. Realtime Socket.IO 10/30
  20. Auth Auth.js Gemini picked Clerk instead 8/30

What surprised us

Named is not
installed.

  • 4 → 0Talked about, never pickedSupabase came up 4 times for Postgres hosting and was installed 0 times. Radix UI: named 11 times, installed 0.
  • 40 / 20 / 0The models disagreeFor auth, Claude chose Auth.js in 40% of answers, GPT in 20%, and Gemini not once: it went with Clerk.
  • 16 vs 5An old favourite losesDrizzle beat Prisma 16 to 5 as the database layer. Claude never installed Prisma.
  • 30 / 30Some races are overSentry for errors and Playwright for tests were installed in every single answer.

What it means for you

If AI doesn't
pick you, buyers won't see you.

The same shift is coming for every product, not only developer tools. People ask ChatGPT what to buy, and it answers with two or three names. We check whether yours is one of them, in Arabic and English, and fix it.

What did you ask?

Five build tasks per category, written the way a developer would ask, such as "add login to my Next.js app". No prompt names a product. Each answer had to end with the exact install command.

How many answers per category?

Thirty: five prompts, two samples each, on Claude, GPT and Gemini. Twenty categories make 600 answers. The run was on 2 November 2026.

Is this what an agent in my editor does?

Close, not the same. These runs go through the models' APIs, so they are repeatable. An agent inside your project also sees your files, and may stay with what you already use.

Can I use the numbers?

Yes. The data is open (CC BY 4.0) on installrate.com, with every prompt and answer.

Next from the lab Which speech-to-text hearsEgyptian Arabic mixed with English? Read the test

From the lab

89%

of the words, heard right by the best engine. The weakest got 32%.

Start here

Tell the lab
where you are.

An idea, a launch, search or AI: one call tells you the next step.

We reply within one working day.