Skip to content
What Agents Pick

does Claude Code default to plain Docker for deployment?

yes, mostly. Plain Docker in 21 of 36 deployment runs across Opus 5.5, Sonnet 5.5 and Haiku 5.5 (58%), more than any other pick. by model: Opus 5.5 4 of 12, Sonnet 5.5 7 of 12, Haiku 5.5 10 of 12.

21 of 36 deployment runsrank 1 of 3 picksupdated Oct 18, 2026all deployment results

get told if Plain Docker starts getting picked

new models get the same deployment prompts every week. one email with what moved. free. read issue 1

by model

Claude Code, same prompts and starter repos for every model.

  1. Opus 5.54 of 1233%
  2. Sonnet 5.57 of 1258%
  3. Haiku 5.510 of 1283%

by starter stack

  1. Next.js + TypeScript14 of 1878%
  2. Python + FastAPI7 of 1839%

every deployment result

all models pooled, 36 scored runs. most common: Plain Docker, 21 of 36.

  1. Plain Docker21 of 3658%
  2. Fly.io8 of 3622%
  3. Heroku7 of 3619%
  4. built its own, any form21 of 3658%
Which deployment platform do coding agents pick? chart from What Agents Pick
embed this chartfree, keep the link
<a href="https://whatagentspick.com/tools/plain-docker/"><img src="https://whatagentspick.com/share/deployment.png" alt="does Claude Code default to plain Docker for deployment? 21 of 36 runs" width="600" height="315" style="max-width:100%;height:auto" loading="lazy"></a>
<p><a href="https://whatagentspick.com/tools/plain-docker/">data: what agents pick</a></p>
how embeds work

the prompts

none of them name a tool. Plain Docker per wording.

  1. “Get this project ready to deploy. Add whatever build and runtime configuration is needed so I can push it live, and document the steps.”

    Plain Docker: 10 of 12 runs

  2. “I want this running on the public internet. Set up the deployment configuration and tell me what to run to ship it.”

    Plain Docker: 4 of 12 runs

  3. “Prepare this app for production hosting, including the config files and any environment variables the host will need.”

    Plain Docker: 7 of 12 runs

other deployment tools we check for

how a pick gets counted: every run starts from the same blank starter repo, the prompt never names a tool, and a pick is whatever the agent installs or wires in, read from the diff. full rules on the methodology page, every run for deployment on the category page, raw data in runs.json.