← statichum.studio

LLM-Driven Predictive Test Selection That Reads Your PR Diff And Picks Which Test Suites Should Be Blocking After CloudBees Bought Launchable

dev tool real project •• multiple requests

An HN top-thread asker wants 'an LLM tool that can sit on a CI pipeline to propose what tests should be blocking' by reading the diff, not just retry-pass patterns... and a way to estimate how many times to repeat new tests to prove they aren't flaky to begin with. Launchable was the obvious answer here, but CloudBees bought it and rolled it into 'CloudBees Smart Tests' enterprise tier, leaving smaller teams without an OSS or affordable SaaS path to LLM-based change-aware test selection.

builder note

Build it as a CI step that emits a JSON test-plan, not a hosted SaaS dashboard. Buildkite, GitHub Actions, GitLab and CircleCI users all want the same primitive... they don't want yet another login. Hard problem inside the LLM is staying cheap on monorepo-size diffs. Use embedding similarity to test files first, only escalate to a reasoning model when similarity is ambiguous.

landscape (3 existing solutions)

The 'change-aware test selection' category is now dominated by one acquired enterprise product (CloudBees Smart Tests) and a handful of retry-only flake detectors. There is no LLM-native, vendor-neutral, OSS or affordable-SaaS option.

CloudBees Smart Tests (ex-Launchable) Now bundled inside CloudBees enterprise pricing... small teams and indie maintainers can't access it standalone. The original Launchable free tier is gone.
Atlassian Flakinator + TestDino + BrowserStack All work on retry-and-pass signal AFTER tests have already been run. None read the PR diff to predict which tests are even worth running, and none ML-estimate the flake floor of a NEW test.
BuildKite + managed Anthropic provider BuildKite now proxies Claude through pipelines so you can build this yourself in pipeline scripts, but it ships no off-the-shelf test-selection product, just the LLM substrate.

sources (3)

hn https://news.ycombinator.com/item?id=46345827#46354793 "LLM analyze changes and propose the set of test suites that is relevant to the change" 2026-02-12
other https://www.cloudbees.com/blog/cloudbees-acquires-launchable... "Launchable is joining the CloudBees family" 2025-08-14
other https://testdino.com/blog/flaky-test-detection-tools "Most flaky test detection tools work by tracking retries... when a test fails on the first attempt but passes on retry, it gets flagged" 2026-03-15
ci-cdtestingllmdeveloper-toolsopen-source