emrahsamdan

Yes depending on which connector you chose to connect. There could be a new PR on GitHub, a rollback in CircleCI or a feature flag switch on LaunchDarkly. All waits for a human to chime in by default.

These are all becoming tablestakes, imo for any AI SRE. The real moat is to build the data layer in an efficient manner so that the investigation (and mitigation) is fast and cost-efficient. The models are making it easier for any company at the same time.

Running the test takes around 5-6 hours per vendor depending on how much wrestle it requires (not every system is ideal for ai agents - including ourselves) but the actual work was to come up with the real world scenarios and what would be the expected RCA and remediation for this. Our own SRE team worked for 1.5 weeks for that.

how does it compare to AWS' Application composer?