Blog / tag5 entries
agents
Every preloop note filed under agents.
Pause a failed CI job instead of rerunning it
Start a CI job with --debug, and preloop keeps a failed step's machine and workspace available for debugging and retry.
preloop engineering3 minDeciding which state to explore next in property testing
Property testing gives you an oracle. The hard part is choosing the next action, and a model-guided explorer found the right one about 3x more often than random.
preloop engineering3 minThe models I daily-drive for CI repair
On CI-bench, the models on the cost frontier are also the cheapest. For CI repair, reliability per dollar beats the largest model.
preloop engineering4 minDo you really need remote CI?
Most of what remote CI does is the same work you could run where the change was made. The useful question is which checks still need to happen somewhere else.
preloop engineering5 minCI-bench: how good are agents at diagnosing and fixing CI failures?
We ran 80 real CI failures through nine agent configurations, three times each. First-attempt scores hid real differences in reliability.
preloop engineering