"our agents will break the tasks into smaller tasks, and we have purpose-built agents for those smaller tasks,"
"the things you've done in the past, your builds, your security tests, your code changes, your services and their dependencies. That is used by the agents... so you don't have inaccuracies and hallucinations."
"none of this is done without human input... our AI is not doing the deployment to production. Our AI is creating the deterministic pipeline to do the deployment to production."
Harness offers AI-driven modules including an AI pipeline builder, AI test automation, autonomous code fixing, AI AppSec, and AI-driven chaos testing that injects random failures to test resiliency. Harness claims software teams spend only 30–40% of time on planning and coding, with the remainder on testing, securing, deploying, and optimizing, indicating potential productivity gains from AI in post-coding processes. The company contends that purpose-built agents break tasks into smaller steps, cross-verify outputs, and use organizational context—builds, security tests, code changes, service dependencies—to reduce hallucination and inaccuracies. Human oversight, auditing, compliance review, and deterministic pipelines are retained to mitigate non-determinism.
Read at Theregister
Unable to calculate read time
Collection
[
|
...
]