Salesforce pauses Heroku as AI agents rise; adjust autoscaling and pipelines
Vendors are pivoting from traditional PaaS and CI/CD toward agentic platforms, with Salesforce halting new Heroku features and leaders touting AI agents, underscoring the need to rethink autoscaling and delivery flows. Salesforce put Heroku into sustaining engineering while prioritizing Agentforce [TechRadar](https://www.techradar.com/pro/salesforce-halts-development-of-new-features-for-heroku-cloud-ai-platform)[^1]; meanwhile, Databricks' CEO argues AI agents will render many SaaS apps irrelevant [WebProNews](https://www.webpronews.com/the-saas-sunset-why-databricks-ceo-believes-ai-agents-will-render-traditional-software-irrelevant/)[^2], echoing calls for agentic DevOps beyond classic CI/CD [HackerNoon](https://hackernoon.com/the-end-of-cicd-pipelines-the-dawn-of-agentic-devops?source=rss)[^3]. A real-world ECS/Grafana case study shows AI-heavy, I/O‑bound stacks can miss CPU-based autoscaling triggers, requiring new signals and tests [DEV](https://dev.to/shireen/understanding-aws-autoscaling-with-grafana-gl8)[^4]. [^1]: Confirms Salesforce halted new Heroku features and is prioritizing Agentforce. [^2]: Summarizes Databricks CEO’s thesis that AI agents will displace traditional SaaS. [^3]: Opinion piece advocating agentic DevOps supplanting conventional CI/CD pipelines. [^4]: Demonstrates ECS autoscaling pitfalls for I/O‑bound, LLM-integrated workloads using Grafana and k6.