agents
Start building with OpenAI’s new open-weight model, gpt-oss-120b, now available on Heroku Managed Inference and Agents. This gives developers a powerful, transp…
Building intelligent applications requires powerful, cost-effective AI. Today, we’re simplifying that process by making Amazon’s cutting-edge Nova models direct…
Ever found yourself in the endless loop of tweaking a prompt, running your code, and waiting to see if you finally got the output you wanted? That slow, frustra…
Since its launch, automatic prompt caching has been delivering a notable, zero-effort performance increase for Heroku Managed Inference and Agents. Enabled by d…
This month marks significant expansion for Heroku Managed Inference and Agents, directly accelerating our AI PaaS framework. We’re announcing a substantial addi…
If you’ve ever debugged a production incident, you know the drill: IDE on one screen, Splunk on another, Sentry open in a third tab, frantically copying error m…
Large language models are good at writing code. Data from Anthropic shows that allowing Claude to execute scripts, rather than relying on sequential tool calls,…
Host Sowbhagya Suresh shares some of the latest news and cutting-edge research from across Microsoft—from understanding the challenges facing coding agents to u…
Microsoft researchers have discovered “Lazarus,” a backdoor technique that can reprogram dormant neurons in an AI model, causing an otherwise normal AI agent to…
AI coding agents can waste time and tokens relearning the same lessons. TokenEconomizer is an open-source plugin that builds on past sessions to cut costs while…





