BlogCategory
How we build AI into real products: LLM integration, AI agents, retrieval, evaluation, and the product and cost decisions behind every AI feature.
Copilot server authentication gives a service its own way to make GitHub Copilot requests for an organization, without borrowing a developer’s signed-in session. That sounds like plumbing. It…
OpenShell agent security matters because an agent that can read files, call APIs, and use credentials needs limits outside its own reasoning loop. NVIDIA announced its OpenShell Reference…
Voxtral 3 voice agents turn speech, reasoning, tool calls, and spoken replies into one product stack. That can remove a lot of assembly work for teams building support…
Agent scale engineering changes the work around code before it changes the code itself. Models can now carry out longer tasks, but a product team still has to…
Gemini agent controls matter before a team lets a workplace agent read documents, create tickets, or coordinate work across tools. Google’s new Gemini agent is built for that…
OpenAI Decisions API gives product teams a narrower way to use a model. Instead of asking for open-ended text, an application can ask a defined question and receive…
OpenAI Dots changes the design problem for teams adopting AI agents. The product is built to keep working between conversations, across connected apps, with its own cloud computer.…
How we add language model features to an existing product: swappable models, retrieval over your data, structured outputs, evals in CI and production safeguards.
How we put image, video, speech and music generation into products: model and pipeline choice, safety layers, rights and provenance, queueing and GPU cost.
Which problems language models actually solve well, how an AI feature is built, evaluated and budgeted, and how we take it from prototype to production.
When an agent is warranted and when a fixed workflow is better, and how we design tools, approvals, sandboxes, scenario evals and audit logs for agents that act.