Shipping AI You Can Defend: A QA Field Report
Beyond the launch posts, Llama 4 is reshaping how analysts approach research synthesis. We talked to the people actually using it in production.
Elena Brost3 min read
The archive
All articles
100 stories from the Inference Daily desk.
Agents Are Eating the Backend, One fine-tuned distillation at a Time
Beyond the launch posts, DeepSeek V4 is reshaping how engineering teams approach expense reporting. We talked to the people actually using it in production.
Mira Castellanos3 min read
Generative Answers, Real Citations: The voice mode Approach
Duolingo is the latest in a string of teams treating small-model orchestration as the default, not the experiment. Here is what they got right — and what they are still figuring out.
Priya Raman3 min read
The Agent Stack Is Quietly Consolidating Around small-model orchestration
Booking.com is the latest in a string of teams treating evals-first development as the default, not the experiment. Here is what they got right — and what they are still figuring out.
Mira Castellanos3 min read
The Automation Playbook: pricing analysis in the LLM Era
Beyond the launch posts, Gemini 3 Pro is reshaping how founders approach pricing analysis. We talked to the people actually using it in production.
Priya Raman3 min read
Why operators Are Suddenly Standardizing on Vercel v0
Snowflake is the latest in a string of teams treating RAG-as-a-service as the default, not the experiment. Here is what they got right — and what they are still figuring out.
Jonas Halvorsen3 min read
The Agent Stack Is Quietly Consolidating Around long-context workflows
Zendesk is the latest in a string of teams treating computer-use agents as the default, not the experiment. Here is what they got right — and what they are still figuring out.
Daniel Okafor3 min read
Inflection's Latest Move Signals a Shift Toward evals-first development
Beyond the launch posts, Phi-4 is reshaping how engineering teams approach code review. We talked to the people actually using it in production.
Jonas Halvorsen3 min read
The Agent Stack Is Quietly Consolidating Around tool-first agents
The interesting story is not the demo. It is the second month, when evals-first development either earns its keep or gets quietly rolled back.
Mira Castellanos3 min read