Making io_uring Actually Fast: I/O Threads, Chunking, and the Memory Story Nobody Talks About
Part 2 of 2. Part 1: We replaced mmap with io_uring in our Rust query engine. It got slower. Part…
Blog
We Replaced mmap with io_uring in Our Rust Query Engine. It Got Slower.
In the beginning, there was mmap. It was convenient: it let us lazily read huge numbers of Arrow IPC files…
The EPIC Framework for Agent Evaluation, Explained
A shopper is using a brand’s AI agent to find wide-fit running shoes to train for a marathon. The agent…
The Blind Spot We Closed in Video Just Reopened in AI Agents
Around 2010, one of the first major broadcasters to launch a streaming product had a problem nobody could name. The apps loaded. The streams played. Every dashboard was green. And viewers were disappearing before a single frame appeared on screen. The metric that explained it didn’t exist. We had to go find it and thenRead more »
The Viewer Doesn’t Experience an “Ad Break.” They Experience the Whole Show.
Twenty million people don’t open a live sports app gradually. They open it ten minutes before kickoff, all at once. That’s exactly when one publisher’s Nexa data showed something breaking: pre-roll ad start failures spiking to 48 times their normal rate, right when everyone tuned in. Nobody on the ad ops side would have calledRead more »
AI Shopping Agents Can Fail Even When the Purchase Succeeds
An AI shopping agent can complete a purchase and still fail the customer. Why? Because outcome and experience are not the same metric. In this episode of Beyond The Cart, Keith Zubchevich, CEO of Conviva, discusses what e-commerce brands need to consider when deploying AI agents. Watch the full episode on YouTube and read theRead more »
Quality of Experience Doesn’t End When the Video Starts (or When the Agent Responds)
Fresh off a World Cup where Conviva monitored tens of millions of concurrent streams across 20+ platforms, Conviva CEO Keith Zubchevich joined the Profluence Sports Podcast to talk about the future of live-streamed events. His main point: the Quality of Experience (QoE) discipline that built streaming can’t stop at the stream. It has to extendRead more »
Conviva Launches SDK Integration via MCP
SDK Integration MCP is Conviva's solution for allowing developers to guide, review and approve agents-driven Sensor SDK integrations.
Agentic Analytics at the 2026 World Cup
Nexa, Conviva's analytics agent, is built to close the gap that's always existed in live sports streaming: speed of response to viewer issues.
Conviva Uncovers Patterns That Make Agent-to-Agent Commerce Convert at 4x
AI-referred buyers convert at 3.5x the site average, and 45.5% when they ask an on-site agent about price. Conviva's A2A Commerce Report reveals the behavioral signals driving the channel.
Agent-to-Agent Commerce Is Real, It’s Here, and It Converts
Download the Conviva report to discover how your business can leverage the A2A acquisition channel to boost conversions and retention.
Why AI Agents Waste the First Two and a Half Minutes of Every Conversation
Conviva research finds that consumer-facing agents spend an average of two minutes and 32 seconds establishing basic context before they can address a customer's actual request.