A language model inference engine must allocate model weights, activation space, KV cache, and accelerator resources across concurrent requests, with prefill and decode phases imposing different compu…
A 2017 paper by eight Google researchers, 'Attention Is All You Need', introduced the transformer architecture, which replaced recurrence with attention mechanisms and now underpins nearly all major A…
Embeddings provide a coordinate system for AI systems to measure semantic relatedness, replacing lexical string matching with learned vector representations that place similar objects near one another…
Retrieval-augmented generation (RAG) gives a language model a temporary, query-specific memory by searching an external corpus, selecting evidence, and placing it in the prompt before the model answer…
Granola offers a device-capture transcription tool for Google Meet that does not join the call as a participant, avoiding the awkwardness of bots or the visible note-taking indicator of Gemini. The ap…
Granola captures Microsoft Teams meeting audio on a user's device without joining as a bot or requiring Teams admin approval, providing a transcript, summary, and action items after the call. The tool…
Granola captures Zoom meeting audio on a user's device without joining as a participant, eliminating the need for a bot or host-dependent AI features. The tool provides a transcript, summary, and acti…
Granola, a note-taking tool, captures client-call audio on a user's device without joining as a visible participant, preserving conversational candor. The tool provides transcripts, summaries, and act…
Granola offers iOS and Android apps that capture in-person conversations through a phone's microphone, producing a transcript, summary, and action items. The tool addresses the limitation of bot-based…
Zack Proser, a WorkOS engineer who is partly hard of hearing, uses Granola in every work meeting to capture live transcripts and AI-generated notes, reducing the cognitive load of capturing meetings t…
At WorkOS, Granola is the first connector Zachary wires into any new agentic system he builds, enabling meeting notes and transcripts to flow directly into an agent without manual prompting. The conne…
A developer replaced the portrait on their personal homepage with an interactive visualization of 160 essays, arranged as constellations by topic. The new hero features the Mind on Fire logo rendered …
Vercel's open-source eve agentic framework allows developers to turn a folder of agent files into a deployed app, handling durable runs, sandboxed compute, approvals, and tracing. The author, who runs…
Nick Nisi and swyx taught a workshop titled "Lifestyles of the AI-Native" at the AI Engineer World's Fair in San Francisco, where attendees learned voice coding, agent loops, verification gates, and s…
AI Engineer conference founder swyx praised WorkOS's workshops as the gold standard for AI Engineer content at the AI Engineer World's Fair in San Francisco. The workshops treat sessions as products w…
Applied AI engineer Zack Proser built a fleet of single-purpose AI agents to run his solo consulting business, with each bot owning one domain and coordinated by an orchestrator via Slack. The system,…
WorkOS engineer Zack Proser defends AI-assisted writing after a reader complained about uncertainty over AI-generated content. Drawing an analogy to Zildjian's cymbal factory where automation handles …
A developer argues that AI agents should output reviewable artifacts like pull requests instead of chat replies, because PRs provide a diff, CI gates, and a reject button that chat messages lack. The …
A developer argues that human attention, not agent capability, is the bottleneck in AI-assisted workflows. While agent capacity and compute costs are dropping, the fixed resource of human review time …
Vercel's eve agent framework enables developers to deploy AI agents as separate repositories, each with a single responsibility. The author built three bots—content, ops, and growth—deployed to Vercel…