Field notes · 238 articles
Practical notes on AI, business software, and the decisions behind a production build.
AI, software, and business
Ensure safety and accuracy in your AI workflows. Learn how to build human-in-the-loop authorization gates using Eve.dev's durable execution framework.
Learn how to build a durable AI web scraping agent that extracts structured data, survives browser crashes, and handles rate limiting automatically using Eve.dev.
Build an autonomous AI social media manager that researches trends, generates week-long content schedules, and durably posts content over time using Eve.dev.
A hands-on review of xAI's Grok Voice Agent Builder beta. What the no-code voice agent platform handles well, where you still need the API, and how to decide which one your project needs.
Learn how to build your own AI software engineer. We use the new Model Context Protocol (MCP) to give the Vercel AI SDK agent access to read your local file system, write code, and execute bash commands safely.
I built a dependency-audit agent that runs npm commands on real projects. The new experimental sandbox support in Vercel AI SDK v7 is what made me comfortable shipping it.
Voice is eating text. Learn how to wire the Vercel AI SDK's streaming capabilities with a WebRTC backend to create a low-latency conversational voice agent that handles natural interruptions.
Chatbots are limited. Learn how to connect the Vercel AI SDK to Playwright to build an agent that navigates the web, clicks buttons, and scrapes data autonomously.
Voice agents die if they have latency. I used Gemini Omni Flash to build a real-time conversational agent that responds in under 500 milliseconds.
Single-prompt chatbots are dead. Learn how to orchestrate a 'Swarm' of specialized agents that seamlessly hand off tasks and state to each other using the AI SDK's tool-calling capabilities.
Processing video usually requires massive compute overhead. I used Gemini Omni Flash to extract structured JSON data directly from raw video feeds in real time.
Giving an LLM the ability to write code is dangerous. Learn how to securely connect the Vercel AI SDK to an E2B cloud sandbox so your agent can write Python, execute it on CSVs, and generate charts safely.
Process crashes used to mean lost context for AI agents. I tested the new WorkflowAgent in Vercel AI SDK v7 to see if it actually survives mid-thought restarts.
RAG pipelines are slow because of server round-trips. I moved a Gemini Omni Flash workflow entirely to Edge Functions to kill the cold start.
Console logging agent tool calls is a nightmare. I set up the new Terminal UI in Vercel AI SDK v7 to visualize a local coding assistant.
Giving an LLM permission to delete database rows is terrifying. I used the new human-in-the-loop tool approvals in Vercel AI SDK v7 to build a safer admin agent.
Language models can finally see more than just text. I tested the new multimodal capabilities in Vercel AI SDK v7 to analyze raw video files.
When an agent takes ten seconds to respond, you need to know why. I used the new OpenTelemetry support in Vercel AI SDK v7 to track down a slow API call.
Founders are burning cash on flashy AI features. I'm seeing the actual returns come from boring backend automation.
You do not have to abandon your existing agent frameworks to use the new SDK. Here is how I brought Vercel AI SDK v7 into a custom Claude Code harness.