Le meilleur du dev et de l'IA, scoré chaque jour par un agent. Filtré, résumé, classé. Aucune couleur, aucun bruit — juste la matière.
Ce workshop transforme un prototype de chatbot en expérience persistante: persistance des messages en streaming, création d’un chatId et routage vers /chat/:chatId, sauvegarde en DB et réhydratation de l’UI. Vous verrez comment router, revalider le sidebar et recharger les conversations de manière fiable.
This workshop demonstrates how to turn a quick chat prototype into a persistent product by adding backend persistence, streaming updates, and robust routing. It covers building a POST /api/chat endpoint to stream OpenAI completions, persisting chats with Drizzle and returning a chatId, routing to /chat/:chatId, saving messages in real time while rehydrating the UI from the database.
In this workshop you'll tackle advanced challenges: an evaluator-optimizer loop and showing sources in the frontend. The description frames the system as an evaluator in a loop and proposes frontend source cards—favicon, title and snippet—similar to patterns in Anthropic's Building Effective Agents.
Day 4 focuses on turning subjective agent vibes into objective, data-driven evaluation using LLM Evals. It introduces Evalite, an open-source eval framework built on Vitest to run tests without cloud providers, and guides you to define success criteria and write a first scorer to aim for a 100 score. By end, you'll have a foundational evaluation setup for the DeepSearch agent.
Showing Sources In The Frontend outlines an evaluator-optimizer loop for LLM workflows and recommends displaying sources in the UI as card-like entries (favicon, title and snippet). It reframes the agent as a decision loop—answer when you have enough information, otherwise search—and adapts frontend patterns to present sources clearly.
The article explains observability for AI agents using Langfuse, showing how to set up traces, view them, and attach custom trace metadata. It also covers implementing a time-aware web scraper tool to diagnose and improve a DeepSearch agent.
That workshop reframes the agent as an evaluator-optimizer loop: one LLM call generates a response while another provides evaluation and feedback. It also covers showing sources in the frontend with a card-like UI (favicon, title, snippet) to surface provenance and improve traceability.
This workshop examines how much control the LLM should have over the app's control flow, pitting agents against workflows. It notes that more agentic systems offer flexibility, while deterministic workflows improve predictability. In upcoming exercises, the dial will be turned back toward determinism to test concrete patterns.
Day 1 guides you through building a real AI agent in TypeScript, from wiring an LLM with the Vercel AI SDK to debugging tool calls and securing the app. It covers tool integration (Serper), authentication (Discord login), and rate limiting, showing every step, tool call, and source. By the end, you have a working agent that chats, searches, and transparently explains its work.
This workshop reframes the typical LLM agent as an evaluator-optimizer loop: one call generates a response while another evaluates it, then feedback guides the next step. It emphasizes moving logic from a pure agent to an evaluative loop and optimizes around it. It also covers displaying sources in the frontend as card-like items (favicon, title, snippet) to mirror DeepResearch patterns.
Using Vercel AI SDK's useChat, this workshop guides turning a quick chat prototype into a persistent, streaming chat app. It covers streaming completions, creating/storing chat IDs, routing by chatId, and persisting messages in real time, plus rehydrating UI from the database and updating the sidebar via route revalidation. By the end you’ll have an end-to-end persistent chat experience with routing, saving, and reloading conversations.
Observability is essential when AI agents drift in production. Day 3 guides you through setting up Langfuse, exploring initial traces, and adding custom trace metadata, culminating in a time-aware web scraper tool to diagnose and improve your DeepSearch agent.
Day 3 focuses on observability for AI agents. It guides you to set up Langfuse, inspect traces, and add custom trace metadata to diagnose and improve your DeepSearch agent. By the end, you'll transform it from a mystery into a well-understood, diagnosable system.
Using Vercel AI SDK's useChat, you can prototype a chat quickly, but turning it into a durable, persistent product requires backend persistence, real-time updates, and solid routing. The workshop guides you through building a POST /api/chat endpoint that streams OpenAI completions, using Drizzle to create and return a chatId, saving messages as they stream, rehydrating the UI with past conversations, and keeping the sidebar in sync via route revalidation.
The workshop advances an evaluator-optimizer loop: the model answers when it has enough information and searches for the rest. It also covers displaying sources in the frontend as a card-like list (favicon, title, snippet). The practical goal is to implement an optional Ask Clarifying Questions step and reuse a frontend source-display pattern.
Observability is essential when building AI-driven products, enabling you to see, debug, and improve agent behavior as conversations and calls grow. Day 3 guides you through setting up Langfuse, exploring traces with custom metadata, and building a time-aware web scraper tool to turn the DeepSearch agent into a well-understood system.
Observability is crucial for AI-driven products; Day 3 covers seeing, debugging, and improving agents. You'll set up Langfuse, explore traces, and add custom trace metadata, then build a time-aware web scraper tool. By the end, your DeepSearch agent becomes understandable and deployable with confidence.
Observability is essential when building AI-driven products. Day 3 teaches you to see and debug agent behavior using Langfuse, explore traces, and add custom trace metadata, then to build a time-aware web scraper tool to improve your DeepSearch agent.
The article surveys additional paths toward code independence, examining how to reduce vendor lock-in and improve portability across runtimes and tooling. It highlights patterns and architectures that decouple software from single platforms, encouraging modularity and open standards.
A 2024 piece analyzing the computational aspects of transposing matrices, highlighting core algorithms and performance trade-offs. It discusses memory layout, cache locality, and parallel approaches, with practical notes for implementing efficient transposes in real-world workloads.