Experimenting with tldraw, xyflow · React Flow · Svelte... Flow & Mermaid JS as visual ways to interact with a code base for interactive modern code review. Claude & Codex can generate so much code so quickly that we are going to need new ways to review and understand their work. Markdown documents, ERDs, tree-maps, flow-charts, systems architecture diagrams, process maps. These could be the new lingua franca of a higher level abstraction of software development. What you're seeing below is a visualisation of the database structure of a Laravel app, automatically generated in a visual code review tool to help with the review of a new feature.show more

My weekend project is to do a complete review... of Claude Code/Desktop... Stay tuned for the review I'll publish with everything I findshow more

Cursor Origin (Cursor Review) has been tested in a... closed beta with selected partners internally and will likely be announced later today. Users will get access to new tabs called Codebase and Review. > The Codebase tab will let users sync their repositories from Github. > The Review tab will be dedicated to the "agentic code review" process, in which users will be notified when their attention is required. Currently, the Cursor Origin page shows a waitlist form, which makes a lot of sense since they will have to copy a ton of code repositories. > "Code is moving faster than any infrastructure was built to handle. Origin was designed for this moment."show more

A Refine review often surfaces errors that authors (and... other AI's) missed. A common request: can Refine check whether the issues are fully addressed in a new version of the work? We're happy to be rolling out a new feature that does exactly this with a new review. 1/show more

Code reviews Codex goes beyond static analysis—it checks a... PR against its intent, reasons across the codebase and dependencies, and can run code to validate the behavior of changes. Set it up to auto-review new PRs in your repo, or tag @ codex.show more

if you use claude code, this will save you... real money. the problem: every time you make an edit, your ai rereads the whole codebase to figure out what changed. tens of thousands of tokens, every turn, for context it already had. this repo fixes it. it’s called code review graph, and it just maps your entire codebase: every file, every function, every connection laid out so you can see the actual shape of your project how to set up (2 min): 1. pip install code-review-graph 2. code-review-graph install - auto-configures Claude Code, Cursor, Codex, Gemini CLI + more 3. code-review-graph build change one function, and it traces exactly what that touches... every caller, every dependent file, every test. your ai only reads what's affected, not the whole repo. and the savings are wild. a task that used to burn ~100,000 tokens (about a dollar) now runs closer to a penny.show more

Claude Code 2.1.90 just dropped with a new /powerup... command Run it and you get interactive lessons that teach you how to use Claude Code right inside the tool. It's solid and has a lot of potential for learning directly in the terminal. Curious how the UI will look in VSCode and Claude Code Desktop. Going to keep digging into this new release!show more

Human review tooling, using Pierre's diff/tree components, is also... built in. In addition to leaving comments & asking targeted questions, the review UI can generate overviews (with visualizations) of a change to help spot high-level architectural issues and point you towards the areas that deserve your eyes the most.show more

How we prototype using Claude Code Prototyping used to... be so time-consuming that you could only afford to make 1 or 2. Claude Code changed that, now we build dozens of prototypes for a single feature Here's how we rebuilt the todo list, with the actual prompts included:show more

Claude Code Desktop now opens a new window for... each session This makes it much easier to visualize multiple Claude Code agents running in parallel My current stack depends on the task: - Ghostty: when starting a project. Bash commands, git, env variables, provider connections. All manual through the terminal with a Claude panel running alongside. - Claude Code Desktop: once everything is configured. GitHub connected, CLAUDE.md, Skills, subagents and Hooks ready. Claude Code runs on its own, no more terminal setup, just panels running and outputs to review. - VSCode: when I need to review code by hand. I use it less and less, but there are moments where I have to confirm Claude got it right. I usually open the Claude extension inside VSCode, but it lacks most of the CLI features so it's limited Solid update. Worth trying once your workflows are already set up 👇show more

Claude can code- but can claude grow?! 🪴 So... far the answer is YES. Claude is successfully keeping a living organism ALIVE. There were some hiccups this week! Some errors and resets, but Claude managed to power through and take care of Sol 🍅 A week in review:show more

Warp is a really great terminal, and I thought... y'all deserved a rundown of all its features. So, I recorded one! We cover everything from block filtering to code review, with a bunch of features in-between you might not know about. Enjoyshow more

HE DESCRIBED A SITE TO CLAUDE CODE AND WALKED... AWAY FOR 8 MINUTES What came back looked like a studio spent weeks on it. The setup that made it work: > Two design skills installed - Claude stops using safe boring defaults. > Visual references instead of text descriptions. > One detailed prompt with the concept, Claude asks clarifying questions before building. First version already solid -> review pass, one batch of fixes, done. What used to take a designer and a developer and several weeks of handoffs now takes a single session and no coding experience. Full walkthrough in the article below ↓show more

Updated the subagents system in my custom Pi extension... to include: - Pi subagents - Codex subagents - Claude Code subagents The Pi thread can call and spin up any of them, and instead of just using the "codex exec" or whatever, it'll do a tool call that wraps it up in a first class way. Have a decent UI for them already added in as well. Pi being the main thread then having Codex/Claude Code as tools when needed feels so good. A flow I'm already using a ton is: "Implement feature ___, have a cc fable subagent research and plan out the api design + feature, then have a codex subagent implement it, then have a cc fable subagent do a review/fixes focused on simplicity and correctness" I also have a dynamic workflows extension setup and working, but it's not nearly as polished yet. Probably gonna make the subagent system more robust, then built it around that so u could have a workflow that flows between codex/cc/pi...show more

in software, we're entering a new age of skyscrapers:... rather than a small group of humans hand-typing code into a computer, software is now built by thousands of humans and agents working together to build applications at a scale that was previously unthinkable. the unsung heroes of this new era are infrastructure engineers. they are the people who are figuring out how to make software with 100x the amount of code, and 1000x the amount of contributors actually work OpenAI is one of the few companies already operating at this scale so we Every 🪨 spent a few days deep inside of the company to learn how their infrastructure team thinks about building software skyscrapers—and how they use agents to do it one of the most important articles we've written this year:show more

I’ve built a background daemon that connects to Linear... for one of my enterprise clients (multi-billion company). It runs autonomous AI workflows: – Creates PRDs from tickets – Waits for human review – Implements, verifies, and opens PRs automatically Built with LangGraph for orchestration, Codex + Claude for deep code understanding, direct LLM's API calls (via OpenRouter) for more deterministic tasks. It’s pretty cool watching the whole flow execute live in the console ⚡️show more

Simplicity is at the heart of great software. This... is one of the reasons why Claude Code has been sticky for me. As a builder, I love planning and brainstorming, and this is now a key focus of Claude Code. I use Shift + Tab a lot to cycle between brainstorming, planning, and execution. This functionality provides the appropriate interface for me to either be very involved or less involved as I please. This works particularly well when building out new and complex features or entire new projects. This saves a huge amount of time. It allows me to tune Claude Code to execute and build more effectively. It also builds a loop of trust, and I often (surprisingly) find Claude Code asking for clarifications when it's confused. Coding agents don't normally do that. I have shared before on the power of brainstorming with AI for longer times. Try it and you will not be disappointed. Vibe coding is fun, but pair it with intentional development cycles, and you watch how far you can take a project with coding agents today.show more

A new PR review experience is now available in... Cursor 3. Take PRs from creation to merge, all in one place. You can see comments, diffs, commits, and review status to understand what changed and next steps. Navigate larger PRs more quickly with the file tree and changes picker.show more

Agentic traces contain perfect information about an agent’s behavior... with every plan, action, and retry. But that information gets lost in a sea of JSON. So we built AgentPrism: open source React components that turn traces into visual diagrams for debugging AI agents. You can plug in your OpenTelemetry data and see your agent’s process unfold: messages, tool calls, retries. Quotient AI automatically monitors, analyzes, and improves AI agents. Being able to review traces quickly is paramount for their research, and for their customers. “Dealing with agent traces was one of the biggest frustrations for our researchers and a huge time sink. All of that has gone away since adding AgentPrism, and we’re excited to bring that functionality to our users.” — Julia Neagushow more