标签：#Product

Contacts are messier than they look. A user's real address book is spread across the people they've saved by hand, the people they've emailed often enough that the provider auto-collected them, and the colleagues in their company directory. Google exposes these through the People API; Microsoft through Graph; both model the data differently and split it across sources you have to query separately. The Nylas Contacts API unifies all of that behind one schema and one grant_id . You read saved contacts, auto-collected contacts, and directory contacts through the same endpoint, create and update entries that sync back to the provider, and organize them into groups. This post walks the contact surface from the HTTP API and the Nylas CLI , which mirrors every operation for terminal use. I work on the CLI, so the terminal commands below are the ones I run when I'm exploring an address book. The contact model and its three sources A contact in Nylas carries the fields you'd expect — given_name , surname , emails , phone_numbers , company_name , job_title , notes — plus richer ones like im_addresses , physical_addresses , and web_pages . The schema is the same across providers, so a Google contact and a Microsoft contact deserialize into one struct. The detail that trips people up is source . Every contact has one of three sources, and they mean very different things: address_book — contacts the user saved deliberately. This is the real address book. inbox — contacts the provider auto-collected because the user emailed them. These were never explicitly saved. domain — contacts from the organization's directory (coworkers). Knowing the source matters because "all contacts" usually isn't what you want. If you're building a contact picker, the inbox source can flood it with one-off recipients the user doesn't think of as contacts. Filter by source deliberately. See the Contacts API overview for the full data model. Before you begin You need a Nylas API key and a connected accou

Meeting notes are the feature everyone wants and nobody wants to build. The hard part isn't the summary — an LLM handles that. The hard part is getting into the meeting: a bot that joins Zoom, Google Meet, and Microsoft Teams, survives each platform's waiting room and admission flow, records cleanly, and produces a transcript you can feed downstream. Each provider has its own join mechanics, and none of them ships a tidy "record this meeting" API. The Nylas Notetaker API is that bot as a service. You point it at a meeting link, it joins on schedule, records, and generates a transcript, and you fetch the recording and transcript through one endpoint. This post walks the Notetaker surface from the HTTP API and the Nylas CLI , which mirrors the whole lifecycle for terminal use and quick testing. I work on the CLI, so the terminal commands below are exactly what I run when I'm testing a notetaker against a live meeting. Two ways to run a notetaker: grant-scoped or standalone Before any code, there's one architectural choice worth understanding, because it changes the endpoint you call. A grant-scoped notetaker is tied to a connected account and lives under /v3/grants/{grant_id}/notetakers . Use it when the bot acts on behalf of a specific user — it can read that user's calendar and join their meetings as them. A standalone notetaker has no grant at all and lives under /v3/notetakers . You hand it a raw meeting link and it joins, no connected account required. This is the one to reach for when you just have a URL and want a recording — a public webinar, a meeting on an account you haven't connected, or a system that deals in links rather than users. Same request body, same lifecycle, same media output; the only difference is whether there's a grant_id in the path. See the Notetaker overview for how both models fit together. Before you begin You need a Nylas API key. If you're using a grant-scoped notetaker you also need a connected account; for standalone, the API key al

Half a year ago I asked a simple question: during an online call, could a short, to-the-point hint appear on my screen in a second or two — while the other person is still talking? Not an after-the-fact transcript, but help in the moment. The result is a desktop assistant (macOS + Windows). Below is an honest breakdown of what turned out to be hard, and which solutions worked. Engineering only, no marketing. Architecture in one paragraph On the device there are only two things: audio capture and a thin UI overlay. All the "brains" (provider keys, prompts, model selection) live on the server. The client gets a short-lived per-session token and streams audio; the server returns the transcript and the generated answer. I picked this split not for "security theater" but because otherwise keys and prompts would have to be baked into the binary — and both leak instantly. Hard part #1: system audio, not the microphone The mic only captures you. You need the other party's audio — i.e. the system output. And that's where the platform pain starts: macOS. For a long time there was no native "give me system audio" API; the classic path was a virtual audio device (BlackHole/Soundflower-style) or, in recent versions, ScreenCaptureKit, which can hand you a process's audio. ScreenCaptureKit turned out to be the best option: no kernel extensions for the user to install. Windows. WASAPI loopback saves you — you can grab whatever is going to the output device, without virtual cables. Takeaway: "system audio capture" is not one feature but two different subsystems for two OSes, and most of the early bugs were about permissions and device selection, not about audio itself. Hard part #2: latency is everything A hint that arrives 6 seconds late is useless — the conversation has already moved on. The latency budget has three parts: STT (speech → text). Streaming only. Batch "recognize after the phrase ends" immediately adds 1–2 seconds. The key metrics weren't "overall accuracy on a benchm

Choosing a learning path is one of the most critical decisions you make as a beginner. When I set out to learn web development, I knew exactly what I needed: resources that were thorough, accessible 24/7, and completely free—both online and in print. Before settling on my 2026 learning path, I experimented with a few popular options. Here is a look at what I tried, why they didn’t quite stick, and where I ultimately landed. What Didn’t Work for Me Scrimba Scrimba offers highly interactive introductory courses in web development. However, I realized a bit too late that the platform isn't entirely free; a paywall kicks in shortly after you begin the core HTML and CSS sections. Because I was looking for fully open resources, I had to move on. Frontend Mentor Frontend Mentor is an excellent platform for practicing UI design, but it operates on a freemium model. While the basic learning paths are free, accessing project solutions, starter files, and advanced challenges requires a paid upgrade. 100Devs 100Devs is a free, self-paced, community-taught bootcamp led by Leon Noel. Originally broadcast live on Twitch, the full 30-week course repository is now available on YouTube and communitytaught.org. I actually joined the inaugural cohort in 2020 and attempted subsequent restarts. Leon is an engaging instructor, but the live-stream format presents some hurdles for self-paced learners. The videos are several hours long and include significant time spent interacting with the live chat, managing stream tangents, and breaking away from the core curriculum. Ultimately, the pacing made it difficult for me to stay focused and build momentum. (Note: I also found myself misaligned with some of the community’s culture and leadership choices over time, which made it easier to look for a fresh start elsewhere.) What did I choose? Ultimately, I chose The Odin Project (TOP) as my primary framework, and I couldn't be happier with the decision. The Odin Project checks every single box for

Tools Full comparisons and context in my 2026 AI tech stack post . This is just what you need installed to follow the workflow below. Claude Code If you're new, start with the cheat sheet and Anthropic best practices . Security — set this up first: Claude Code Security Hooks — 7-layer prompt injection defence, read guards, canary files Lock down your .env and any git-secret files in .claude/settings.local.json before anything else MCP: Context7 — library/API docs on demand DeepWiki — open source repo documentation Skills: Matt Pocock's skill set — /grill-me , /handoff , /improve-codebase-architecture (covered in detail below) Understand Anything — interactive code knowledge graphs Ponytail — laziest-senior-dev heuristic, pairs well with /improve-codebase-architecture Agents: DocsExplorer — handles docs lookup in a subagent without polluting main context Hooks / proxies: rtk — token reduction proxy, single Rust binary UI: Claude HUD — status bar showing model, context size, active tools and agents Other tools JetBrains — for git, debugging and reviewing Claude's changes; Claude Code plugin Warp.dev — terminal; Warp Oz for hands-off tasks, Claude Code for hands-on Process As I've mentioned in previous posts, my workflow is typically very different from what you'll see in the hype and social media posts. I don't typically work on monorepo, single stack, single language projects. My clients are typically full-on microservices with multiple languages and stacks. And beyond that, I still prefer IDEs over fancy pluggable text-editors, which often means I can't keep all the projects single scoped. What this means is that current favourites like Air , Conductor , and Antigravity don't work for me. So I've been solving my own problems, and this process I'm sharing today allows me to employ multiple agents working mostly independently on different repos towards a singular goal. I treat my agents like I would juniors or contractors; trust but verify. I give them tasks, but I ha

Wooting’s 60HE v2 isn’t just a terrific Hall Effect keyboard. It’s a fantastic keyboard period.

Network-attached storage (NAS) provides accessible shared space on your home network. After testing, these are my favorite NAS devices.

A great CLAUDE.md is not the longest one. It is the one where every line changes what Claude does. The whole skill is knowing what belongs in it — and, just as importantly, what does not. The sections that earn their place Start with a one or two line project description and your stack, with version numbers. Claude infers a lot from your code, but it will not guess that you are on Next.js 15 instead of 14, or which ORM you chose. Then a directory map — not every file, just the top-level layout with a note on what each part holds. After that: the build and test commands, the conventions a formatter does not enforce, and critically, the things not to touch. # Project: Acme Dashboard Next.js 15 (App Router), TypeScript, Drizzle ORM, Vitest. ## Structure src/app/ # routes and pages src/lib/ # shared utilities, db client db/migrations/ # generated - never hand-edit ## Commands Build: npm run build Test: npm run test ## Conventions - API routes return { data, error } - never throw to client - Server components by default ## Do not touch - db/migrations/ is generated. Never edit by hand. Every line in that file would cause a mistake if removed. That is the bar. What to leave out This is where most files go wrong. Two kinds of content waste your budget: Personality instructions. "Act as a senior engineer," "think step by step," "be thorough." These feel productive but change nothing — Claude already does them. General advice that does not prevent a specific mistake is pure noise. Rules a tool already enforces. If you have a formatter or linter, do not restate what it enforces. Wire it into a hook instead, and keep CLAUDE.md for what tools cannot enforce. The one-line test For every line, ask: "If I remove this, will Claude make a mistake?" If yes, keep it. If no, delete it. This single question, applied ruthlessly, is the difference between a file Claude follows and one it ignores. A bloated file buries the rules that matter in noise, so Claude cannot tell which line is the

If you use Claude Code, there is one file that quietly shapes every session: CLAUDE.md. Most developers either do not have one or have one that works against them. Here is what it actually is, in plain terms. The file Claude reads every session CLAUDE.md is a markdown file that Claude Code reads at the start of every conversation. Think of it as your project's constitution — the source of truth for how your specific repository works. Because Claude reads it every time, you stop re-explaining your stack, your conventions, and your commands on every task. Why it exists Without a CLAUDE.md, every session starts cold. Claude can read your code, but it cannot infer the things that live outside the code: that you are on Next.js 15 and not 14, that a directory is generated and must never be edited, that your team has a particular commit style. You end up explaining these again and again, slightly differently each time, so the output drifts. CLAUDE.md captures that knowledge once, somewhere Claude always sees it. Where it lives, and how to start Put CLAUDE.md in the root of your project. You do not have to write it from a blank page — the /init command analyses your codebase and generates a starter, detecting your build tools, test framework, and existing patterns: $ claude > /init Treat the result as a foundation, not a finished product. The real value comes from refining it as you learn what Claude gets wrong without guidance. What belongs in it A good CLAUDE.md is short and specific: A one-line stack description, with versions — Claude will not guess Next.js 15 over 14 A directory map — the top-level layout and what each part holds The build and test commands The conventions a newcomer could not infer from the code A "do not touch" section — generated files, migrations, protected paths Here is a compact example: # Project: Acme Dashboard Next.js 15 (App Router), TypeScript, Drizzle ORM, Vitest. ## Structure src/app/ # routes and pages db/migrations/ # generated - never h

You wrote a detailed CLAUDE.md, and Claude Code still gets things wrong — wrong convention, touches files it should not, ignores rules you clearly wrote down. The cause is almost never that the rules are missing. It is that they are buried. The over-specified file problem CLAUDE.md loads into Claude's context every single session, and performance degrades as that context fills. When the file grows too long, something counterintuitive happens: Claude starts ignoring parts of it. The important rules get lost in the noise, and the genuinely critical instructions sit too deep to reliably influence output. A bloated file does not just waste tokens. It actively makes Claude less reliable, because it cannot tell which of your hundred lines is the one that matters. The trap of good intentions It always starts reasonably: "let me put everything relevant in here." But relevant is a low bar. The file grows until it is impossible to scan, full of duplication, and so noisy that the truly important rules carry no weight. More content felt like more control. It was the opposite. The fix: prune ruthlessly Run every line through one question: "If I remove this, will Claude make a mistake?" If the answer is no, the line is noise — delete it. And if something only matters in a specific situation rather than always, it does not belong in the always-loaded file at all. That is what skills and subdirectory CLAUDE.md files are for — they load on demand, only when relevant. Let Claude fetch what it needs Instead of embedding everything, tell Claude how to pull context when it needs it. Rather than pasting an entire API guide into the file: # Wasteful - embeds the whole file every session: @docs/api-guide.md # Better - Claude reads it only when relevant: For Stripe integration work, read docs/stripe-guide.md The second form costs almost nothing until the moment it is needed. The result A pruned CLAUDE.md is often a third of the length and many times more effective. The rules that matter are

Create trend motions in your browser! Discussion | Link

I bombed a system design interview last year — not because I didn't know the architecture, but because I spent the first 5 minutes fighting Excalidraw. So I built SystemDesignBoard — a free, keyboard-first whiteboard specifically for system design interviews. What it does You open it, press a key, and start drawing. No account, no onboarding, no drag-from-a-sidebar friction. R → place a Service node C → place a Database/Cache/Queue A → connect two nodes N → open the scratchpad for scale math The features I'm most proud of Animated connectors that show communication type Instead of just drawing arrows, connectors visually encode how services talk: ⇄ sync — paired dashes (request + ACK) ≋ stream — near-solid fast line with glow (continuous pipeline) This matters in interviews — your interviewer can glance at your diagram and immediately understand the communication pattern. Cloud provider badges Tag any node as AWS (EC2, Lambda, RDS, S3), GCP (GKE, Cloud Run, Firestore), or Azure. Each subtype has its own icon. Trade-off logging Right-click any node → Log Trade-offs → attach your CAP theorem stance, consistency level, and scaling strategy directly to the component. Diagram-as-Code Type: [Mobile App] -> [API Gateway] [API Gateway] -> [Auth Service] [Auth Service] -> [Users DB] [Feed Service] -> [Posts DB x3] [Feed Service] -> [Redis Cache] Hit Apply — it auto-lays out the whole architecture in seconds. Export to animated GIF Export your diagram as a GIF that shows live traffic flow animations. Great for sharing after an interview or in a design doc. Tech stack React + TypeScript + Vite @xyflow/react (ReactFlow v12) for the canvas Zustand + Immer for state with full undo/redo html-to-image + gifshot for PNG/GIF export It's free and open No signup required. Works entirely in the browser. Free during beta. 👉 systemdesignboard.com Would love feedback — especially from anyone who's done system design interviews recently. What's missing? What's annoying? Drop a comment below

📖 Originally published on my blog . Part of a series on building with Claude Code. For a while I'd watch the AI work and quietly grumble: a fairly big task, and it would finish one module before starting the next, while I just sat there waiting for it to clear one before the other's turn came up. The work itself was fine—it was just slow. Slow because it was stuck in a queue. Then it clicked: a lot of these modules have nothing to do with each other, so why make them go one after another? Split them up, let several agents work at the same time, done. What I want, and where it stops What I want is simple: the same work, for roughly the same tokens, with the wall-clock time cut way down. But let me put the boundary up front— not every task can be split this way . This is just an approach I've worked out for myself; take what's useful. The prerequisite: a clean architecture For several agents to work at once without stepping on each other, the prerequisite isn't the AI—it's your architecture . That task of mine could be split because it was already several modules, talking to each other through interfaces, with internal implementations that don't affect one another—as long as each one honors the interface contract, it can be built independently. Loosely coupled, highly cohesive, in other words. And I'd nailed that design down together with opus before writing a line: opus helps me think it through and lays out options, but I'm the one who decides . You can't cut corners here. Forcing parallelism onto an architecture you haven't cleanly split is like cutting a tangle of yarn into a few pieces that are all still knotted together—it only gets messier. Who runs the show, who plans, who does the work With the design settled, it's time to assign roles. The split I tend to use: opus runs the show —holds the big picture, hands out work, does the final check; sonnet does the TDD planning —per the design, it lays out how each module gets tested and implemented; haiku writes the

AI Coding Agents Need a Control Layer AI coding agents are getting good enough that the problem is changing. A year ago, the question was mostly: Can this thing write useful code? Now, for a lot of builders, the better question is: How do I supervise this thing once it is actually doing work? That shift feels important. Claude Code, Cursor, Codex, and similar tools are not just autocomplete anymore. They can plan, edit files, run commands, review code, and work across larger chunks of a project. That is powerful. It also gets messy fast. The bottleneck is moving The hard part is no longer just picking the best coding agent. It is figuring out how to manage agent work once multiple tools or sessions are active. Questions start showing up: What is each agent doing right now? What changed? What still needs human review? Where did approval happen? Which agent owns which task? Did two agents touch the same part of the codebase? What should be paused, redirected, or stopped? What happened while I was focused somewhere else? That is not really a prompting problem. It is a control problem. The current workflow is mostly duct tape A lot of agent workflows seem to rely on some combination of: terminal tabs tmux sessions git branches git worktrees editor diffs notes issue trackers rules files memory vibes That works for a while. But once agents become more autonomous, or once a builder runs more than one agent at a time, the workflow starts to need a real operating layer around it. Not because the agents are bad. Because the agents are getting useful enough to need supervision. The missing layer The layer I keep thinking about has a few jobs. State What is running? What is paused? What needs attention? Ownership Which agent owns which task, branch, file, or objective? Review What changed, and what still needs a human to look at it? Approval Where should the human say yes before work continues? Intervention When should a builder pause, redirect, compare, or stop an agent? Memor

I’m building ScriptTap, a no-root Android automation app for user-controlled phone workflows. The app lets people create scripts with taps, swipes, routines, screen-aware checks, OCR/text detection, image/pixel checks, variables, logic, and AI-assisted script creation. The technical side is hard, but the trust side may be harder. ScriptTap needs Android Accessibility permission because user-authored input automation requires it. That is a powerful permission. I do not want to minimize it, hide it behind vague onboarding copy, or expect people to click through without understanding what they are enabling. That creates a product-design problem. If the copy is too soft, it feels dishonest. If the copy is too warning-heavy, a legitimate automation tool can feel suspicious before the user even understands what it does. The explanation I am trying to make clear is: ScriptTap is no-root. Scripts are created and controlled by the user. Screen capture is user-controlled. It does not bypass Android permissions, lock screens, app security, or consent flows. Accessibility is required for overlay/input automation, so users should understand why it is being requested. The short version I keep coming back to is: ScriptTap uses Accessibility so your scripts can interact with the screen the way you tell them to. This is a powerful permission. You should only enable it if you understand and trust what the app is doing. For developers who have built apps with sensitive permissions: How did you explain the permission without either hiding the risk or scaring users away from a legitimate feature?

I know it sounds strange, but I am in my first year in CS Major, and I don't like posting things on social media, but I found lately that companies are more likely to hire people who are active on social media like X (Twitter). For me, I genuinely post my projects on LinkedIn, but not sharing things like today I learned something new etc... What's your opinion about that? Or How can I manage that?

A notes app that lives in your MacBook's notch. Discussion | Link

Every time you open a new session with an AI coding tool, it starts from zero. It does not know what you decided yesterday, what failed last week, or what comes next. You have to explain the project again. And again. EGC (Extended Global Context) fixes this. EGC is a local runtime that gives every AI coding tool you use a persistent memory. At the end of each session, the AI saves what it learned: decisions made, what failed, your preferences, what comes next. At the start of the next session, it loads that state back automatically. One install. Every tool. Every session. Website: https://fmarzochi.github.io/EGCSite What it looks like in practice You open Claude Code on a project you have not touched in two weeks. Without typing anything: State loaded from egc-memory via ~/.egc/state/Projects--MyApp.md Context and preferences acknowledged. Ready to pick up: - Test full install on a clean machine - Add GEMINI.md with session memory protocol - Publish v1.0.1 fix after clean install test passes The AI already knows what you were building, what decisions you made, what failed, and exactly where you stopped. You did not type anything. You just started working. How it works EGC ships two MCP servers that run locally during every session. egc-memory: 14 tools for persistent memory Tool What it does get_state Loads project memory at session start update_state Saves decisions, preferences, and next steps store_decision Persists a single decision to SQLite query_history Returns past decisions by timestamp search_history Full-text search with BM25 ranking working_memory_set Stores transient context with a TTL lesson_save Records cross-session knowledge with confidence decay lesson_recall Retrieves active lessons above a threshold detect_patterns Surfaces repeated commands and recurring errors compress_observations Compresses hook events to save token budget State files live at ~/.egc/state/<project-slug>.md . One file per project. Plain Markdown. Human-readable. egc-guardian:

Day 9. Template matching works. But screen sizes, resolutions, and Android versions might break everything. Eight days ago, the agent was an idea. Now it can read text, handle interruptions, and find icons on a screen. But there's a question I've been avoiding: does it work on any phone other than mine? The Cross-Device Problem Every screenshot I've taken, every icon I've cropped, every coordinate I've mapped—it's all on one device. My phone. Same screen size. Same resolution. Same Android version. Same DPI. Template matching relies on reference images that look exactly like the target on screen. Change the screen density, change the icon size, change the font scaling, and the match confidence drops. Suddenly "send_button.png" doesn't match anymore, and the agent can't press send. This isn't a bug in my code. It's a fundamental challenge in computer vision: reference-based matching breaks when the visual context changes. Today's Experiment I tested the same agent on a friend's phone—different manufacturer, different Android version, slightly larger screen. The results were humbling. Task My Phone Friend's Phone OCR (text recognition) ✅ 95% accuracy ✅ ~90% accuracy Find "Mom" in contacts ✅ Found ✅ Found Template match: send button ✅ 94% confidence ❌ 62% confidence Template match: back button ✅ 91% confidence ❌ 58% confidence OCR held up reasonably well because text is text. Fonts might change slightly, but the characters are the same. But the icons—the send button, the back arrow—were rendered at a different size and slightly different pixel arrangement on my friend's device. The agent failed to send the message. Why This Matters An AI agent that only works on one phone isn't an agent. It's a script. If I want this to be useful to anyone else—or even to myself if I change phones—it needs to be device-agnostic. Possible Solutions I'm Exploring Solution Pros Cons Multi-resolution icon library Simple. Just crop icons at different DPIs. Tedious. How many variants are eno

Give every customer their own Hermes or OpenClaw agent Discussion | Link