标签：#t

I spent a week building a counter program in Anchor — the Rust framework for writing Solana programs. By the end I had two instructions, one authorization constraint, and a test suite I could actually trust. Here is what I built, how I tested it, and the moment I proved the tests were real. Start Here: The Accounts Struct If you come from Web2, this is the part that looks the strangest: #[derive(Accounts)] pub struct Initialize { #[account( init, payer = authority, space = 8 + Counter::INIT_SPACE, )] pub counter : Account , #[account(mut)] pub authority : Signer , pub system_program : Program , } In a Web2 backend, your handler receives a request object and talks to a database. On Solana, there is no database; there are accounts. Every account your instruction needs to read or write must be declared upfront, before the handler runs. Anchor validates them before your code ever executes. Here is what each field does: counter — the account being created. The init constraint tells Anchor to make a CPI to the System Program, allocate 8 + Counter::INIT_SPACE bytes, and fund it from authority . The 8 is for the discriminator Anchor stamps on every account so the program can later verify "this is mine." authority — the wallet signing and paying for the transaction. mut because its SOL balance is decreasing to fund the new account. system_program — required any time you create accounts. Anchor checks that the address matches the real System Program. The accounts struct is the schema. The handler is the logic. The Handlers pub fn initialize ( ctx : Context ) -> Result { let counter = & mut ctx .accounts.counter ; counter .authority = ctx .accounts.authority .key (); counter .count = 0 ; Ok (()) } ctx.accounts gives you typed access to every account declared in the struct. The handler is short because Anchor already did the hard work: allocating the account, checking the signer, paying the rent. Your code just sets the initial values. pub fn increment ( ctx : Context ) -> Resu

Atlantic reporter Alex Reisner recently uncovered four datasets of music being used to train AI models and made them fully searchable for the public. Two of the sets are absolutely enormous at 12 million and 9 million tracks. The other two are much smaller, but still represent a significant amount of training data at over […]

If you’ve spent any time working with autonomous AI coding agents recently, you know the drill. You give the agent a straightforward task: "Add a user profile page and link it to the navbar." The agent says, "I've got this." It writes some code. You run it, and it throws an import error. You paste the error back. The agent apologizes, rewrites the file, and now your routing is broken. You paste that error back. Ten iterations later, your config is mysteriously deleted, the navbar is entirely missing, and the agent is trying to install a deprecated version of React. This is the AI Agent Doom Loop. It happens because current agent frameworks mistake intelligence for discipline. We dump a 10,000-token SYSTEM_PROMPT.txt telling the agent everything about our project, hoping it remembers the architecture constraints on step 45 of its execution loop. It rarely does. I built Agent Rigor because I got tired of babysitting agents that code themselves into corners. The Root Cause: Context Rot When an agent starts a task, its context is pristine. But as it reads files, executes commands, and hits errors, its context window fills up with junk stack traces and previous failed attempts. By the time it's 20 steps deep, the original system prompt you carefully crafted is buried. The agent forgets the architecture guidelines. It starts prioritizing the immediate error in front of it over the overall goal. This is when it starts guessing, hallucinating, and making things worse. The Solution: Progressive Disclosure and Empirical Discipline Agent Rigor isn't a new LLM or a magic prompt wrapper. It's an operating system for agents that enforces strict empirical discipline . Instead of one massive prompt, Agent Rigor uses a 3-tier hierarchy: L1 (Apex Kernel): The absolute, non-negotiable laws. (e.g., "Never guess an API signature. Always grep or read the file first.") L2 (Phase Directors): Orchestration that only loads when the agent enters a specific phase (Planning, Execution, Verifica

Most carbon footprint apps do the same thing: Quiz → "Your footprint is 120 kg CO₂/week" → Generic tips → User never returns. That's not a coaching experience. That's a guilt trip with no follow-through. For PromptWars Virtual — Challenge 3 (Carbon Footprint Awareness & Reduction), I built CarbonCompass with a different premise: Not just measure. Guide. Live demo: https://prompt-wars-virtual-hackathon-8u1kxxwh1-mithunvisveshs-projects.vercel.app/ The Problem with Existing Carbon Tools I started by looking at what already exists — Capture, Klima, JouleBug. Each of them calculates a footprint accurately. But they all fail at the same step: the recommendation layer. "Install solar panels." "Buy an EV." "Go vegan." These are structurally correct but useless for a hostel student in Chennai who travels by bus and eats at the mess. They're recommendations designed for a demographic that already has money and flexibility. CarbonCompass is built around two real Indian users: Aditi — a college student in Chennai. Bus commute, hostel mess food, shared room electricity. Her biggest carbon lever is food waste, not transport. Rohan — a tech professional in Bengaluru. Petrol car + scooter commute, air-conditioned 2BHK, frequent food delivery. His biggest lever is home energy, not diet. The same app, two users with different lifestyles receive coaching tailored to their highest-impact opportunities. That's the core product promise. The Architectural Decision That Made Everything Work Before writing a single line of code, I ran this prompt in Google Antigravity's Plan Mode: You are a senior product architect. Before coding: Generate user personas Design a SINGLE shared calculation module that the Dashboard, Impact Simulator, and AI Coach all call with the same inputs Create the data schema Propose page architecture Flag risks for a one-week build Do not write code yet. Create an Implementation Plan. The agent produced a full Implementation Plan artifact — a structured document I cou

Shinkei makes a refrigerator-sized robot called Poseidon to kill fish quickly and humanely.

This is a submission for the June Solstice Game Jam TypeForge: Turing-Inspired Intelligent Typing Coach What I Built TypeForge is a premium typing coach aligned with Apple's Human Interface Guidelines, built to help typists build speed and accuracy through automated, localized error diagnostics. TypeForge analyzes keystroke performance to isolate specific character transitions that cause delay or accuracy drops, then generates custom, adaptive exercises targeting those weaknesses. Developed for the June Solstice Game Jam, the project celebrates the power of computing and accessibility by turning raw diagnostics into a personalized educational experience. The solstice theme represents the journey of transition: taking a typist from darkness, meaning slow, error-prone typing, into light, meaning fluid, expert flow. Video Demo Live Application https://typing-forge-six.vercel.app/ Code https://github.com/shogun444/typingforge Flowchart Architecture graph TD User([User Typer]) -->|Keystrokes| Trainer[Typing Trainer Core] Trainer -->|Log Errors| Zustand[Zustand Stores] Zustand -->|Query Key Stats| Heatmap[Mistake Heatmap] Zustand -->|Identify Weaknesses| Generator[Drill Generator] Generator -->|Focus Word Pools| Trainer Zustand -->|Calculate Performance| Drawer[Analysis Drawer] How I Built It The application was built using Next.js for structure and routing, Tailwind CSS for premium glassmorphism styling, and Zustand for highly responsive state management. Development was accelerated throughout using Google's agentic AI coding assistant, Antigravity. I focused on clean Apple HIG spacing, micro-interactions, responsive scaling, and high-fidelity audio feedback to create a tactile, premium user experience. I also engineered custom canvas-based timeline sparklines to avoid heavy graphing packages and preserve maximum load performance. # === SYSTEM ARCHITECTURE === # app/ # Next.js pages including Settings and Profile views # stores/ # Zustand stores (typing-store, stats-stor

How I Built a Real-Time Bounty Marketplace with Supabase and 14-Layer Edge Security I wanted to build a platform where anyone can post a task (a "bounty"), set a reward, and have people complete it with verifiable proof. Think freelance work, but optimized for quick, composable task completion — with proof submission as the core trust mechanism. The result is BountyClaimer — a real-time marketplace running on Supabase + Vercel with a security system baked into Edge middleware and scattered across every layer of the stack. 🛠️ The Tech Stack Frontend: React + Vite + TypeScript Backend: Supabase (PostgreSQL, Realtime, Storage, Auth) Payments: Stripe Hosting: Vercel (Edge Middleware) Security: Custom "Armadillo" system (14 layers) Architecture Pattern: Phoenix Architecture for real-time state consistency 🔄 The Core Workflow Post — A user posts a bounty with a reward and description Claim — Others browse and claim available bounties Submit — The claimer completes the work and submits proof (images, video, audio, text, files) Settle — The bounty owner reviews and approves — funds are released Sync — Real-time updates keep both sides in sync instantly The hardest parts were real-time state sync across multiple users , anti-abuse without hurting legitimate users , and security at the edge . 🏛️ The Phoenix Architecture One pattern I'm particularly proud of is what I call the Phoenix Architecture — a real-time state management approach that ensures every client sees the same truth without polling. The core idea: instead of each client fetching data and hoping it's current, database changes (bounty status updates, proof submissions, claim state transitions) are broadcast out via Supabase Realtime. Every connected client receives the same event stream and updates locally. // The Phoenix pattern — subscribe to changes once, // update locally from the event stream const channel = supabase . channel ( `entity- ${ id } ` ) . on ( ' postgres_changes ' , { event : ' * ' , schema : '

You add a sixth Lambda trigger to your OrderEvents table, deploy it, and within 20 minutes your SLA dashboard goes red. Latency on order writes jumps from 4ms to 40ms. The function itself is fine. The table is fine. The problem is that five other Lambdas are already hitting the same partition key on every write, and you just made it six. DynamoDB's internal partition throttling doesn't care that each function looks clean in isolation. This is an N+1 trigger problem, and your AI coding assistant cannot catch it. Not because it lacks intelligence, but because the fact that five Lambdas already target that table lives in your AWS account and your full codebase — not in the file your assistant has open. Infrawise · npm Why the LLM Can't See the Pattern When you ask Claude to write a new order processing Lambda, it reads the file you have open and generates code that looks correct — because in the context of that one file, it is correct. It doesn't know about ProcessRefundsLambda , NotifyFulfillmentLambda , SyncInventoryLambda , UpdateAnalyticsLambda , and AuditTrailLambda , all of which you wrote in previous sprints and which all write to the Orders table. This is a category of failure that model quality doesn't fix. A better model produces a more fluent explanation for why your latency spiked. The fact that five functions converge on the same table is a lookup, not a prediction. The source of truth is a combination of your code (which functions exist) and your infrastructure (what they access). Infrawise draws that boundary explicitly. It extracts the answer from your code using AST parsing and from your infrastructure using API calls, then hands that graph to the model as structured context — it never generates the answer. How Infrawise Traces Trigger Chains to the Same Table When Infrawise scans your repository, it uses ts-morph to walk every CallExpression in every source file. It's not searching for the string "DynamoDB" — it matches call structure against a known

Webhooks are one of the most common ways SaaS platforms communicate with external services. They deliver real‑time updates about bookings, payments, messages, or status changes. But webhooks are also one of the most fragile integration points — and if they are not handled correctly, the entire system becomes unreliable. Why webhook handling is tricky Webhooks are inherently unpredictable because they depend on external systems. Common issues include: duplicate deliveries, missing events, delayed notifications, invalid payloads, unexpected retries, out‑of‑order events. A robust webhook handler must be prepared for all of these scenarios. Core principles of safe webhook processing A reliable webhook system follows several essential rules: Idempotency: every event must be safe to process multiple times. Signature validation: verify that the request is authentic. Payload schema validation: reject malformed data early. Queue‑based processing: never process webhooks synchronously. Retry logic: handle temporary failures gracefully. Audit logging: store every event for debugging and recovery. These principles ensure that even if the external service misbehaves, your platform remains stable. Real‑world example Modern property management systems depend heavily on webhooks for booking updates, cancellations, pricing changes, and guest messages. An example of a resilient webhook workflow can be seen in an event‑driven short‑term rental automation platform , where each webhook is validated, queued, processed idempotently, and logged for traceability. If you want to explore how a real SaaS platform structures webhook handling, you can check PMS.Rent . Conclusion Webhooks are powerful but unreliable by nature. A safe webhook handler must assume that events will arrive late, arrive twice, or arrive broken. When the system is designed with idempotency, validation, queues, and retries, webhooks become a reliable foundation for real‑time automation.

I've been working on ctrodb — a client-side database for TypeScript that runs in the browser (IndexedDB) and Node.js (in-memory). Zero runtime dependencies. It started as a personal project to stop rewriting IndexedDB wrappers. Every new client-side app needed the same boilerplate: open a connection, create object stores, handle version upgrades, write CRUD helpers. After the sixth time, I wrote it once and got it right. What it does ctrodb gives you MongoDB-like CRUD with schema validation at write time: import { Database } from " ctrodb " const db = new Database ({ name : " my-app " , schema : { version : 1 , collections : { notes : { fields : { title : { type : " string " , required : true }, body : { type : " string " }, pinned : { type : " boolean " , default : false }, tags : { type : " array " , items : { type : " string " } }, createdAt : { type : " string " , default : () => new Date (). toISOString () }, }, indexes : [{ field : " createdAt " }], }, }, }, }) await db . connect () const notes = db . collection ( " notes " ) const note = await notes . create ({ title : " Hello " , body : " World " }) const results = await notes . query () . where ( " pinned " , true ) . sort ({ createdAt : " desc " }) . limit ( 10 ) . fetch () Every record is a Model — a Proxy wrapper with typed field access. note.title works. note.update() handles writes. Direct property assignment logs a warning telling you to use .update() instead. What's included The core package ships with three plugins: Full-text search — inverted index, stop word removal, auto-indexed on create/update/delete Relations — has_many, belongs_to, has_one with lazy accessors built into every Model and eager loading via .with() Custom validation — extendable rules beyond the built-in validators (email, URL, regex) Plus React hooks (separate import, same package): import { DatabaseProvider , useQuery , useMutation } from " ctrodb/react " Signal-based reactivity. When data changes, useQuery re-fetches and your

In a world completely powered by technology, have you ever wondered what actually keeps our digital lives from crashing down? Enter the unsung heroes: system and network administration . Think of an operating system like Windows or Linux as a computer's command center, orchestrating everything from the heavy-lifting CPU to the smallest plugged-in device. To keep your data safe and your machine stable, it cleverly splits its brain into two zones: a restricted "user mode" where your everyday apps play, and a highly secure, privileged "kernel mode" reserved strictly for critical system operations. When individual computers connect to form massive global networks, the complexity skyrockets. This comprehensive guide breaks down those complex environments into simple, bite-sized concepts. Here is a quick snapshot of what we will cover: Host & OS Administration : This module covers how an operating system functions as the primary intermediary between a user and a computer's raw physical hardware. It explains how the system kernel manages critical computing processes, memory allocation, local storage file systems, and administrative tasks like security patching and automated scripting. Networking Concepts, Topologies, and Protocols : This module explores how individual computer systems connect and communicate across localized or global distances. It details the structural design of network topologies, addressing rules like IPv4 and IPv6, and the standardized layer frameworks that ensure safe and efficient data transmission. 🏛️ Part 1: Operating Systems & Host Administration 🖥️ Computer Resources and Functions At its core, every computer system is a collection of physical machinery and digital structures working together to solve problems. To understand how an operating system manages these pieces, it helps to look at the foundational puzzle blocks of a computer. This section maps out the primary hardware and data elements the system has to control, alongside a simple breakd

The Counterintuitive Truth: Feature Flags Are Not Config Files Most engineers first encounter feature flags as a simple abstraction: a key-value lookup that returns true or false. That mental model works fine for a single service handling a few hundred requests per minute. It becomes actively dangerous at scale. A mature feature flag system isn't a config file with an API wrapper — it's a distributed control plane . The distinction matters architecturally. A control plane manages the real-time behavior of a running system across many nodes simultaneously, with its own consistency guarantees, failure semantics, and propagation latency. That's a fundamentally different design problem than reading a YAML file on startup. One constraint drives every downstream decision: user traffic must never block on a remote flag service call. If evaluation requires a synchronous RPC, you've coupled your request path to the availability and latency of an external system. Netflix's Archaius library enforces this by evaluating flags entirely in-process against a locally-cached configuration snapshot. A network round-trip per evaluation injects 10–50ms of tail latency at p99 — catastrophic when you're competing on streaming start times measured in hundreds of milliseconds. Google, Meta, and Netflix collectively evaluate flags against millions of requests per second with sub-millisecond overhead. That figure is only achievable through local evaluation backed by an async synchronization layer, not RPC. The other failure mode engineers underestimate is flag sprawl . Systems accumulate flags the way codebases accumulate dead functions — gradually, then all at once. I've seen services carrying thousands of flags where fewer than 10% were actively managed. The operational weight alone becomes a liability: which flags are safe to remove? Which ones are kill switches for production behavior that no one documented? Knight Capital's $440M loss in 45 minutes in 2012 remains the canonical cautionar

🌍🚀 Project Showcase: Carbon Footprint Tracker I'm excited to share one of my recent projects — a Carbon Footprint Tracker designed to help users better understand their environmental impact and encourage more sustainable lifestyle choices. As developers, we have the opportunity to build technology that not only solves problems but also creates awareness about important global challenges. This project was a great experience in combining technology, user experience, and sustainability into a single application. ✨ Key Features: • Carbon footprint calculation system • Clean and intuitive user interface • Responsive design for all devices • Real-time user interaction • Environmental awareness focused experience • Modern frontend architecture 🛠️ Technologies Used: • React • JavaScript • HTML5 • CSS3 • Git & GitHub 💡 What I Learned: • Building interactive user interfaces • State management and user input handling • Creating responsive layouts • Writing cleaner and more maintainable code • Designing applications around real-world problems 🔗 GitHub Repository: https://github.com/Prem759-0/Challenge-3-Carbon-Footprint 🔗 Live Demo: https://challenge-3-carbon-footprint.vercel.app/ I am continuously improving my skills through hands-on projects and exploring how technology can create meaningful impact. Every project teaches me something new and pushes me one step closer toward becoming a professional Full-Stack Developer. Feedback and suggestions are always welcome! 🙌

The local MCP gateway that cuts tokens ~90% Discussion | Link

Jumper isn't the only big name leaving Google DeepMind.

A sync engine is one of the most critical components in any SaaS platform that integrates with external services. Whether you manage bookings, payments, messages, or inventory, the system must stay consistent across multiple channels without losing data or creating conflicts. Why sync engines fail Most sync issues come from predictable technical problems: API rate limits. Slow or unstable external endpoints. Conflicting updates from different sources. Missing retry logic. Lack of idempotency. When these issues accumulate, the platform becomes unreliable and difficult to scale. Key principles of a reliable sync engine A well‑designed sync engine follows several core principles: Event sourcing to track every change. Message queues to handle spikes in traffic. Idempotent operations to avoid duplicates. Timestamp‑based conflict resolution. Retry and backoff strategies for unstable APIs. These patterns ensure that the system remains consistent even when external services behave unpredictably. Real‑world example Platforms that manage short‑term rental operations rely heavily on sync engines. Calendar updates, pricing changes, and new bookings must be processed in real time. A good example of an event‑driven sync model can be seen in modern PMS systems. For instance, the approach used in event‑driven property management architecture is similar to the one implemented in PMS.Rent Conclusion A sync engine is not just a background process — it is the backbone of any API‑driven SaaS platform. When designed correctly, it ensures reliability, scalability, and predictable behavior across all integrated channels.

Whitespace problems are the ones you can't see until they bite. A pull request where half the "changes" are trailing-space diffs. A shell script that breaks in CI because someone's editor saved it CRLF. A .env with a UTF-8 BOM that makes the first variable name mysteriously not match. A file with no final newline that turns one-line changes into two-line diffs forever. None of it shows up on screen. All of it shows up in git blame . Today, catching this takes three or four tools stitched together — and I got tired of that, so I built wssweep : one zero-config command that finds all the common whitespace smells and, with --fix , cleans them in place. $ npx wssweep src/app.js (2) 14: trailing-whitespace trailing whitespace - missing-final-newline no newline at end of file config.yml (1) - mixed-eol mixed line endings (CRLF×3, LF×1) ✖ 3 whitespace issues in 2 files (mixed-eol=1, missing-final-newline=1, trailing-whitespace=1) $ npx wssweep --fix # clean them It checks seven things: trailing whitespace, mixed CRLF/LF line endings, lone CRs, a missing final newline, extra trailing blank lines, a UTF-8 BOM, and tabs mixed with spaces in one indent. Non-zero exit on findings, so it's a CI gate. pip install wssweep gets the same tool in Python — byte-for-byte identical output and fixes. Why not editorconfig-checker / pre-commit / prettier? Because each does part of it: editorconfig-checker reports — but you have to author an .editorconfig first, and it can't fix anything. pre-commit 's trailing-whitespace / end-of-file-fixer / mixed-line-ending hooks do fix, but only inside the pre-commit framework, and they're three separate hooks. Nobody runs them ad-hoc on a fresh checkout. prettier fixes whitespace only as a side effect of reformatting all your code, and won't touch files it can't parse. dos2unix does line endings and nothing else. wssweep is the one npx / pip command, no config and no framework, that does the whole set at once and drops into any CI regardless of toolch

Debugging authentication in web apps is painful. You need to test the same flow as five different user types — new visitor, returning user, admin, expired session, logged-out — and the easiest way is to constantly create new accounts or clear all your cookies and start over. There's a faster way. These five techniques use direct cookie manipulation to simulate any auth state without touching your database or creating dummy accounts. I use CookieJar for most of this — a free Chrome extension built natively on MV3 that gives you a proper UI for cookie editing. But I'll show you the underlying Chrome DevTools method too, so you understand what's actually happening. 1. Simulate a Logged-Out State Without Clearing Everything The naive approach: clear all cookies and reload. The problem: you just nuked your dev server session token, your local storage flags, your Stripe test mode cookie, and everything else you carefully set up. The targeted approach : identify and delete only the session/auth cookie. Most session cookies are named session , sid , auth_token , _session_id , or something close. In DevTools: Application → Cookies → [your domain] → find the session cookie → right-click → Delete With CookieJar: open the extension, search session , click the trash icon next to just that cookie. Your dev environment stays intact. The user state resets to logged-out. 2. Test the "Returning User" vs "New User" Path Without a Second Account Session cookies tell the server you're authenticated. But many apps use separate cookies to track whether a user has seen the onboarding flow, completed setup, or visited before. Look for cookies like onboarding_complete , setup_done , first_visit , or custom flags in your app code. To test the new user experience: Export your current cookies (CookieJar → Export → JSON format, or copy from DevTools) Delete the specific onboarding/first-visit flag cookie Reload and test the new user path Re-import or re-set the cookie to restore your state This

Il venture capital con progetti a 4-5 anni incarna perfettamente la tensione tra la teoria di Manso e la filosofia di Taleb. È un orizzonte temporale che suona contro-intuitivo: troppo lungo per la logica del "fail fast" da incubatore, troppo corto per la pazienza della ricerca fondamentale. Eppure è proprio qui che si gioca la partita dell'innovazione dirompente. Il problema strutturale I fondi VC operano tipicamente su cicli di 10 anni. Un progetto a 4-5 anni occupa il cuore del fondo: non è un esperimento rapido da liquidare, ma nemmeno un investimento da tenere per un'intera generazione. Manso ci dice che il contratto ottimale per l'innovazione richiede tolleranza nel breve termine e ricompensa nel lungo. Ma cosa significa "breve" e "lungo" quando il progetto stesso dura 4-5 anni? Qui emerge un paradosso. Il VC tollerante — quello che Manso celebrerebbe — potrebbe essere tentato di mantenere vivo un progetto che sta fallendo, perché il fallimento prematurato distruggerebbe il valore dell'opzione. Ma Taleb ci avverte: l'antifragilità non è la persistenza a oltranza, è la capacità di trarre beneficio dallo stress. Un progetto che assorbe risorse per 5 anni senza generare informazioni utili non è antifragile: è semplicemente costoso. La soluzione di Manso: il contratto come orologio Per Manso, la risposta sta nella struttura contrattuale. Il contratto ottimale per un progetto a 4-5 anni non è lineare: non è un flusso costante di finanziamento legato a milestone arbitrarie. È qualcosa di più sofisticato. Il principale (il VC) deve commettere a un livello di finanziamento iniziale che copra la fase esplorativa — i primi 12-18 mesi — senza richiedere risultati misurabili. Questa è la fase di "tolleranza eccezionale per il fallimento" di cui parlava Holmström. Poi, a intervalli predeterminati, il VC ha l'opzione — non l'obbligo — di continuare. Ma la soglia di abbandono deve essere più bassa del livello ottimale ex-post. In altre parole: il VC deve essere disposto a co

The problem GitHub shows your pull requests in whatever order they happened to be opened — not in the order they actually need your attention. A one-line typo fix and a PR touching authentication code get exactly the same visual weight in your inbox. Multiply that across a dozen open PRs and you spend more time deciding what to look at than actually reviewing. What I built PR Focus is a Chrome extension (Manifest V3) that sits on top of GitHub's PR pages. It combines three signals into a single priority queue: CI status — failing checks bubble up PR age — stale PRs don't get forgotten AI risk score (0–100) — weighted toward changes touching auth, database, or infra code Each PR also gets a plain-English summary generated from the actual diff (not the title someone wrote at 11pm), and you can generate an approve / request-changes draft review in one click, edit it, and send — without leaving the extension. Why BYOK instead of my own AI backend This was the decision I spent the most time on. Running my own AI backend would have meant: A server in the data path of every PR diff users review — a much bigger trust ask, especially for private repos. Either eating the AI cost myself (unsustainable as a solo dev) or marking it up into a subscription. Going BYOK (bring your own key — OpenAI, Groq, Mistral, or a local Ollama instance) flips both of those: Your GitHub token and AI key live in chrome.storage.local . There's no server of mine in the path — PR diffs only ever go to the AI provider you explicitly configure. Groq's free tier is generous enough to run the AI features for free for most individual workflows. You're paying provider cost directly, with zero markup, if you pay anything at all. How it's built Manifest V3 — required rethinking persistence patterns that worked under MV2's persistent background page; service worker lifecycle and content script injection needed more careful handling. GitHub REST + GraphQL APIs rather than DOM scraping — more upfront work, but