标签：#ai

This post is a TypeScript implementation of the pattern described in "Beyond the Agentic Loop: The Orchestrator Pattern for Multi-Agent Systems" by Amogh Ubale (Stackademic). The original is Python with generic agents; here we keep the idea intact and re-theme it as a shopping assistant so the three execution modes have something concrete to chew on. All the design credit goes to that article — go read it first. The cast: a handful of shopping agents Before the pattern, the scene. The demo is a small storefront assistant backed by a few single-purpose agents: Catalog — list the categories on offer, or search products by keyword and price. Inventory — check stock and availability for a product. Pricing — look up the current price and any active promotions. Reviews — fetch a product's rating and review highlights. Order — place an order for a product. A customer request might need just one of these, several of them at once, or a few in a strict order — and deciding which of those shapes a request calls for is exactly what the orchestrator is for. The problem: the LLM as a while loop The default way to build a multi-agent system is the agentic loop : you hand the model a bag of tools and let it drive. think → call a tool → observe the result → think again → call another tool → … The LLM is both the brain and the control flow. That's wonderfully flexible, and it's the right tool when the task is open-ended and you genuinely don't know the steps in advance. But in production it has three nasty properties: Unpredictable shape. Every "think" step is another LLM round-trip, so a three-agent task might take 3 calls or 9 — you don't know until it runs, and latency swings with it. (The article clocks a representative three-agent query at ~7 calls through the loop; the wall-clock and spend follow, but the unpredictability is the part that actually bites.) Non-determinism. The same question can take a different path each time, which makes behavior hard to reason about and hard t

Fable 5 came and went. And because it was taken away so quickly, developers wanted it back even more. Scarcity has a way of making things feel more valuable. Reviews during its short tenure described a model that was very capable and great at churning on long-running, ambiguous tasks. But it was too expensive. The model was also intelligent enough that, on large work and overhauls, it tended to overthink. Most likely because of its size. For iterative work like implementing a feature or change, Fable 5 was comparable head-to-head with GPT 5.5, except Fable 5 would run for 10x as long: a larger model, more overthinking, and more time. The other issue was fallback behavior. If you hit a case where the model needed to call the fallback Opus model, you would not necessarily know it happened, and you would be billed at the higher charge. Nonetheless, it was a noticeable change compared to existing models. It was good at churning on a specific, goal-oriented problem. For example, optimizing a slow path by repeatedly profiling, tracing call sites, tightening hot loops, and validating the regression budget. For architecture design, it was still not remarkable. So it was good at that goal-oriented push, but even within that you needed to run it in sessions, review its code, and steer or compact to get the results you wanted. It is a good model to use for planning, research, and review, which is where I had adopted it. I saw real benefits. However, when it came to orchestration or running workflows, I still believe GPT 5.5 is better and more cost-effective on both tokens and time. Personally, I care about token spend, but I care immensely more about my time. The bigger problem Fable 5 exposed Model capability aside, I still think we are missing a bigger problem, and Fable 5 put a magnifying lens on it because of the nature of its capabilities. AI adoption in organizations is still a challenge for many developers because there are not enough good examples of how power users of

We’ve all been there: it’s 2 AM, you’re deep in a "Refactoring Rabbit Hole," your coffee is cold, and your heart is racing. You feel productive, but is your body paying the price? As developers, we often ignore the physical signals of burnout until it's too late. In this tutorial, we are going to quantify the "Dev Grind." We'll build a Programmer Stress Warning Dashboard using the Oura Ring API to track Heart Rate Variability (HRV) and correlate it with your GitHub commit frequency . By the end of this guide, you'll have a real-time visualization of how that complex Kubernetes migration is actually affecting your nervous system. We will be utilizing HRV monitoring , biometric data visualization , and the Oura Ring API to create a predictive stress model for high-performance engineers. The Architecture 🏗️ The logic is simple: we fetch your physiological "readiness" and stress markers from Oura and overlay them with your activity from GitHub. If your commits are spiking while your HRV is tanking, it's time to step away from the keyboard. 🥑 graph TD A[Oura Cloud API] -->|HRV & Stress Levels| B(Next.js Backend) C[GitHub API] -->|Commit Frequency| B B -->|Data Aggregation| D{Correlation Engine} D -->|JSON Stream| E[D3.js Visualization] E -->|Alerts| F[Developer Dashboard] style F fill:#f96,stroke:#333,stroke-width:2px Prerequisites 🛠️ To follow this tutorial, you'll need: Oura Ring & a Personal Access Token (from the Oura Developer Portal ). Next.js (App Router) for our frontend and API routes. D3.js for crisp, reactive data visualizations. Vercel for instant deployment. Step 1: Fetching HRV Data from Oura API Heart Rate Variability (HRV) is the gold standard for measuring autonomic nervous system stress. A high HRV usually means you're recovered; a low HRV means you're under pressure. Here is a clean implementation of a Next.js API route to grab your daily stress metrics: // app/api/oura/route.ts import { NextResponse } from ' next/server ' ; export async function GET (

When I started coding, I made so many silly mistakes 😅 Today I’m sharing 3 small mistakes that every beginner developer makes: 1. Trying to write "Perfect Code" on Day 1 Bro, your code will be messy at the start. Just make it work first. Perfect comes later. 2. Watching tutorials but not coding yourself Watching videos is easy. But you only learn when you type the code on your own laptop. 3. Getting scared of errors Red error ≠ Failure. Error = Teacher. Copy it to Google, you’ll find the fix. What mistake did YOU make when you started? Tell me in the comments 👇

Anthropic's popularity with business users is growing so well that the latest beef with the government might actually boost it, data from Ramp suggests.

NAACP lawsuit says xAI uses gas turbines without permits for Grok data center.

In the coming weeks, Apple will move anonymously generated emails addresses to a different domain.

There is a comparison that the artificial intelligence industry had kept out of the public conversation until now. Satya Nadella brought it up this Sunday in a post on X that garnered over a thousand responses in just a few hours. The metaphor he used is "industrial offshoring" . Just as the first wave of globalization hollowed out industrial economies, wiping out factory jobs and decades of competitive advantage with consequences we still feel today, artificial intelligence threatens to do the same to corporate knowledge. The Silent Drain of Expertise The mechanism Nadella describes is concrete. If an organization hands over its workflows, its domain knowledge, and the accumulated judgment of its teams to external AI models, those models absorb it. What was once a unique advantage, now could become a generic capability available to everyone. There are no layoffs or plant closures. The hollowing out happens silently, in every usage cycle, in every operation the model records and leverages. Where there was once exclusive know-how, there is now a standard resource. "You can outsource a task, or even a job. But you can never outsource the learning." Microsoft CEO Warns That AI Winners Could Hollow 'Entire Industries' - Business Insider AI models are hoovering up corporate knowledge, and that's leaving one big loser, says Satya Nadella. businessinsider.com The Invisible Asset / The Identity This warning is not directed at employees but at executives. The risk Nadella identifies is not the loss of an individual position, but the erosion of the organisation's collective intellectual property, its processes, and the judgment a team spends years building. To name this, he introduces a term that was not in the business management vocabulary until now: "Token Capital" . This represents the layer of agentic capability that a firm builds and owns when it connects its real workflows with the AI models it uses. It is not software or a database. It is a system that learns with eve

The promise of agentic AI coding was a tireless partner, an assistant that could take a feature request and run with it while we focused on the hard problems. The reality, for most professional engineering teams, has been different. The reality is a brilliant but distractible intern you have to constantly supervise. The reality is spending 20 minutes writing the "perfect prompt," only for the AI to ignore a critical constraint, use a deprecated pattern from your codebase, and confidently break three other features. The reality is the "babysitting tax." It's the cognitive overhead of constantly reviewing, reverting, and re-explaining. And it's negating the incredible potential of these tools. At BrainGrid, we believe the problem isn't the agent—it's the plan. Or the lack thereof. In our rush to generate code, we've skipped the most critical step: creating a shared, deep, and unambiguous understanding of what we're actually building. "Vibe coding" doesn't work in a multi-tenant system where permissions are non-negotiable, or at least not with peace of mind. It doesn't work in a complex fintech application where money is on the line. And it certainly doesn't work in a four-year-old codebase with layers of tech debt and unwritten rules. The bottleneck in software development is no longer just the speed of writing code. The bottleneck has shifted to the speed of creating a reliable plan. BrainGrid is the AI-powered planning platform built to solve this new bottleneck. It's designed to provide the structure and guidance—the "babysitting plan"—that turns powerful but unreliable coding agents into predictable and effective teammates. Here's how: We Give the Agent a Map BrainGrid starts by deeply analyzing your entire codebase—its architecture, data models, and dependencies. It provides the persistent context that agents desperately need but currently lack. We Help You Define the Destination Our requirements agent acts like a seasoned tech lead, asking you and your team clar

The most important design decision in an email classifier isn't the model — it's the label set, and here's the one I keep coming back to: You triage email into one of four categories: URGENT — production incidents, executive requests; reply within 1 hour ACTION — code reviews, meeting follow-ups; reply same day FYI — informational, no response needed NOISE — newsletters, marketing, automated notifications From: {sender} Subject: {subject} Snippet: {snippet} Return ONLY the category name. Nothing else. That's the working prompt from the Nylas email triage recipe , and almost every line encodes a taxonomy-design lesson worth unpacking. Most people building email agents obsess over model choice and prompt phrasing. The recipe's quiet thesis is that the label set itself does the heavy lifting — get the taxonomy right and a cheap model classifies well; get it wrong and no model saves you. Why four is the magic number The recipe states it flatly: four is the right number. Three loses fidelity — everything important collapses into one overloaded bucket and you've built a binary classifier with extra steps. Five and the model starts confusing categories, because the boundaries between adjacent labels get too thin to express in a definition. Notice what makes these four work. They aren't topics — they're response obligations . URGENT means "reply within the hour," ACTION means "reply today," FYI means "no response needed," NOISE means "archive." Each label maps to exactly one behavior. That's the test I'd apply to any email taxonomy: if two labels lead to the same action, merge them; if one label leads to two different actions depending on content, split it. The same principle shows up in the sales context. The Agent Accounts overview describes an outreach agent classifying replies as interested / not now / unsubscribe — three labels, because the workflow has exactly three branches: book the meeting, schedule a follow-up, stop emailing. The taxonomy is the decision tree, fla

You've built the agent, the reply loop works, the demo lands — and then someone asks the question you didn't budget time for: "so what address does it send from?" Suddenly you're staring at noreply-svc-prod2@yourcompany.com realizing that the first thing every recipient sees isn't your prompt engineering. It's the From line. An agent's email address is an interface. Humans parse it before the subject, mail servers judge it before the body, and spam filters score it before any human sees it at all. Once your agent has a real mailbox — which is what Nylas Agent Accounts (currently in beta) provide — address design becomes a product decision with three layers: the local part, the domain, and the disclosure question. The local part: role beats persona beats hash Take three candidate addresses for the same scheduling agent: scheduling@ — a role. Tells recipients what the mailbox does and implies that emailing it is how you use the service. jane.ai@ — a persona. Friendlier in a sidebar avatar, but it invites recipients to treat the sender as a colleague, with all the expectations that carries. bot-7f3a@ — an artifact. Screams "auto-generated," gets mentally filed next to spam, and gives a human nothing to anchor on. The docs consistently model the first pattern — sales-agent@ , support@ , scheduling@ appear throughout the Agent Accounts overview — and I think that's right for a reason deeper than convention. A role address makes an honest promise about capability: scheduling@ claims it can schedule, nothing more. A persona address makes an implicit promise of general competence that current agents can't keep. When jane.ai@ fails to understand a simple request, it reads as a person being obtuse; when scheduling@ fails, it reads as a tool hitting its limits. Same failure, different trust damage. The overview's framing is worth internalizing: an agent identity should be like any other user in your organization — reachable, persistent, accountable. Address design is how that

Day 1, 4:02 p.m.: a customer asks your agent a billing question and gets an answer. Day 6, 9:30 a.m.: they reply "actually, that didn't work." If your agent lives in a chat widget, that second message starts from zero — the session died with the tab, the context is gone, and the customer gets to repeat themselves. If your agent lives in a mailbox, the reply arrives inside the conversation , with the full history attached by the protocol itself. That's the argument in one before/after: chat sessions evaporate; email threads persist. And for agents that work across days rather than minutes, the thread is the most underrated memory substrate available. The protocol already built your memory layer Email threading runs on three headers, as the threading docs lay out. Every message carries a globally unique Message-ID . A reply adds In-Reply-To (the ID it's answering) and References (the full chain of IDs, oldest to newest). By the time a thread is five messages deep, References holds five Message-IDs in order — a complete, tamper-evident record of the conversation's shape, maintained by every mail client on earth. Compare that to what we hand-roll for chatbots: session stores, conversation tables, context windows we serialize and rehydrate. Email gives you the equivalent for free, federated across organizations, and — this is the part I find most compelling — human-auditable . Anyone with mailbox access can read exactly what the agent's memory contains, because the memory is the correspondence itself. No vector store inspection tools required. With Nylas Agent Accounts (in beta), the agent owns the mailbox where this accrues, and you never parse headers by hand. The Threads API groups messages by their header chain; each thread object gives you ordered message_ids , participants , and activity timestamps. When a reply fires message.created , the payload includes a thread_id — fetch the thread, walk its messages, and the agent has its full conversational past before decid

A human assistant borrows the boss's calendar; a scheduling bot owns its own. That one difference dissolves most of what makes calendar automation miserable. The borrowed-calendar model is how nearly every scheduling tool works today: connect to a person's Google or Microsoft account via OAuth, request calendar scopes, and act on their behalf. It works, but the seams show everywhere. The human's calendar fills with bookings the bot manages. Delegation permissions vary by provider and admin policy. Tokens expire when the person changes their password or leaves the company. And the bot has no address of its own — every invite, every confirmation email, appears to come from a person who didn't write it. Nylas Agent Accounts (currently in beta) invert this. Each account is a real mailbox and a real calendar , provisioned automatically, owned by your application. From a participant's perspective there's nothing special about it — it's just another attendee on the invite. What "owning availability" actually changes When the bot's calendar is its own, availability stops being a permissions question and becomes a query. The agent calls the free/busy endpoint against its own primary calendar, gets back busy blocks for a time window, and proposes open slots. No delegation, no scopes negotiation, no "the admin needs to approve calendar sharing for service accounts." The scheduling-agent tutorial wires the whole loop: a meeting request lands at scheduling@agents.yourcompany.com , a message.created webhook fires, an LLM parses duration and timezone, the agent checks its own free/busy and replies with 3 candidate slots. When the human picks one, the agent creates the event: curl --request POST \ --url "https://api.us.nylas.com/v3/grants/<GRANT_ID>/events?calendar_id=primary&notify_participants=true" \ --header "Authorization: Bearer <NYLAS_API_KEY>" \ --header "Content-Type: application/json" \ --data '{ "title": "Product demo", "when": { "start_time": 1744387200, "end_time": 174

When was the last time you deleted an email account on purpose? For most teams the answer is never, and that tells you something. We treat mailboxes the way we treated servers in 2008: hand-built, carefully named, kept alive indefinitely because recreating one is painful. They're pets. Meanwhile every other piece of our infrastructure — compute, queues, databases — became cattle: numbered, provisioned by code, destroyed without sentiment when the job ends. Email is finally catching up. With Nylas Agent Accounts (in beta), a mailbox is created with one call and destroyed with another, and that symmetry is the whole point. The full lifecycle in two commands Provisioning, from the CLI: nylas agent account create signup-agent@agents.yourdomain.com Or via POST /v3/connect/custom with "provider": "nylas" — no OAuth, no refresh token, just an address on a domain you've registered. Teardown is equally unceremonious: nylas agent account delete signup-agent@agents.yourdomain.com --yes (The API equivalent is a DELETE on the grant.) The signup automation recipe treats this as a loop: provision a fresh inbox, point a third-party signup form at it, catch the verification email through a message.created webhook, follow the confirmation link, delete the grant. No human inbox involved at any step, and nothing left behind. The middle of that loop is about twenty lines of webhook handler, and the recipe's version filters hard before acting — right grant, right sender, right URL shape: const { grant_id , id : messageId , from } = event . data . object ; if ( grant_id !== AGENT_GRANT_ID ) return ; const sender = from [ 0 ]?. email ?? "" ; if ( ! sender . endsWith ( " @saas-you-care-about.example.com " )) return ; const match = /https: \/\/ saas-you-care-about \. example \. com \/ confirm \? token= [^ " \s < ] +/ . exec ( message . body , ); if ( match ) await fetch ( match [ 0 ]); Nylas fires message.created within a second or two of mail arriving, so the whole signup round-trip typical

Every project I touch lately ends up needing the same awkward thing: a reliable way to pull the web into a script or an agent. Not a brittle scrape held together with CSS selectors and hope, but something that takes a URL and hands back clean, structured text I can actually pipe into the next step. I have built that wrapper more than once, and it is never as small as you think it will be. So when Mozilla dropped the tabstack CLI, a single Go binary that wraps the Tabstack AI API, I wanted to spend a proper afternoon with it. The pitch on the README is direct: every web interaction your agent or stack needs, from the terminal or a script. It turns any URL into clean Markdown or schema-shaped JSON, runs natural-language browser automation, and answers research questions with cited sources. The part that made me sit up is that the output is pretty in a terminal and pipeable into jq without a flag. That is a small detail, and it tells you the people who built it actually live on the command line. Let me walk you through it the way I poked at it myself. Getting it installed There is no runtime to install and nothing to bootstrap, because it ships as a single static binary built for macOS, Linux, and Windows. The quickest route is the install script: curl -fsSL https://tabstack.ai/install.sh | sh That fetches the right binary for your platform and puts it on your PATH , and you are ready to go. If you would rather not pipe a script into your shell, there are a couple of alternatives. With Go on your machine you can use: go install github.com/Mozilla-Ocho/tabstack-cli/cmd/tabstack@latest That drops the binary in $GOPATH/bin , which is usually ~/go/bin . If your shell cannot find tabstack afterwards, you almost certainly have not got that directory on your PATH : export PATH = " $HOME /go/bin: $PATH " And if you want to avoid Go entirely, there are pre-built binaries on the Releases page, or you can clone the repo and run make install-local , which builds it and copies it t

The email mailbox just became an API resource, and that matters far more than the setup time it saves. For most of software history, a real email address — one that sends, receives, and threads — was an artifact of IT process. Someone created it in an admin console, someone else configured the client, and your application got access through OAuth consent screens and refresh tokens borrowed from a human. Compare that to how you get a database, a queue, or a TLS cert today: one API call, one ID back, done. Nylas Agent Accounts (currently in beta) close that gap. The quickstart goes from API key to a sending-and-receiving mailbox in under 5 minutes, and the provisioning step is a single request: curl --request POST \ --url "https://api.us.nylas.com/v3/connect/custom" \ --header "Authorization: Bearer <NYLAS_API_KEY>" \ --header "Content-Type: application/json" \ --data '{ "provider": "nylas", "settings": { "email": "test@your-application.nylas.email" } }' No refresh token, no OAuth dance — unlike OAuth providers, the "nylas" provider needs only an email address on a registered domain. The response contains a grant_id , and that one ID drives everything else: messages, drafts, threads, folders, attachments, calendar, webhooks. There are actually three ways to create an account — this API call, the Dashboard, or a single CLI command ( nylas agent account create ) — but they all end at the same place: a live mailbox. Why 5 minutes is a threshold, not a convenience Provisioning time isn't a linear cost. There's a threshold below which a resource changes category — from "thing you request" to "thing your code creates." Virtual machines crossed it with cloud APIs and we got autoscaling. TLS certs crossed it with ACME and we got HTTPS-by-default. Mailboxes crossing it means email addresses stop being scarce, pre-planned identities and start being something a program allocates when it needs one. What does that look like in practice? System mailboxes without ceremony. A support

Move originally planned for Monday would have heavily increased power users' costs.

Git worktrees have been around since 2015, but it wasn't until recently they became popular. Learn what they are, how to use them, and why you might. The post What are git worktrees, and why should I use them? appeared first on The GitHub Blog .

SpaceX's valuation has increased by $1 trillion since its shares started trading on Friday.

By spring 2026, the division of labor between human engineers and AI had become precise enough to describe. Not speculate about. Describe. Delegate these 7 immediately: Boilerplate generation: CRUD scaffolding, config files, standard patterns. Near-human accuracy. Review required is a naming scan, not a logic audit. Test generation: 40-60% faster test development with no measurable decline in coverage quality, provided the tests are reviewed by someone who understands the domain. Documentation: 67% of companies rely on AI-assisted doc generation in 2026. The first draft is a solved problem. Your job is verifying and contextualizing. Code translation: Python to TypeScript. React to Vue. Framework migrations that once consumed sprint cycles now take hours. Routine bug fixing: Claude Code, Devin, BugBot can resolve 60% of reported bugs autonomously. Resolution time down 30-50%. Automated code review: First-pass filter before human review. Misses context issues. Doesn't replace human review. Eliminates noise so you focus on signal. Commit hygiene: Messages, PR summaries, changelog entries. Fully automatable. No meaningful error rate. Never delegate these 6: Architecture and system design: AI proposes. You decide. The tradeoffs require organizational context, team capability assessment, and long-horizon thinking no model possesses. Business context translation: The spec says "export to CSV." You ask: which users, under what conditions, with what compliance implications? AI cannot know the specification is wrong. You can. Security architecture: AI generates vulnerabilities as readily as it detects them. Adversarial thinking is not statistical. It is human. Long-horizon product thinking: What to build and why. Not how. Multi-stakeholder navigation: The politics, the relationships, the conversation with the PM that keeps the sprint on track. No model has stakes in the outcome. Agent orchestration: Designing, managing, and correcting the AI systems themselves. This is the ne