Loading…
Latest reads
Every post, summarised
Grounded summaries of engineering blogs, newest first. Each links to the original.
- 4,668 posts
- 20 companies
The Good Stuff
Paid picks we use ourselves. Links carry a referral code — a subscription through one earns us a commission at no extra cost to you.
Latest posts
Announcing The AI Agent Blueprint
The AI Agent Blueprint is a strategic guide for support, customer experience, and AI transformation leaders navigating how to adopt and scale AI Agents. Its first part, “Launch it,” covers building a business case, deciding whether to buy or build, evaluating an agent with a four-step framework, planning deployment, and continuously training, testing, deploying, and optimizing performance. The second part, “Scale it,” focuses on redesigning customer experience, organizational and system design, and economics through AI-first journeys, new roles and governance structures, and revised metrics, ROI models, and reinvestment strategies. The Blueprint argues that launching an agent is only the beginning: sustainable value requires treating AI as infrastructure and support as a potential growth lever, and it is live now.
Her Tech Circle rebuilt a community from scratch using Notion
After Girls in Tech abruptly ended its global operations, Renece Brewster and Karen Katz had one week to decide how to preserve an Australian community of 18,000 members. They launched Her Tech Circle (HTC), retaining the community’s core values while focusing on helping women in Australia and New Zealand thrive, lead, and contribute in tech. To rebuild quickly, HTC made Notion its digital headquarters, first piloting it with the social media team before rolling it out across the organization. The workspace combines a public-facing volunteer portal, a shared marketing database, and a directory that doubles as an org chart, linking roles, team leads, and peer support. HTC’s experience argues for testing tools early, making knowledge discoverable, and building scalable systems that let volunteers contribute independently rather than concentrating operational knowledge with founders.
Updates to Teams and Auto
Two billing updates will apply at the next renewal after September 15 for monthly and yearly plans. Teams is moving agent usage from fixed request costs to variable request costs, so charges rise or fall with the amount of work performed; a simple syntax question costs less than implementing a full pull request. This change extends the credit system already used by individual plans and unifies billing across tiers. For individuals, Auto will count toward included monthly usage at competitive token rates at the next renewal after September 15, replacing its unlimited status since June 2025; the post says Auto had previously matched premium-model pricing for individuals from December 2023 through June 2025 and for teams since June 2025.
How to cut through AI hype and choose solutions with confidence
Teams evaluating AI solutions can waste time, money, and trust when they lack technical fluency, choose unsuitable vendors, underestimate internal requirements, or expect immediate perfection. The post introduces Retrieval-Augmented Generation (RAG), vector search, agentic AI, and MCP as concepts that help teams distinguish static or rules-based tools from systems that retrieve current information, understand intent, take actions, and operate within governed boundaries. It argues that building an AI Agent in-house requires substantial work across embeddings, retrieval, prompt chaining, governance, security, maintenance, and model upgrades. Vendor evaluation should consider ongoing R&D, product roadmaps, adaptability, and maintenance, while implementation depends on structured content, documentation, process visibility, and APIs. Fin is cited as typically resolving over 76% of support questions out of the box, with resolution expected to improve through ongoing optimization and measurement.
Games as Model Eval: 1-Click Deploy AI Town on Fly.io
Daniel Botha argues that conventional benchmarks reveal little about how models behave in long-context, interactive situations or whether they deliver the tone a product requires. He presents games as a more observable evaluation setting, because success signals are unambiguous and gameplay exposes strategic reasoning, long-term planning, and adaptation with opponents or collaborators. The post focuses on a fork of a16z-infra’s AI Town, a pixel-art simulation inspired by Generative Agents: Interactive Simulacra of Human Behavior, where characters remember conversations, maintain relationships, react to events, and stay in character. A single deploy script runs the project on Fly Machines with scale to zero, cost and performance optimizations, and support for OpenAI-compatible services, Together.ai models, and custom embedding models configured through secrets.
The Future Isn't Model Agnostic
The post argues that AI product teams should stop treating model agnosticism as a default priority because users value reliable, familiar behavior more than model flexibility. It says improving models are converging, while differentiation shifts to product experiences shaped by prompts, edge-case handling, workflows, and model-specific behavior. Swapping models therefore means more than changing an endpoint: teams must rewrite prompts, rerun evaluations, and absorb changes users notice in how the product feels. Claude Code and Qwen 3 Coder, which the post says outperforms Claude in benchmarks, illustrate how tightly model behavior, interface, rituals, trust, and expectations can become coupled. The recommended approach is to choose one model, specialize deeply, and treat evaluation as architecture, with games such as an AI Town environment offered as a way to test models.
Cursor Agent CLI
Cursor has made its Agent available through a command-line interface (CLI) and in headless environments, extending it beyond the editor, web, mobile, and Slack. The release targets customers using Neovim, JetBrains, and other IDEs, while allowing Agent to run alongside those tools or as multiple parallel agents in a terminal or remotely. The CLI supports any model included with a Cursor subscription, and users can start it after installing with curl https://cursor.com/install -fsSL | bash and invoking agent chat with a prompt. Agent can generate files, run terminal commands, search a codebase, and now read, modify, or delete files and execute approved shell commands. The CLI is in beta, with evolving security safeguards and use limited to trusted environments.
GPT-5 is now available in Cursor
Cursor has made OpenAI’s GPT-5 available to users, presenting it as a coding-focused model based on an initial internal evaluation. Five engineers report using it for long-running tasks with Background Agents, parallel foreground agents, complex debugging, and Stripe-query latency optimization, while noting that explicit instructions improved its steerability. One engineer adjusted GPT-5’s verbose default style and follow-up behavior through rules. In a monorepo with separate frontend and backend submodules, GPT-5 built a backend API endpoint and corresponding React component, regenerated protobufs, and corrected resulting type errors in one shot. During launch week, paying users receive free credits, and the announcement characterizes GPT-5 as well suited to coding and tool calling.
From Intern Project to Production: How I Shipped the Draw Tool for Canva's Present Mode
Canva engineers developed and shipped a real-time drawing tool for presentation mode after user feedback highlighted it as a highly requested feature. Integrating the existing editor-bound draw functionality into presentations required resolving tight package coupling, dual-window scaling mismatches, and performance regressions. To overcome architectural boundaries, core draw logic was extracted into a shared common package using interface abstractions. Coordinate normalization resolved positioning and scaling differences across presenter and audience views, while code-splitting deferred loading the core engine until activation. As a result, presentation load time regression dropped from 7% to 0.24%, and the feature reached over 470,000 monthly active users in production.
It's Time to Evolve Authentication Security
Identity-based attacks and compromised credentials are driving a need for stronger authentication, while security requirements must be balanced against user friction and application sensitivity. The guidance recommends phishing-resistant factors, including smart cards, biometric-capable hardware, FIDO2 with WebAuthn, and Passkeys, while warning against security questions, SMS codes, email TOTP, and password antipatterns. It also advises using strong MFA as a backup, dynamic authentication policies and threat detection, and OAuth 2.1/OIDC through an identity provider, with step-up authentication to maintain assurances during a session. For application integration, the recommended approach is to redirect users to an Okta-hosted Sign-In Widget through vetted OIDC client libraries or Okta SDKs, reducing implementation errors in PKCE and token verification while supporting evolving standards.
Building financial operations agents with Hypermode and Stripe
Hypermode Agents and Stripe can be combined to create domain-specific financial operations agents from natural-language descriptions rather than conventional code. The workflow uses Hypermode’s Concierge to generate a system prompt, then connects the agent to Stripe through the Stripe Model Context Protocol (MCP) server and optionally to services such as Notion, Slack, and Google Calendar. With a restricted Stripe API key and sandbox data, the agent can retrieve policies, inspect customer and transaction history, apply refund rules, process payments, create invoices, and analyze subscriptions for metrics such as MRR. The examples describe partial refund decisions, onboarding workflows, campaign suggestions, and populated test environments, while the guidance recommends prompt iteration, human approval for high-value transactions, and monitoring and logging for compliance and improvement.
How Aaron Chasan is making the office less lonely
While working at Ernst & Young in 2020, Aaron Chasan heard HR leaders worry about maintaining social connection in a hybrid workplace, prompting him to build Thred. The tool asks employees who opt in to complete an interest assessment, then matches them with coworkers for one-on-one conversations around shared interests, applying a summer-camp insight about connecting isolated newcomers with socially connected peers. Platform data says employees who made a friend on Thred are 50 percent less likely to leave, and the service has expanded beyond workplaces to neighborhoods and school districts. Chasan runs Thred’s product roadmap, wikis, schedules, and other projects in Notion, which he describes as central to his professional and personal organization. He advises builders to surface common ground, start building rather than over-research, and maintain a personal connection to the problem.
Forward Deployed Engineering
Forward Deployed Engineering (FDE) is presented as a customer-facing engineering function for B2B companies that need to integrate software deeply, customize implementations, and deliver outcomes for enterprise customers. Palantir is described as creating the role after its founding in 2003, with engineers deployed at military sites and customer offices; the model later spread to companies including Scale AI, C3.ai, Databricks, and Snowflake. At Ramp, the team grew from two to 16 FDEs after emerging in fall 2023, moving from firefighting toward generalized features, platforms, and AI that support enterprise product-market fit and new verticals. Its operating model spans prospects, implementation, rollout, and long-tail support, while “always be scoping” encourages direct requirement questioning, workarounds, and generalized solutions. The hiring guidance prioritizes drive, ownership, customer empathy, and communication alongside sufficient technical fundamentals, arguing that judgment about quick fixes versus scalable solutions is central to the role.
MCP UI: Breaking the text wall with interactive components
Model Context Protocol (MCP) can let AI agents search catalogs, interpret reviews, build carts, and support purchases, but a text-only flow does not provide the visual and interactive details central to commerce. Shopify presents MCP UI as an extension that returns embedded UI resources for components such as product cards, with delivery through inline HTML, remote resources in sandboxed iframes, or Remote DOM. Its intent-based message system keeps components from directly modifying state: actions such as view_details, checkout, notify, and ui-size-change are surfaced for the agent to interpret, while render data lets hosts provide CSS for adaptive styling. The open-source, deliberately extensible protocol is demonstrated in a Shopify Storefront MCP UI Server prototype and is intended for commerce as well as data visualization, form builders, and media players.
AppLink Fundamentals III: Building with AppLink – Development Flow and Language Choices
AppLink Fundamentals III describes how to build Salesforce extensions on Heroku, covering local testing, OpenAPI contract management, deployment workflows, and programming-language selection. For applications that receive Salesforce requests, the supplied invoke.sh script simulates production headers using Salesforce CLI data, can activate session-based permission sets, and accepts JSON payloads for testing; Pattern 1 applications that call Salesforce APIs do not require this special setup. The OpenAPI specification serves as the shared contract for endpoints and Salesforce consumers, with publish-time validation intended to catch misalignment. AppLink also supports Agentforce actions through x-sfdc agent extensions, enabling topics, publishing, input and display settings, privacy controls, and outputs such as generated PDFs in the automotive finance example. The comparison positions Apex for transaction-critical record updates and AppLink languages such as Node.js, Python, and Java for external integrations, intensive computation, elastic scaling, and reuse of existing code.
Introducing CIBA for Secure Transaction Verification
CIBA addresses identity verification when an application cannot use an interactive login on the consumption device, including bank customer-service changes, retail POS payments, browser-constrained devices, and shared kiosks. Client-Initiated Backchannel Authentication decouples authentication from the application: a client sends a back-channel request to an OAuth 2.0 authorization provider, while the user approves it on a separately enrolled phone or smartwatch. CIBA extends OpenID Connect with a grant type, discovery metadata, and poll, ping, and push token-delivery modes; in the described banking flow, the application receives a user-scoped token to update the email address. The approach improves least-privilege access and avoids exposing credentials on shared devices, but can enable MFA-fatigue-style attacks, should not be used same-device, and may warrant device code flow in some cases.
FlashList v2: A ground-up rewrite for React Native's New Architecture
FlashList v2 is a ground-up rewrite of the React Native list component, aimed at removing v1’s dependence on item-size estimates, native layout corrections, and imprecise scrolling. Built for React Native’s New Architecture, it uses synchronous layout measurements to correct positions before paint and eliminates the need for native code. Its algorithm combines progressive rendering, predictions updated by item type, and rapid corrections, while adaptive rendering responds to scroll velocity, direction, and device performance. The new scrolling system progressively refines target positions for precise scrollToIndex operations, and horizontal lists can contain resizable items and coordinate with parent lists. The release also adds scroll-position maintenance, improved masonry support, recycle-pool controls, helper hooks, and better web support; benchmarks report up to 50% less blank area while scrolling than v1 on the new architecture.
AppLink Fundamentals II: Advanced AppLink Integrations – Automation & AI
Heroku AppLink lets connected Heroku applications extend Salesforce through Data Cloud, Flow, Apex, and Agentforce, bringing external logic, real-time data processing, and automation into Salesforce orgs. It uses an OpenAPI YAML or JSON specification, including x-sfdc metadata for authentication and permissions, to generate strongly typed Apex classes, Flow External Service definitions, Agent Actions, and related Connected App and Permission Set configurations. Developers can invoke services synchronously or asynchronously from Apex, use operations as no-code Flow actions, and configure Agentforce to call endpoints for specialized processing; callbacks support longer-running work. AppLink uses User Mode authentication by default, while administrator-controlled Permission Sets can temporarily elevate access during execution without changing a user’s permanent permissions.
AppLink Fundamentals I: AppLink Integration Patterns – Connecting Salesforce to Heroku Applications
AppLink Fundamentals I describes four integration patterns for connecting Salesforce orgs with Heroku applications, focusing on API access and Salesforce extension. Pattern 1 uses run-as-user authentication for automated or customer-facing applications, with the AppLink add-on, CLI plugin, optional SDK, named authorizations, and SOQL queries through the Data API; the SDK manages authentication, session management, and connection pooling for single- or multi-org access. Pattern 2 lets Salesforce users invoke published Heroku services through Flow, Apex, or Agentforce, using User Mode or elevated “user mode plus” permissions controlled by Permission Sets, an OpenAPI description, and a service-mesh buildpack that blocks external access. The post also positions batch processing and real-time eventing as extensions of these patterns, and describes Data Cloud querying and Data Action Targets for applications to receive Data Cloud events.
Secure Your Express App with OAuth 2.0, OIDC, and PKCE
Building authentication from scratch is risky and time-consuming, so the tutorial integrates Okta with an Express application using Passport, openid-client, OAuth 2.0, and OpenID Connect (OIDC). It creates a role-based expense dashboard in which users view spending data for their assigned teams, with team membership mapped from the email claim in the ID token. The setup uses Authorization Code Flow with PKCE, defined in RFC 7636, alongside express-session, EJS views, environment variables, and Okta redirect URI configuration. The sample project includes routes for login, logout, dashboard, profile, and team-specific expenses, while the running app displays these authenticated views. It concludes that OIDC supplies the identity layer over OAuth 2.0 and presents PKCE as a security baseline for server-side and browser-based web applications.
Top topics
- Architecture834
- Performance815
- LLMs659
- Machine Learning621
- Open Source563
- AI Agents553
- AI469
- Developer Experience448
Weekly digest
The best engineering reads, once a week.