Loading…
Topic
832 posts about Architecture. Every summary links to the original.
See the idea
Amazon Bedrock is the managed reasoning tier in an agent architecture, not the whole system. This layered view shows the pipelines, governed tables, query layer, and guardrails around it.
API versioning as an architecture: requests enter through a version header, pass through a chain of reversible version changes, and reach controllers that only ever see the latest model.
BIAN gives banks a shared vocabulary and service-domain contracts that sit between business concepts and the systems implementing them. See how domains, contracts, and governed access stack into one architecture.
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.
Newest first
The post addresses the difficulty of using AI agents to configure Stripe resources when one-off API calls leave no durable source of truth for state, changes, or environment differences. It recommends using agents to author Terraform configuration rather than operating Stripe directly, so products, prices, and webhook endpoints become explicit, reviewable code. The example defines a Standard Plan with $20 monthly and $200 annual prices, selected webhook events, and outputs for both price IDs, then applies it with terraform plan and terraform apply. Terraform provides declarative, repeatable configuration supported by Git history, pull-request review, and environment-specific workspaces. Separate sandbox and livemode workspaces, paired with matching STRIPE_API_KEY values, are presented as a way to reduce accidental cross-environment changes.
First Block features Gerry Giacomán Colyer, Clara’s co-founder and CEO, discussing the company’s founding, rapid growth, and expansion of AI agents for finance operations across Latin America. Clara’s bank partner shut down only months after launch, prompting the team to secure direct issuer licenses with Visa and MasterCard in two weeks and build more robust infrastructure from the outset. The episode connects that resilience to product-led growth: a self-serve onboarding flow supported more than 20,000 customers across three countries, from pre-revenue startups to the Mexican Stock Exchange. The company is now applying its transaction data across Latin American businesses to a financial analyst agent that automates policy enforcement and approval workflows. It also covers the founding lesson from a previous company’s financial-tooling difficulties, early milestones, scaling decisions, and a roadmap across markets, alongside questions about efficiency, resilient infrastructure, and distinctive data advantages.
Differential Transformer V2 introduces an architectural refinement to differential attention that pairs and subtracts query heads within the same grouped-query attention group. The architecture doubles query heads while preserving key-value head counts, which avoids increasing key-value cache demands and removes the need for custom kernels. DIFF V2 replaces the per-head RMSNorm of its predecessor with a per-token, per-head projected lambda passed through a sigmoid function. This formulation expands the context root-mean-square range to between zero and root two, preventing massive gradient magnifications, mitigating attention sinks, and stabilizing large learning rate pretraining. Ablations confirm that sharing keys and values across subtracted heads and constraining lambda scaling are necessary to prevent training instability and elevated loss.
Open Responses is a new open inference standard initiated by OpenAI, developed by the open source AI community, and backed by Hugging Face. While agentic workloads require multi-step planning and tool execution, the ecosystem has remained constrained by the legacy Chat Completion format and proprietary Responses implementations. Open Responses addresses this mismatch by standardizing semantic event streaming, provider-specific configuration options, and distinct roles for model providers and intermediary routers. The specification formalizes reasoning visibility across raw traces, protected encrypted content, and sanitized summaries while supporting provider-managed sub-agent execution loops. Developers can now orchestrate multi-step tool calls and stream reasoning deltas across heterogeneous providers through a single consistent API schema.
Traditional retrieval-augmented generation relies on text parsing and optical character recognition to extract data from complex visual documents. These legacy techniques introduce high engineering effort, inconsistent accuracy, and heavy scaling costs. Vision RAG resolves these challenges by embedding entire visual documents directly through multimodal models like Voyage AI's voyage-multimodal-3.5, removing the need for text extraction pipelines. In this pipeline, dense vector embeddings map both text queries and visual assets into a unified representation space. At query time, the system retrieves relevant document images and supplies them alongside the text prompt to Anthropic's Claude 3.5 Sonnet to generate visually grounded responses.
Ramp built Inspect, a hosted background coding agent that writes code and verifies its work using the context and tools available to engineers. For backend tasks it can run tests, inspect telemetry, and query feature flags, while frontend work can be checked visually with screenshots and live previews. Each session runs in a sandboxed Modal VM initialized from repository-specific images and snapshots, with integrations including GitHub, Slack, Sentry, Datadog, LaunchDarkly, Braintrust, and Buildkite. Inspect supports frontier models, MCPs, custom tools, and skills, and provides Slack, web, Chrome extension, pull request, and browser-based VS Code workflows whose changes remain synchronized. Ramp reports that about 30% of merged pull requests in its frontend and backend repositories are written by Inspect.
Universal Commerce Protocol (UCP) is an open standard co-developed by Shopify and Google to let AI agents discover merchant capabilities, negotiate what both sides support, and transact with merchants. It addresses commerce complexity arising from cart-, buyer-, and market-dependent payment rules, discount combinations, and fulfillment variations. UCP uses layered extensibility: a shopping service supplies transaction primitives, capabilities such as Checkout and Orders are independently versioned, and extensions add domain-specific schemas without changing the core. Profiles and reverse-domain namespaces support decentralized capability discovery, while checkout states and continue_url enable structured handoff when human input or unsupported capabilities are required. Payment handlers are negotiated dynamically per transaction, and the public protocol is presented as ready for merchants, agents, and providers to build against.
Code And Let Live argues that read-only, ephemeral sandboxes are the wrong abstraction for coding agents, which need durable computers rather than fresh containers for every task. It introduces Sprites, disposable cloud computers that provide root Linux shells, 100GB of initial capacity, HTTPS through an Anycast network, automatic idle shutdown and metering stops, and persistence until explicitly removed. Sprites can be checkpointed and restored in about a second, allowing interactive recovery after changes while retaining installed software and development state across days or months. The argument extends beyond developer workflows: durable agents can keep realistic application context, observe logs, and support personal software whose development and production environments are the same, although the post says Sprites are unsuitable for applications serving millions of users.
Lean teams competing with larger companies cannot match their rivals’ hiring capacity or budgets, prompting a reassessment of success based on individual impact rather than headcount. Adding tools, integrations, and AI can create a “multi-tool trap,” scattering information and accelerating mistakes when infrastructure and direction are weak. The recommended response is to consolidate work and knowledge into connected systems, invest in documentation such as roadmaps, specifications, requirements, and strategic memos, and choose infrastructure improvements over reflexive hiring. These foundations give AI usable context, preserve decisions through organizational change, and help individuals operate as effective generalists; the conclusion is that scalable infrastructure can let one person do work that once required three, while making each future hire more impactful.
Lyft built a centralized Feature Store to optimize feature management, deployment, and data consistency for machine learning workflows across its rideshare platform. The system ingests batch features defined by Spark SQL and JSON metadata into Airflow DAGs, which simultaneously write data to Hive for model training and to an online serving layer for low-latency inference. Real-time streaming features are processed with Apache Flink and Apache Kafka before being ingested into the serving infrastructure. The online layer, dsfeatures, couples DynamoDB with a ValKey write-through LRU cache and OpenSearch to serve embeddings. Infrastructure optimizations reduced standard P95 read latency by a third while supporting over a trillion additional read and write operations.
The Technology Innovation Institute introduced Falcon-H1-Arabic, a family of Arabic language models released in 3B, 7B, and 34B parameter sizes. Built on a hybrid architecture, each block runs Mamba State Space Models and Transformer attention in parallel before fusing their representations at the output projection. Pre-training incorporated around 300 billion tokens across Arabic dialects, English, and multilingual content filtered via linguistic analysis. A post-training pipeline combining supervised fine-tuning and direct preference optimization addresses long-context utilization and alignment. Across evaluations on the Open Arabic LLM Leaderboard, the 34B model achieves roughly 75%, exceeding the performance of larger baseline systems like Llama-3.3-70B.
The post frames AI as a new “miracle material” that could reshape knowledge work as steel and semiconductors reshaped earlier eras. It argues that coding agents already let one programmer orchestrate several AI coding agents, but broader knowledge work remains constrained by fragmented context across tools and weak verifiability. At the organisational level, it compares AI with steel and steam, suggesting agents could preserve workflow context, surface decisions, and reduce dependence on meetings and hierarchical approvals; Notion is described as using more than 700 agents alongside 1,000 employees for repetitive tasks. At economy scale, it predicts organisations spanning humans and thousands of agents, with continuous workflows and new rhythms, while acknowledging that this transition may be disorienting and requires redesign rather than simply adding chatbots to existing tools.
MongoDB recapped its product releases, executive transitions, and enterprise adoption milestones throughout 2025 alongside predictions for 2026. The company acquired embedding and reranking specialist Voyage AI to mitigate large language model hallucinations and launched MongoDB AMP to accelerate legacy application modernization. Vector search and full-text search capabilities were expanded from MongoDB Atlas to Community Edition and Enterprise Server, enabling on-premises and hybrid retrieval-augmented generation workloads. Enterprise implementations included pharmaceutical distributor McKesson scaling tracking infrastructure to handle 1.2 billion containers annually after replacing its monolithic legacy system. Executive predictions for 2026 emphasized human-in-the-loop verification, grounding language models with factual retrieval, and building multi-cloud resilience against outages and data sovereignty constraints.
Many existing AI agent frameworks suffer from brittleness, tool misuse, and failures when executing complex workflows. To address these limitations, the open-source Configurable Generalist Agent (CUGA) introduces structured orchestration that decomposes user goals into programmatic subtasks tracked by a dynamic task ledger. The framework integrates agentic patterns like planner-executor and code-act, delegating subtasks to specialized agents that generate pseudo-code before running execution in a secure sandbox. Released under the Apache 2.0 license, CUGA integrates with Langflow for low-code visual workflow assembly and supports multi-tool environments through OpenAPI specs, MCP servers, and LangChain. Testing on inference platforms like Groq with open models such as gpt-oss-120b demonstrates rapid response times during multi-step planning and validation.
llama.cpp server now includes a router mode that enables dynamic loading, unloading, and switching between multiple LLMs without restarting the server. The architecture runs each model in an isolated process to ensure a single model crash does not affect other active instances. Running llama-server without specifying a model activates auto-discovery across the cache directory or a designated folder of GGUF files. In addition to on-demand loading and least-recently-used eviction capped by default at four models, the server provides endpoints for manual loading, unloading, and listing model statuses. Models inherit global configuration options or use dedicated configuration presets while also integrating directly into the built-in web UI.
Kiro's Stripe power is presented as a way to build a production-ready SaaS subscription flow while avoiding the fragmented output common with generic coding assistants. Using a natural-language specification for three monthly tiers and a three-month one-time option, Kiro creates a React frontend, Node.js backend API, CDN-hostable static assets, and server-side Stripe Checkout Session creation. The integration includes Stripe-specific steering files, MCP servers, and hooks, while the webhook handler preserves the raw request body, verifies HMAC signatures with stripe.webhooks.constructEvent(), rejects invalid events with HTTP 400, and routes lifecycle events such as checkout completion and subscription cancellation. The post concludes that this provides a secure, scalable foundation while leaving teams to customize business logic, including access provisioning and deprovisioning, instead of building payment infrastructure from scratch.
The 2025 BFCM live globe was implemented inside a browser-based pinball machine to represent real-time merchant sales and celebrate milestones. Built with three.js and react-three-fiber, the experience runs at 120fps, uses Server-Sent Events for order arcs and live metrics, includes a 128x32 shader-driven dot-matrix display, and supports AR through react-three/xr. For performance, the team simulated pinball physics in 2D with Rapier2D and used raycasts for ramps and elevation, reducing the physics step from 2ms to 0.2ms. The scene also includes interactive mini games, infrastructure statistics, Easter eggs, and milestone-triggered reactions, while Apache FlinkSQL pipelines process event streams behind the commerce visualizations. The globe was also displayed on the Exosphere in Las Vegas for the third consecutive year.
Slack's Security Engineering team handles billions of daily security events and needed a reliable way to streamline on-call alert triage. An initial prototype relying on a single 300-word prompt produced inconsistent results and frequently reached spurious conclusions without properly challenging assumptions. To gain precise control, the team decomposed the workflow into chained model invocations with structured JSON outputs organized across three agent personas: a Director, four domain experts, and a Critic. Domain experts gather raw evidence through tool calls, the Critic evaluates finding quality and synthesizes a timeline, and the Director steers investigation phases using tiered model costs. The multi-agent system enables engineers to supervise investigations via a real-time dashboard while uncovering emergent issues like credential exposures across process ancestry chains.
Transformers v5.0.0rc-0 introduces major architectural updates focused on simplicity, training, inference, and ecosystem interoperability across modern AI workflows. The release adopts a modular modeling approach and centralizes attention implementations into a unified AttentionInterface abstraction to reduce contribution and code review overhead. Support for Flax and TensorFlow is officially sunset in favor of focusing on PyTorch as the primary backend, while tokenization is standardized around the tokenizers library. For execution workloads, v5 adds native continuous batching, paged attention mechanisms, and a dedicated transformers serve OpenAI-compatible serving system. Finally, weight loading is refactored to make low-precision quantization a first-class citizen alongside broad interoperability with formats such as GGUF, MLX, and TorchAO.
For the 2025 NYC marathon weekend, Shopify and Endorphins Running built a gamified treadmill that awarded in-store credit for maintaining a self-selected pace. Participants had 30 seconds to reach their target, then earned credit for each second spent within a defined pace zone, with a personalized barcode receipt redeemable through a Shopify POS UI extension. The implementation used a curved, motorless TrueForm Trainer, FTMS messages, a Python relay, Socket.IO, a local Remix application, receipt printing, and a production-hosted POS integration. Interval timestamps were normalized because treadmill messages arrived irregularly, while a state machine coordinated warm-up, gameplay, operator controls, database updates, discounts, and printing. The resulting experience attracted new customers, with 63% of participants identified as new customers, and its patterns could support other sensor-driven in-store incentives.
The best engineering reads, once a week.
