Loading…
Latest reads
Every post, summarised
Grounded summaries of engineering blogs, newest first. Each links to the original.
- 4,671 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
The Companions to Come
JetBrains is extending Kotlin’s companion mechanism with experimental companion blocks and companion extensions in Kotlin 2.5.0. Companion blocks replace the object keyword with a companion block, compiling members as static members on the JVM. Companion extensions allow adding class-level members to any type, even types the developer does not control. These features improve multiplatform interoperability by enabling expected companion block members to be actualized using Java static members. Companion objects remain fully supported and are still required when the companion must implement an interface, but companion blocks are recommended for new code.
How Etsy gets its mobile apps ready for peak traffic
Mobile apps cannot be reverted after release, so Etsy’s peak traffic preparation focuses on observability and mitigation decisions made months in advance rather than capacity scaling during the event. The company runs a code slush with three phases: mindful merging in mid-October, infrastructure fortification, and peak requiring senior sign-off for any change. To avoid tooling disruption, Etsy ran both legacy and new crash reporters simultaneously through a dual-reporting layer, letting engineers use the tool they knew and providing comparison data to eventually sunset the old platform. Before peak, each crash-prone feature is ensured to have a remote flag that disables the failing code path without an app store release. Crash rate is translated into an estimate of lost orders via business analysts, making technical health discussable with teams and the CTO.
Augment Voice Calls with Twilio Conversation Intelligence Using Node.js
Twilio Conversation Intelligence, Conversation Orchestrator, and Conversation Memory together analyze voice calls for a Node.js voice agent built with Conversation Relay. After a call, Twilio sends a webhook to /intelligence-results containing a call summary, sentiment analysis, and script adherence for categories like introduction with the required phrase “Thanks for calling Owl Air! I’m Hoot.” The developer creates a Memory Store and Conversation Configuration, then an Intelligence rule selecting Sentiment, Summary, and Script-Adherence operators triggered at conversation end. A Node.js handler extracts the data and persists it to a SQLite database using tables for intelligence_results, operators, and operator_script_adherence_categories. Testing involves calling the Twilio number and verifying the summary, sentiment, and script adherence records in the database.
Stripe’s Payment Method Factory: Orchestrating agents for repeated, custom integrations
Stripe offers over 125 different payment methods globally, each requiring integrations that previously took up to six months because teams started from scratch. They hypothesized that reusable prompts with hardening could reduce effort, and a bake-off showed vanilla Claude Code took 20 days versus 4 days with their prompts. The resulting factory has created three new payment method integrations and migrated ten existing ones to a modern stack, reducing timelines from six months to two to six weeks. The factory also uses code-based orchestration, continuous knowledge loops where agents suggest prompt improvements, and agents testing their own code against sandbox environments. The factory’s approach has since been extended to Stripe’s tax and verification teams for building their own connectors.
Seven Architectural Readiness Checks Before Production Launch
Auth0’s free tier supports up to 25,000 MAUs for MVPs, but teams must complete seven architecture checks before production launch to avoid blockers. The checks cover Auth0 Organizations for multi-tenancy, Enterprise Connections for SSO, Custom Domains, JIT hash migration, Fine-Grained Authorization, MFA factor progression, and tenant lifecycle management. The free plan caps Organizations at five, Enterprise Connections at one plus unlimited Okta, and MFA at passwordless and passkeys only. Upgrading to B2B Essentials or Professional unlocks unlimited organizations, up to five enterprise connections, and advanced MFA including TOTP, WebAuthn, push, and SMS; Professional also enables Custom Database migration scripts. Teams must add a credit card for Custom Domains, add a secondary admin to prevent tenant deletion after 150 days of inactivity, and note that FGA free trial supports 100 MAUs and 50,000 tuples for prototyping.
On the Effectiveness-Fluency Trade-Off in LLM Conditioning: A Systematic Study
Controlling the output of Large Language Models (LLMs) is a central challenge for their reliable deployment, yet current conditioning methods are often evaluated narrowly on effectiveness without considering generation quality. This study systematically investigates a range of conditioning methods in both concept injection and removal scenarios, including efficient steering, activation steering, prompting, and supervised fine-tuning. The authors find that efficient steering methods frequently achieve their conditioning goal at a steep cost to fluency, degrading generation quality. They identify a critical previously overlooked interaction: activation steering methods are far less effective on instruction-tuned models than on their base counterparts. Simple prompting and supervised fine-tuning are viable options for concept injection but are not as good at concept removal, while cheaply computed textual metrics highly correlate with costly LLM-as-judge scores, providing practical insights for evaluation.
How Atlas Agent Engine Powers MongoDB’s Internal AI Strategy
MongoDB announced the public preview of Atlas Agent Engine, a secure platform for building, deploying, and governing AI agents with built-in memory, retrieval, and open flexibility to choose any LLM or framework. The company validated the platform internally with Holly, a unified agentic workspace that replaces seven disconnected tools for sales reps and is powered by Atlas Agent Engine’s runtime, orchestration, and governance. Compared to manually hopping between tools, Holly cuts the time to research and build an outbound prospecting list by roughly 95%, reducing account prep from hours to minutes. Atlas Agent Engine enforces centralized controls and governance while granting developer autonomy, addressing CIO fears about agents running amok in enterprise systems. It is part of a trio of launches alongside MongoDB 9.0 and Atlas Infinite, giving builders a governed platform to run agents grounded in real-time operational data.
AI Demand is Constant, Unpredictable, and Extreme. MongoDB is Built for It.
AI-driven demand is constant, unpredictable, and extreme, unlike earlier internet and cloud eras where spikes were more predictable. Enterprises need a data layer that can absorb sudden bursts of traffic without re-architecture. MongoDB announced Atlas Infinite, a new deployment option within MongoDB Atlas that independently scales compute and storage within minutes. Atlas Infinite supports replica sets with 10x the data capacity of Atlas Core and delivers 189% more throughput per dollar in internal tests. MongoDB 9.0 was also released, offering up to 35% faster find-one queries and new security features like queryable encryption with prefix, suffix, and substring searches.
Building the Agentic Ecosystem: Partner Updates from MongoDB.local NYC
At MongoDB.local NYC, MongoDB launched Atlas Agent Engine in Public Preview, providing a single foundation for building, deploying, and governing AI agents. Six global systems integrators—Accenture, Capgemini, Cognizant, Infosys, TCS, and Tech Mahindra—are launch partners, integrating the engine into their AI offerings. The platform is model- and framework-neutral, with partners like Arize AI offering trace monitoring for production reliability. MongoDB also announced Devin for MongoDB Modernizations, leveraging Cognition’s AI software engineer to automate legacy code migration while AMP handles data movement. New partnerships with Emergent, Monk.io, and Retool extend MongoDB’s reach into AI application development and internal tools, reinforcing that the agentic era requires an ecosystem of partners with industry expertise.
Context Engineering Has a Retrieval Issue: Introducing rerank-3 and Native Reranking
AI agents require precise context retrieval, not larger windows, and MongoDB’s new Rerank-3 and Rerank-3-lite models outperform Cohere Rerank v4.0 Pro by 2.14% and Qwen3-Reranker-8B by 3.31% overall, with greatest improvements on long documents and code. The $rerank native aggregation stage rescores candidate sets index-free within MongoDB, while Automated Embedding generates and refreshes vectors near-real-time to prevent model version drift. This unified platform eliminates separate vendors and external API calls, supporting lexical, vector, and hybrid search directly against operational data without moving or syncing. The result is simpler retrieval architecture that improved Gravity’s accuracy and cut latency by roughly 50% by better discriminating between strong and weak matches. Retrieval quality forms one layer of MongoDB’s broader agent platform, which also includes performance scaling with Atlas Infinite and agent memory with Atlas Agent Engine.
Open TTS Leaderboard: Scalable Evaluation for Multilingual Text-to-Speech and Voice Cloning
The open-source TTS model landscape has exploded, with over 8,000 models on Hugging Face Hub, yet evaluation methods remain unstandardized and cannot scale. The Open TTS Leaderboard addresses this by using objective metrics such as word error rate (WER), speaker similarity (SIM), and speed (RTFx and TTFA) to evaluate models in hours instead of weeks. It supports multilingual evaluation and voice cloning, providing separate tabs for listening to outputs and comparing streaming performance. Unlike arena-based leaderboards that significantly underrepresent open models due to high hosting costs, this leaderboard prioritizes open-source models. The project encourages community participation through feedback and voting; evaluation scripts will be open-sourced soon, and future updates will incorporate new datasets, languages, and metrics.
Warmup Services Harm Your Deliverability
Warmup services that simulate email engagement harm deliverability because inbox providers detect the pattern and tighten filtering, causing reputation decline that makes recovery harder. Validity’s new Heatwave blocklist identifies domains warmed through synthetic engagement, using signals from its Intelligence Network to automatically list domains crossing a threshold, and over 1.2 million domains have already been listed. The signal is shared with providers including Comcast, Proofpoint, Spamhaus, and SURBL, potentially damaging domain reputation with these providers. A domain on Heatwave receives a permanent record, and even if the domain stops cold outreach, the warming listing stays, making recovery difficult or impossible. Legitimate senders should verify their domain at lookup.validity.tools, obtain proper consent, and increase volume gradually through real engagement, as the domain warms itself through real engagement and there is no shortcut to trust; warmup activity may also run through agencies without the sender’s knowledge.
How Notion built a Custom Agent workflow to keep Academy content current
Notion built a Custom Agent workflow in Notion to keep Academy content current as product changes ship. The system uses two databases: an Academy library mapping the curriculum and a maintenance-tasks database tracking work from each product change. Two Custom Agents handle the work: the Academy Drift Agent compares launch docs against the library and flags affected lessons, while the Academy Drafting Agent drafts approved updates using editorial guidance. MCP connects the workflow to Parta, the e-learning platform, so approved content moves into final QA without manual hand-off. The loop includes human review checkpoints before scope approval and before content moves into Parta, reducing content drift and giving the team hours back each week.
Data visualization best practices: A practical guide to clear, honest, effective charts
The post examines why business intelligence (BI) dashboards lose user trust, even when data is accurate, focusing on how inconsistent metric definitions and opaque data sources cause users to doubt results. Richard Tomlinson argues that AI tools accelerate chart creation but also amplify trust debt if underlying data governance and semantics are weak, since AI can generate many inconsistent charts quickly. He recommends governing data and meaning, preserving provenance, and designing for inspection so visualizations invite investigation rather than presenting unexplained answers. Tomlinson stresses that dashboards should be self-explanatory, traceable, interactive, and context-aware, and that the critical metric for modern BI is ‘time to trust’ not just time to answer. Self-service fails when verifying an AI-generated answer takes longer than asking an analyst, so good visualization must enable inspection and challenge.
How Databricks rolls out frontier models to 12,000 employees on Day 1
Databricks provides 12,000 employees Day 1 access to new frontier models through a pipeline using Unity Gateway for governance, cost management, and observability. New models are immediately made available on an experimental basis with per-user budgets to control costs and mitigate risk from models that may not be on the efficiency frontier. Budgets include monthly maximum, daily runaway limit, quality frontier budget, and experimental budget, with configurations pushed via Unity Gateway CLI running on employee laptops. After three days, Databricks evaluates models using benchmark data, user-reported quality, and cost tracking via OpenTelemetry traces to decide whether to promote the model. Opus 5.5 was promoted as higher quality and lower cost than predecessors, while GPT-6 Sol was included in the smart router due to its cost advantage over GPT-5.6 Sol.
Your data, your storage, your rules: a 2026 guide to storing Unity Catalog managed tables
Unity Catalog managed tables let you control where your data physically resides while keeping it in cloud storage you own, such as S3, ADLS, or GCS, unlike platforms that store tables in provider-controlled storage. You set managed storage locations at the metastore, catalog, or schema level, with the most specific level winning, and can change where new tables land using ALTER CATALOG or ALTER SCHEMA commands. Managed tables use open formats including Iceberg and Delta, and external engines such as Apache Spark, Flink, and Trino can read and write through Iceberg REST Catalog and Unity Catalog open APIs. When converting an external table to managed, Databricks copies the data and transaction log into the managed storage location you have set. This approach enables a single source of truth across analytics and AI workloads while satisfying compliance, cost allocation, and data residency requirements.
Lower the Cost of Building and Running Visual AI Agents with NVIDIA VSS Blueprint 3.3
Vision-language models enable production-scale video understanding, but building maintainable systems that combine ingestion, stream processing, event detection, retrieval, summarization, and reporting with services like Kafka, Redis, and Elasticsearch is challenging. The NVIDIA VSS Blueprint 3.3 introduces the Build Vision Agent skill, which composes multi-workflow applications from a single natural-language prompt using one of four Foundation profiles. It also adds Adaptive EVS, which prunes unchanged video patches via cosine similarity before VLM processing and batches tokens around events. Adaptive EVS cuts alert latency by 17%, delivers 80% fewer VLM input tokens for a 60-minute summary, and enables 46% more concurrent streams on the same GPU. These updates reduce development effort, infrastructure duplication, and operating costs, allowing a single prompt to build a bottling-line agent in under 30 minutes.
7 new Brandwatch AI updates that make your life easier
Brandwatch introduced seven AI-powered updates to help analysts, marketers, and social media managers keep pace with fast-moving online conversations. Iris AI features like Query Writer and Query Fixer streamline building comprehensive research queries by allowing a user to describe a topic through chat. The Ask Iris AI chat on the homepage and dashboards delivers instant summaries and topic breakdowns without requiring a pre-built query. Enhanced Alert and Signal emails now include AI-generated summaries so users can assess breaking stories or issues without reading individual mentions. Other updates include AI-generated categories for segmenting datasets, industry benchmarks for social performance, semantic search for YouTube creator discovery, and automated message classifiers in Engage.
NVIDIA Kumo Tabular Sets a New Accuracy-Efficiency Frontier for Tabular Prediction
NVIDIA Kumo Tabular is an open foundation model for tabular classification and regression that predicts labels in a single forward pass without training, tuning, or feature engineering. It uses a Transformer architecture with column, row, and in-context attention, including length-aware attention temperature to maintain sharp attention on large tables. Pretrained entirely on artificial tables generated from structural causal models with realistic imperfections such as missing values, coarsened features, and heavy-tailed targets, it comes in three sizes (28M to 215M parameters) and handles missing values without imputation. On the TabArena, BeyondArena, TALENT, and ScoringBench benchmarks, Kumo Tabular achieves top rankings and establishes a new accuracy-efficiency frontier, running 17x faster than LimiX-2. The model is available on Hugging Face under the OpenMDW-1.1 license and runs via NVIDIA’s open-source structured-data-models library.
Build adaptive AI interfaces with the AG-UI protocol, agent swarms, and Nova Act on AWS
Static interfaces cannot adapt when generative AI produces variable outputs, such as a medical scan showing one fracture versus twenty ambiguous regions requiring expert review. The solution combines three AWS technologies: the AG-UI protocol for standardized agent-to-UI streaming via Server-Sent Events, the Strands Agents SDK Swarm pattern for peer-to-peer agent collaboration, and Amazon Nova Act for browser-based legacy system integration. AG-UI removes custom WebSocket formats by defining typed events that both agent frameworks and frontends implement as a universal contract. Strands swarm agents debate hypotheses and iteratively refine findings, producing explainable results visible in real time, while Nova Act navigates login screens and fills forms on systems without APIs. A complete radiology assistant walkthrough demonstrates reduced interface development time and HIPAA-compliant data handling for medical imaging.
Top topics
- Architecture834
- Performance816
- LLMs660
- Machine Learning622
- Open Source563
- AI Agents553
- AI470
- Developer Experience448
Weekly digest
The best engineering reads, once a week.