Loading…
Browse by type
Explainer reads
Explainer posts on Yomu, summarised newest first.
- 1,315 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.
Explainer posts
Kaizen for the AI era: How small improvements build smarter support
The post presents Kaizen as a structured approach to continuous improvement, centered on small changes, immediate iteration, and participation from people closest to the work. At Fin, this philosophy is applied to Agent Fin through the Fin Flywheel: teams train it on complex queries, test simulated conversations, deploy it across channels, and analyze performance with AI-powered insights. Each interaction feeds a repeatable loop rather than a one-time launch, while Human Support representatives examine escalations, ask why Fin could not resolve them, and identify content, process, or tooling fixes. A lightweight AI-powered logging process captures suggestions in the moment, enabling subject matter experts or frontline teams to implement changes quickly; together, the two systems make continuous learning an ingrained capability and are presented as a source of competitive advantage.
Money Forward brings Cursor’s coding agents to product, design, and QA
Money Forward expanded Cursor coding agents beyond engineering to product, design, and quality assurance after developers began saving an estimated 15–20 hours per week. Adoption among engineers rose 30% within a week, and the company now reports more than 1,000 daily users; engineering examples include Rails optimization, Terraform deployments, and Vue-to-React migrations. For the company-wide rollout, its MEPAR department chose Cursor for minimal setup, visual browser capabilities, a unified workspace, model-agnostic asynchronous cloud agents, and context retrieval across complex codebases. QA uses MCP-connected Jira and Notion materials to generate test cases and Playwright scripts, reducing test-generation time by 70%, while product managers inspect repositories for requirements and designers prototype against live frontends and product analytics.
State of Open Source on Hugging Face: Spring 2026
The post examines how open source AI on Hugging Face changed over the past year across competition, geography, technical trends, and emerging communities. It combines Hugging Face and community-contributed metrics to assess users, models, datasets, downloads, repositories, and specialized sub-ecosystems. In 2025, the platform reached 13 million users, more than 2 million public models, and over 500,000 public datasets, while the top 200 models represented 49.6% of downloads and China surpassed the U.S. in monthly and overall downloads. The analysis also describes rising participation by independent developers, increased Chinese releases, and active communities in robotics and science, framing open source AI as overlapping ecosystems rather than a uniform market.
Behind the Scenes: How Maintaining Cloud Native Buildpacks Powers Platforms Like Heroku
Maintaining the pack CLI and Cloud Native Buildpacks (CNBs) is presented as invisible infrastructure work supporting platforms including Heroku, Google Cloud, OpenShift, VMware Tanzu, and internal systems. Over the last 14 months, maintainers shipped 27 releases—11 for pack and 16 for buildpacks/github-actions—reviewed more than 65 community pull requests, and delivered Execution Environments and System Buildpacks. The work also covered Windows CI migration, a docker/docker to moby/moby client upgrade, FreeBSD binaries, multi-architecture publishing, and a Platform API 0.14 lifecycle-restorer fix. System Buildpacks address platform composition and defaults, while Execution Environments support consistent configurations across development, CI, and production. The post argues that company-funded maintainers and CNCF collaboration turn production requirements into shared infrastructure, with planned build observability, OCI image annotations, and Kaniko removal as further examples.
5 Career Myths From Women in Engineering
Three engineering leaders at Two Sigma—Angela Wang, Cecilia Ye, and Mae Santos—challenge conventional career progression models by examining five persistent industry myths. Diverse transitions across civil engineering, enterprise architecture, and customer-facing solutions architecture supplied foundational skills for modern roles in feature engineering, reliability engineering, and real-time trading optimizers. The leaders emphasize that deep domain expertise stems from direct proximity to an active system rather than cumulative years of tenure. Beyond core programming capabilities, proactive contributions such as upgrading operational standards and cultivating peer relationships drive career opportunities and leadership recognition. Adapting to emerging technologies and maintaining consistent execution allows engineers to build credibility across evolving technical environments.
Training Composer for longer horizons
Composer is trained for long-horizon coding tasks using self-summarization, allowing reinforcement-learning trajectories to exceed the model’s context window. When a fixed token trigger is reached, Composer receives a synthetic summarization query, uses scratch space to produce a condensed context, and resumes with the summary plus conversation state; training rewards every token in the chained rollout with the final outcome. Against a tuned prompt-based compaction baseline, self-summary reduced compaction-related error by 50% on CursorBench at both 80k and 40k triggers, while summaries averaged about 1,000 tokens instead of more than 5,000 and reused the KV cache. An early Composer checkpoint solved Terminal-Bench 2.0’s make-doom-for-mips after 170 turns, summarizing more than 100,000 tokens into roughly 1,000 tokens of retained information.
AI is redrawing the database market
Emerging artificial intelligence workloads are fundamentally transforming data platform requirements across real-time analytics, data warehousing, and observability. Conversational analytics and autonomous agents replace periodic batch queries with rapid bursts of concurrent, low-latency requests, exposing the architectural limits of traditional cloud data warehouses and standalone transactional databases. To resolve these constraints, architectures are converging on engine-level integrations between Postgres for transactions and ClickHouse for analytical scale, while unifying operational observability and business event storage. ClickHouse also incorporates turnkey agent interfaces through its acquisition of LibreChat alongside dedicated execution tracing from tools like Langfuse. These combined capabilities ensure organizations can reliably support interactive agentic workflows without incurring severe latency penalties or compounding infrastructure costs.
AI doesn’t always generate perfect ClickHouse schemas (yet)
LLMs can generate syntactically valid ClickHouse schemas whose advanced choices are poorly matched to a workload. The post examines recurring pitfalls including query-driven partitioning, per-column codecs, premature projections, materialized-view sprawl, JSON configurations, and forced deduplication with OPTIMIZE TABLE ... FINAL. It explains that partitions primarily support data management, incremental materialized views add work to every insert, and ReplacingMergeTree deduplicates during background merges rather than at insertion. The recommended method is to begin with a simple MergeTree or ReplacingMergeTree, a well-chosen ORDER BY, default compression, and no optional structures, then measure production behavior before adding complexity or seeking human expertise for high-scale, interconnected designs.
Shopify’s journey to faster breadth-first GraphQL execution
Shopify describes how high-cardinality, deeply nested GraphQL queries exposed execution overhead beyond data loading, with field resolvers assembling responses consuming much of request time. Its GraphQL Cardinal engine replaces conventional depth-first traversal with breadth-first execution, resolving each selected field once across an aggregated set of objects and reducing repeated field-level work. For large list queries, Shopify reports up to 15x faster execution, 90% less memory use, and reductions of many seconds in P50 latency. The migration included a tuned interpreter, cheaper tracer behavior, shadow verification, benchmarks, and ongoing conversion of tens of thousands of legacy resolvers, while future work includes asynchronous patterns and lower-level C bindings.
Ulysses Sequence Parallelism: Training with Million-Token Contexts
Ulysses Sequence Parallelism addresses the memory and compute pressure of training language models on sequences extending beyond tens of thousands of tokens, where attention remains quadratic in sequence length even with FlashAttention. It shards tokens across GPUs, projects local queries, keys, and values, then uses two all-to-all operations to exchange data so each GPU computes a subset of attention heads before restoring sequence-sharded outputs. The post describes integrations with Accelerate, the Transformers Trainer, and TRL's SFTTrainer, including variable-length handling and weighted loss aggregation for uneven valid-token counts. In reported four-GPU tests, SP=4 reduced per-GPU memory sufficiently for 96K-token training on H100 80GB GPUs, reached 13,396 tokens per second at 64K, and matched non-SP canonical token-normalized loss within 0.000005 maximum absolute difference.
Working at the intersection of data and AI with Kenza Boulisfane
Thumbtack software engineer Kenza Boulisfane develops an artificial intelligence tool called the Marketing Analytics Agent to democratize access to complex cross-channel marketing data. Non-technical staff across Data Science, Growth, Brand, and Product can ask natural language performance queries without requiring SQL expertise or manual reporting. A primary technical challenge involves unifying fragmented data across multiple advertising platforms that define metrics differently while maintaining data reliability. The system interprets natural language queries, analyzes underlying performance metrics, and translates results into actionable, data-backed recommendations for next steps. Boulisfane also notes that virtual work environments enhance collaboration by encouraging clearer documentation, intentional communication, and focused individual productivity.
How Chronicle hit #1 on Product Hunt using Notion
Chronicle’s Product Hunt launch aimed for a few hundred upvotes but reached number one and generated a waitlist of more than 100,000 signups. The remote team used Notion as a launch “mission control,” expanding an initial planning page into a database with status and due-date properties, assigned owners, collaborator tags, asset links, social copy, and calendar views. The shared hub coordinated feature timelines, asset publication, emails, LinkedIn posts, announcements, pre-launch instructions, and real-time launch-day updates without losing a single source of truth. Templates turned tasks into reusable pages containing creative files, drafts, and strategy notes, while the broader workspace also stored customer interview transcripts and marketing work. The team attributes the result to early preparation, careful copy and assets, coordinated support from its ecosystem, and treating the launch as a company-wide event; it says the process enabled speed, alignment across time zones, and documented repeatability.
Transformation in action: When support becomes the blueprint for company-wide AI
The post describes how businesses are extending AI beyond customer support across the customer lifecycle, with support teams increasingly positioned to lead that work. Research cited in the 2026 Customer Service Transformation Report says 52% of respondents plan to scale AI to other departments in 2026, while 32% say customer service teams lead their AI transformation strategy. WHOOP deployed Fin on its Join page after prospective buyers faced waits of more than 10 hours; Fin resolved 84% of inbound questions and helped drive a 130% increase in attributable sales. The post warns that isolated departmental agents can fragment experiences, and presents a unified Customer Agent with shared memory and business knowledge as the intended direction. It argues support can provide shared standards, guardrails, operating practices, and implementation expertise as AI expands into sales and other functions.
How technical support at Cursor uses Cursor
Cursor’s technical support team treats customer investigations as research problems, using a single session to combine code, logs, team knowledge, and past conversations. Engineers typically start in Ask Mode, use semantic search across a locally indexed codebase and documentation, and group related repositories with multi-root workspaces. MCP servers bring customer data, Datadog logs and traces, Slack and support history, runbooks, account details, and ticketing context into those investigations; Linear MCP turns evidence into escalations, while a Slack-mentioned cloud agent can open documentation pull requests. Slash commands, Rules, Skills, and parallel subagents automate repeated work, including failure analysis, known-issue searches, ticket writing, and customer-response drafting. The team reports that more than 75% of support interactions run through Cursor, with stated throughput gains of 5–10x and estimated productivity improvements of up to an order of magnitude.
How we built security into Custom Agents
Custom Agents were designed for collaborative workspaces where useful access must be balanced against dangerous actions. They use a build-from-nothing model with no default read, write, or interaction permissions, then add resource-level controls such as page-level access, Slack “read and reply,” email confirmation, and selected MCP tools. Runtime safeguards combine permission controls with prompt-injection mitigations, monitoring of external data, warnings, owner confirmation for risky actions, and remediation such as deleting an incorrect Slack message. Alpha testing across Notion and customers produced more than 3,000 internal and 25,000 customer agents, and exposed overly broad Slack write access that could reach #general. That finding led to the custom permission and reinforced the case for first-party integrations, while planned work includes admin-approved broader scopes, Workers integrations, and additional permission modes.
Transformation in action: How AI is evolving support careers
AI is changing customer service operations by shifting human agents away from queue-level work such as triage and FAQs toward training systems, complex escalations, and strategic improvement. In research from The 2026 Customer Service Transformation Report, 45% of teams updated job descriptions with AI-related responsibilities, 40% said agents focus more on training AI systems, and 27% primarily handle complex escalations and edge cases. Interviews with 166 customers found nearly 95% reporting meaningful workflow changes, while 83% saw roles become more strategic and supervisory; mature teams also reported less time handling support volume. New positions including AI knowledge managers and conversation designers are emerging, while existing staff can move into AI-focused work such as optimizing knowledge, monitoring outputs, and improving customer journeys. The source recommends transparent communication, agent participation, dedicated time outside inbox, and metrics such as resolution rate as teams build operating models with AI at their core.
The third era of AI software development
The post describes a third era of AI-assisted software development, in which autonomous agents handle larger tasks over longer timescales while developers define problems and review results. It traces a progression from Tab autocomplete, to synchronous prompt-and-response agents, and then cloud-based agents running on separate virtual machines. These agents can iterate and test for hours, returning logs, video recordings, and live previews that make parallel work and artifact-based review practical. Cursor reports that 35% of its internally merged pull requests are created by agents operating autonomously in cloud VMs, and that agent users now outnumber Tab users two-to-one after usage grew more than 15x in a year. The post says broader adoption still depends on reliable tests, environments, tools, and context, while developers shift toward decomposition, review, and feedback rather than line-by-line guidance.
Mixture of Experts (MoEs) in Transformers
Mixture of Experts (MoEs) in Transformers let a Transformer retain its backbone while replacing selected feed-forward layers with routed expert sub-networks, allowing total model capacity to exceed the active parameters used per token. The post explains why sparse models can reduce inference cost and memory pressure, then focuses on making them first-class in Transformers. Its weight-loading refactor converts independently serialized expert tensors into packed runtime layouts through composable WeightConverter operations and lazy materialization. The Experts Backend supplies eager, batched_mm, and grouped_mm execution strategies, while expert parallelism shards experts across devices and aggregates partial outputs. Training support uses grouped GEMM and custom Triton plus LoRA kernels, with reported improvements of approximately 12× speed, over 35% VRAM reduction, and roughly 6× longer context.
The generative recommender behind Shopify's commerce engine
Shopify describes a foundational generative recommender that predicts next products, and in some contexts ads, from buyer event sequences spanning searches, views, add-to-carts, favorites, and purchases. The system uses an autoregressive model with causal masking, time-aware attention combining RoPE-inspired rotary encoding with relative attention bias, and sampled softmax with shared and positive-aware hard negatives. Built on HSTU, it combines richer activity data, ensemble-focused training for incremental recall, and optimized CUDA kernels; the full training pipeline reached up to 7.3x the speed of a baseline implementation. In an online test of an August model version, relative shop orders rose 0.94%, high-quality click-through rate rose 5%, conversion rate rose 0.71%, and final served product recall at 2 rose 4.8%.
How Notion uses Custom Agents
Notion describes how Custom Agents are being used internally to automate repetitive questions, triage incoming work, and support communications, security, recruiting, and office operations. Agents are configured by describing a workflow and adding a trigger or schedule; they operate across Notion, Slack, Mail, Calendar, and other tools while using existing knowledge for context. Examples include a CX agent that searches the CX Knowledge Base and enablement docs, a Feedback Router that classifies Slack feedback and creates tasks, and Wilbur, which triages web issues and tags the right person. The company says these workflows make knowledge available beyond individual experts, reduce manual routing and response delays, and shift attention toward complex problems and creative work.
Top topics
- Architecture830
- Performance812
- LLMs648
- Machine Learning617
- Open Source561
- AI Agents540
- AI454
- Developer Experience446
Weekly digest
The best engineering reads, once a week.