---
title: "Latest reads"
description: "The engineering internet, summarised so you can actually read it."
---

# Latest reads
> The engineering internet, summarised so you can actually read it.

## Articles

### [Automated merchant review summary system with integrated feedback](https://yomu.fyi/post/automated-merchant-review-summary-system-with-integrated-feedback.md)
- Company: [Grab](https://yomu.fyi/company/grab.md)
- Author: Chengju Zhou
- Published: Sep 25, 2026
- Type: Problem & solution

The system uses representative sampling, large language model (LLM) summarization, automated quality checks, and consumer feedback to generate concise summaries from written merchant reviews. Consumers can scan an overall summary or focus on specific topics such as taste, packaging, and portion size, while merchants can identify recurring themes without reading every comment. The pipeline calculates the merchant’s rating distribution, uses a sentiment model to score reviews, and applies stratified sampling to select a representative subset before sending them to an LLM for summary generation. A separate LLM validates that each claim in the generated summary is supported by the source reviews, and summaries that fail this automated assessment are withheld from publication to reduce unsupported claims. The system regenerates summaries when new reviews or negative consumer feedback reach configured thresholds, and the feedback-driven regeneration includes anti-abuse controls to maintain trustworthiness.


### [How to handle real-time interruptions in your AI voice agent](https://yomu.fyi/post/how-to-handle-real-time-interruptions-in-your-ai-voice-agent.md)
- Company: [Twilio](https://yomu.fyi/company/twilio.md)
- Author: Jesse Sumrak
- Published: Sep 25, 2026
- Type: Tutorial

Real-world AI voice agent calls are messy, with background noise, overlapping speech, and callers interrupting mid-sentence. Twilio Conversation Relay handles interruptions through attributes like interruptible, which controls whether caller input stops the agent’s speech, and ignoreBackchannel, which filters out short backchannel phrases. Background noise that sounds like speech can cause false interruptions and garbled transcripts; Twilio’s testing found Deepgram Flux produced zero transcription failures under combined noise, while a tuned Nova-3 setup also succeeded. Turn detection uses either a traditional silence timer or Deepgram Flux’s fused model, which reduces false interruptions by roughly 30% and trims response latency. When a caller interrupts, the app receives an interrupt message with the exact text played before cutoff, allowing it to trim the LLM’s conversation history so the model only remembers what the caller heard.


### [How to Build an RCS Business Messaging Campaign with Twilio in C#](https://yomu.fyi/post/how-to-build-an-rcs-business-messaging-campaign-with-twilio-in-c.md)
- Company: [Twilio](https://yomu.fyi/company/twilio.md)
- Author: Amanda Lange, Dhruv Patel
- Published: Sep 25, 2026
- Type: Tutorial

RCS Business Messaging upgrades SMS with branded conversations featuring images, suggested replies, and read receipts delivered natively on the recipient’s phone. Twilio Programmable Messaging supports RCS via the same API used for SMS, allowing reuse of existing integrations. This tutorial teaches building an RCS campaign in .NET 10, requiring a Twilio account, registered RCS Sender, Messaging Service, ngrok, and a code editor. The process includes creating a rich card template with hero image, dynamic placeholders, and three buttons (Shop the sale, Send promo code, Unsubscribe), then broadcasting personalized messages via the Twilio helper library while capturing status and replies through webhooks exposed by ngrok. Test devices receive messages without waiting for full RCS sender approval, and the server terminal outputs inbound replies and status callbacks in real time.


### [The #1 AI behavior hurting your customers’ experiences](https://yomu.fyi/post/the-1-ai-behavior-hurting-your-customers-experiences.md)
- Company: [Twilio](https://yomu.fyi/company/twilio.md)
- Author: Jesse Sumrak
- Published: Sep 25, 2026
- Type: Explainer

91% of brands report a drop in customer satisfaction from AI, and the top behavior causing this is losing context when customers change channels, cited by 40% of businesses. Three of the four main behaviors are context-related, with lack of empathy at 39%, inability to handle exceptions at 38%, and failing to understand at 36%. The infrastructure problem includes session boundaries, identity mismatches, channel-specific tooling, and batch timing that prevent context from following the customer, causing 74% of consumers to repeat themselves and 71% to abandon conversations. Twilio’s structural solutions—Conversations, Conversation Memory, and Conversation Orchestrator—attach context to the customer rather than the session and recommend starting with the chat-to-voice transition. To measure improvement, track repeat-explanation rate after a channel change, recognition rate, and abandonment at transition points.


### [Welcoming Allie Sperry, our new Customer Success Engineer](https://yomu.fyi/post/welcoming-allie-sperry-our-new-customer-success-engineer.md)
- Company: [Resend](https://yomu.fyi/company/resend.md)
- Author: Allie Sperry and Brian Kerr
- Published: Sep 25, 2026
- Type: Announcement

Resend has hired Allie Sperry as a Customer Success Engineer to support its growing customer base, bringing experience from Litmus in technical support and Customer.io as a deliverability consultant. Sperry describes herself as an email nerd who enjoys helping developers and builders navigate the complexities of email at scale, and she discovered Resend while building an email sending app for fun using AI tools. She got into software through her older brother’s influence and early experiments with Myspace layouts, which taught her to break down and rebuild code. Her favorite tool is Obsidian for daily notes, and she uses a refillable notebook to draft ideas before uploading photos to Claude or digital notes. Her advice to ambitious software engineers is to focus on the desire to learn rather than knowing everything, and to avoid comparing one’s journey to others, as unique backgrounds create unique work.


### [What is AI agent orchestration? How it works in 2026](https://yomu.fyi/post/what-is-ai-agent-orchestration-how-it-works-in-2026.md)
- Company: [Twilio](https://yomu.fyi/company/twilio.md)
- Author: Jesse Sumrak, Luke Morgan
- Published: Sep 25, 2026
- Type: Explainer

AI agent orchestration coordinates multiple AI agents working on a single task, deciding routing, carrying context, resolving contradictions, and escalating to humans when needed. It operates at two levels: the agent level, where frameworks like LangGraph route between specialized agents, and the conversational AI level, which preserves customer identity and history across Voice, SMS, and WhatsApp channels. Orchestration comprises four jobs: routing, shared memory and state, conflict resolution, and human escalation, with parallel execution requiring robust memory management. Twilio’s Conversation Orchestrator provides a shared conversation record as a system of record, while Conversation Memory extracts observations and resolves conflicts by updating records with the most recent version. The FAQ section addresses differences from workflow automation, comparison criteria for orchestration tools, and the mechanism for agent-to-human handoffs within the same session without callbacks.


### [Same Query, Same Score: Consistent Ranking with StableTfl in Atlas Search](https://yomu.fyi/post/same-query-same-score-consistent-ranking-with-stabletfl-in-atlas-searc.md)
- Company: [MongoDB](https://yomu.fyi/company/mongodb.md)
- Published: Sep 25, 2026
- Type: Explainer

Paginated search in Atlas Search can show duplicate or skipped results across pages because BM25 scores drift between replicas due to changing corpus statistics. The usual workarounds like sticky routing or index snapshots require extra state and are cumbersome. The solution is StableTfl, a scoring function that uses only term frequency and document length, with term length as a proxy for rarity based on Zipf’s brevity law, eliminating corpus statistics and requiring no extra state. StableTfl is contributed to Apache Lucene and is available as a per-field similarity option in Atlas Search. Benchmarks on BEIR show StableTfl achieves 0.315 NDCG@10 compared to BM25’s 0.346, a 9% relative drop, making it suitable for paginated search, RAG pipelines, and multi-replica deployments where consistency matters more than peak relevance.


### [Stop Building MFA from Scratch (And What to Do Instead)](https://yomu.fyi/post/stop-building-mfa-from-scratch-and-what-to-do-instead.md)
- Company: [Auth0](https://yomu.fyi/company/auth0.md)
- Author: Alisha Tingle
- Published: Sep 25, 2026
- Type: Explainer

Building multi-factor authentication (MFA) in-house is a much larger project than teams expect, requiring authenticator app integration, QR code generation, secure backup recovery codes, and edge cases like lost phones. Auth0 positions its MFA offerings as a way to offload that work so developers can focus on core product features. The company’s paid plans include MFA directly, with Pro MFA covering standard authenticator apps in B2C and B2B Essentials plans. Enterprise MFA adds WebAuthn, push notifications, SMS, and voice, available as an add-on to B2B Essentials or included in Professional tiers. Auth0 argues that using its MFA helps teams pass compliance, unblock enterprise deals, and avoid weeks of building login infrastructure.


### [Running open-Jev in SQL on Databricks](https://yomu.fyi/post/running-open-jev-in-sql-on-databricks.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Cyrus Cowley, Tejas Sundaresan, Hanlin Tang, Anshul Gupta, Julia Powell
- Published: Sep 24, 2026
- Type: Tutorial

System One decision models such as Jev produce well-calibrated decisions from discrete options and are fast and cheap for large-scale applications, with potential use cases ranging from analyzing customer support transcripts to applying complex decisions at scale. Open-weight versions like SemIf-OpenJev are available, and Databricks enables serving them on governed data using serverless GPUs via AI Runtime, which provides on-demand GPU compute without managing infrastructure. The workflow is packaged in an importable notebook that downloads the model files, logs and registers the model using Express Deployments, and creates a GPU Model Serving endpoint automatically. The endpoint can be called from SQL via ai\_query, which supports arbitrary custom model APIs, allowing structured request formats directly from SQL to return selected classifications and option probabilities as structured columns. The example classifies hotel reviews as good or bad, and users can import the notebook, select Serverless GPU, and run all to get started.


### [Meet (again) Max Schoening, Notion's new CTO](https://yomu.fyi/post/meet-again-max-schoening-notion-s-new-cto.md)
- Company: [Notion](https://yomu.fyi/company/notion.md)
- Author: Ivan Zhao
- Published: Sep 24, 2026
- Type: Announcement

Notion appointed Max Schoening as CTO, reflecting its ethos of merging technology with liberal arts and integrating engineering and design as one job. Schoening, who joined last year, led product and design and shipped significant launches including Custom Agents for everyday knowledge workers and the Developer Platform allowing extensions. His background includes early design at Heroku, Cloud Run at Google, and six and a half years at GitHub working on Issues, Pull Requests, Actions, and cloud development environments used by millions. He advocates open customer-first platforms, and Notion’s open, agent-neutral context aims to benefit customers from small coffee businesses to large global enterprises balancing innovation, token costs, and governance at scale. As a two-time founder, Schoening embodies the multidisciplinary approach Notion values, and the company hires people whose work cuts across traditional discipline boundaries.


### [Deploy and manage coding agents at scale with the Unity Gateway CLI](https://yomu.fyi/post/deploy-and-manage-coding-agents-at-scale-with-the-unity-gateway-cli.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: The Databricks AI Product and Engineering Team
- Published: Sep 24, 2026
- Type: Announcement

Organizations face a challenge as new frontier models appear roughly every five days, making it difficult to balance flexibility with governance. Databricks introduces the Unity Gateway CLI, which lets admins centrally configure approved coding agents, models, MCP servers, skills, and spending policies. Developers launch any approved agent with a single ug command, and the CLI handles authentication and applies the published settings. Features include Smart Routing that selects cost-appropriate models per task, budget-aware defaults that switch to lower-cost options as spending thresholds are reached, and tracing to capture tool calls and skill invocations for waste analysis. In internal use, the system processed over 61 billion input tokens across roughly 360,000 requests, and tracing helped identify bugs that saved an estimated 1.2 million per year.


### [How Intelligent Load Shedding Prevents Cascading Failures in Tier-0 Systems](https://yomu.fyi/post/how-intelligent-load-shedding-prevents-cascading-failures-in-tier-0-sy.md)
- Company: [Salesforce](https://yomu.fyi/company/salesforce.md)
- Author: Scott Nyberg
- Published: Sep 24, 2026
- Type: Problem & solution

Salesforce’s Cloud Atlas team operates a globally distributed identity data store that must maintain five nines of availability, roughly five minutes of downtime per year. The team redesigned service protection after per-instance rate limiting proved insufficient under autoscaling and increasingly bursty, unpredictable agent-driven traffic. The new approach combines intelligent load shedding, which monitors queue time as an early indicator of system pressure before error rates spike, with coordinator-free global quota management. Servers independently measure and share customer usage to throttle noisy tenants without a centralized coordinator, preventing one customer’s surge from affecting others. This design prevents cascading failures by shedding lower-priority work before overload spreads across dependent services, ensuring graceful degradation rather than widespread outage.


### [From Dockerfile to Kit: the Docker Sandboxes Kit Specification](https://yomu.fyi/post/from-dockerfile-to-kit-the-docker-sandboxes-kit-specification.md)
- Company: [Docker](https://yomu.fyi/company/docker.md)
- Author: Jin Kim
- Published: Sep 24, 2026
- Type: Announcement

The Docker Sandbox Kit Specification v3 defines how an agent declares the networks, credentials, and volumes it needs, so these grants travel with the artifact rather than living in shell history or dashboards. A Kit is an ordinary OCI image whose manifest carries a descriptor annotation vnd.docker.sandbox.kit.descriptor, so it builds with docker buildx, pulls with docker pull, and gets scanned and signed by existing tooling. Capability types like network-policy@2 and credential@1 are versioned independently, and each normative statement in the specification is covered by a conformance check or a written waiver. Two Kit types exist: a workload supplies the root filesystem, while a mixin adds overlays such as a CLI with its network rule; the runtime rejects required capabilities it cannot satisfy. Composition uses strict provides/requires resolution, so authority changes appear as diffs, and a conforming runtime can gate upgrades that widen the grant set.


### [Efficient MoE Training for Biological Foundation Models](https://yomu.fyi/post/efficient-moe-training-for-biological-foundation-models.md)
- Company: [NVIDIA](https://yomu.fyi/company/nvidia-developer-blog.md)
- Author: Michelle Horton
- Published: Sep 24, 2026
- Type: Tutorial

Mixture-of-experts (MoE) architectures scale model capacity more efficiently than dense transformers by activating only a subset of experts per token, but naive implementations suffer from fragmented expert computation, routing overhead, and memory pressure. NVIDIA Transformer Engine (TE) addresses these bottlenecks with optimized primitives including GroupedLinear for batched expert GEMMs, MXFP8 low-precision training, and a fused GroupedMLP kernel that combines quantization, SwiGLU activation, and routing-weight scaling. The BioNeMo recipe implements these techniques for biological foundation models, using TE’s autocast API for MXFP8 precision and the Sequential API to fuse the gate-up, ScaledSwiGLU, and down projections into a single operation. On eight NVIDIA B200 GPUs, the recipe achieved up to 2.21x the training throughput of the Hugging Face baseline for a Mixtral-8x7B model. The tutorial provides prerequisites, code examples, and configuration commands to reproduce the optimizations.


### [How Cloudflare addressed a cross-tenant data exposure vulnerability in Containers](https://yomu.fyi/post/how-cloudflare-addressed-a-cross-tenant-data-exposure-vulnerability-in.md)
- Company: [Cloudflare](https://yomu.fyi/company/cloudflare.md)
- Author: Hrushikesh Deshpande
- Published: Sep 24, 2026
- Type: Incident / postmortem

Security researcher Oren Yomtov reported a vulnerability in Cloudflare Containers and Sandboxes through the bug bounty program, demonstrating that a Workers Paid account could recover residual disk blocks from previous containers on the same host. The issue arose from Linux device mapper thin provisioning with skip\_block\_zeroing enabled, which left unzeroed 64 KiB blocks when a 4 KiB write triggered allocation, allowing the remaining 60 KiB to retain prior data. Researchers recovered directory structures, database pages, and structurally complete SQLite databases from 18 of 24 placements across four continents, using ext4 checksums to distinguish foreign blocks. Cloudflare removed skip\_block\_zeroing, retired all running container disks, and cleared cached image snapshots created before the mitigation, completing cleanup by September 19. Retained disk-I/O telemetry showed no evidence of malicious exploitation, and the researchers confirmed secure deletion of recovered data.


### [Accelerating vision-language models with LFM2.5-VL-DSpark](https://yomu.fyi/post/accelerating-vision-language-models-with-lfm2-5-vl-dspark.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: xx, Yuri Khrustalev, Leonie Monigatti, Viviana Márquez
- Published: Sep 24, 2026
- Type: Announcement

Liquid AI released an experimental DSpark draft model for their vision-language model LFM2.5-VL-3B. The drafter adds a speculative decoding path that trades a minimal increase in memory footprint for a larger speedup without changing output quality. The 280M-parameter drafter, a 4-layer attention-only transformer, captures the target model’s hidden states at fixed tapped layers to draft a block of candidate tokens. On an M5 Max, decoding runs 2.30x to 3.13x faster by task, with end-to-end latency improvements of 1.56x to 2.62x. The drafter ships with day-one support for llama.cpp, MLX-VLM, and SGLang, and is available on Hugging Face in Safetensors and GGUF formats.


### [Self-encrypting VM images for confidential environments hands on](https://yomu.fyi/post/self-encrypting-vm-images-for-confidential-environments-hands-on.md)
- Company: [Red Hat](https://yomu.fyi/company/red-hat.md)
- Author: Vitaly Kuznetsov
- Published: Sep 24, 2026
- Type: Tutorial

Confidential VM technologies such as AMD SEV-SNP and Intel TDX protect runtime data but leave persistent storage protection to the guest OS. This article demonstrates a method using Fedora Rawhide that combines dm-verity integrity for the immutable base image with a dm-crypt encrypted overlay for mutable parts. The base /usr partition remains verity-protected, while on first boot systemd-repart creates an encrypted root partition with a key sealed to the virtual TPM, ensuring each VM gets a unique key. An overlay filesystem mounts the immutable base under the writable overlay, avoiding a full copy of the base image and reducing boot time significantly in cloud environments. The article also outlines current limitations, including the lack of proof of origin for the overlay partition and the absence of integrity or replay attack protection.


### [Scaling GitOps: The "pull" architecture for global fleets](https://yomu.fyi/post/scaling-gitops-the-pull-architecture-for-global-fleets.md)
- Company: [Red Hat](https://yomu.fyi/company/red-hat.md)
- Author: Jann Fischer, Pradeep Surisetty, Sho Weimer, Jan Hutař, Alex Krzos, Mike Ng
- Published: Sep 24, 2026
- Type: Benchmark

Red Hat conducted a performance and scale test of the argocd-agent pull architecture for GitOps, using 42 physical machines, 500 spoke clusters, and software including OpenShift 4.21 and OpenShift GitOps 1.20. The pull model decentralizes reconciliation to lightweight agents on each managed cluster, which pull configurations from a central hub, improving security by eliminating inbound administrative ports and reducing cross-cluster network traffic by up to 80%. In the bootstrap scenario, generating and syncing 31,200 applications across 480 clusters completed in 13 minutes 3 seconds, while the sync-to-commit scenario, which includes a polling delay, took 13 minutes. The test revealed bottlenecks including Kubernetes API limits on the hub, informer processing slowdowns causing watch restarts, event writer retry issues under load, and ApplicationSet controller RAM consumption. The team also deleted all 31,200 applications in 4 minutes 53 seconds using cascading deletion, and the insights are informing future OpenShift GitOps releases.


### [Continuing to Move PHP Open Source Forward](https://yomu.fyi/post/continuing-to-move-php-open-source-forward.md)
- Company: [Jetbrains](https://yomu.fyi/company/jetbrains.md)
- Author: Brent Roose
- Published: Sep 24, 2026
- Type: Announcement

Each year, PhpStorm selects five open-source projects to sponsor for a full year, providing financial support and raising awareness of open source in the PHP community. For this year, the chosen projects are PHPUnit, Lerd, static-php-cli, Composer, and Larabelles, selected from community suggestions based on their impact and need for financing. Sebastian Bergmann, creator and maintainer of PHPUnit, offers the most widely used testing suite for PHP. George Dumitrescu’s Lerd manages local PHP installations and servers, while Jerry Ma’s static-php-cli is used by FrankenPHP and Native PHP. PhpStorm continues its sponsorship of the PHP Foundation and encourages other organizations to contribute to open source, as every bit of support makes a substantial difference when added together.


### [Designing the Kotlin Multiplatform and TeamCity Integration](https://yomu.fyi/post/designing-the-kotlin-multiplatform-and-teamcity-integration.md)
- Company: [Jetbrains](https://yomu.fyi/company/jetbrains.md)
- Author: Bozidar Rakicevic
- Published: Sep 24, 2026
- Type: Problem & solution

The post describes the design of a new TeamCity integration for Kotlin Multiplatform (KMP) developers building iOS apps. The integration addresses common pain points: iOS builds require macOS infrastructure, Apple signing is complex, and there is no guided path from IDE to CI/CD. The solution provides a progressive onboarding flow within the IDE, starting with a tooltip after the first Git push. The flow generates four configuration files (teamcity.yaml, Fastfile, Appfile, Gemfile) and runs a build and tests on a hosted macOS agent, then guides the developer through a single form for Apple signing and TestFlight publishing, and finally automates the pipeline on GitHub pushes. TeamCity Cloud provides hosted macOS agents and a free starting tier, so no Mac is required. The design was validated through usability sessions and focuses on meeting the developer at the right moment with minimal configuration.


[Newer posts](https://yomu.fyi/posts/page/33.md) · [Older posts](https://yomu.fyi/posts/page/35.md)