---
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

### [How Dropbox uses MCP and Dash to close the design-to-code security gap](https://yomu.fyi/post/how-dropbox-uses-mcp-and-dash-to-close-the-design-to-code-security-gap.md)
- Company: [Dropbox](https://yomu.fyi/company/dropbox.md)
- Author: Ilya Yakovlev,Andrew Cheung,Binoy Dash,Simran Jumani,Dmitriy Meyerzon,Mark Breitenbach,Ishan Mishra
- Published: Jun 12, 2026

Dropbox developed a system using the Model Context Protocol (MCP) and Dash's semantic search to bridge the gap between security threat models and code implementation. By retrieving original security documents during pull requests, an LLM agent automatically evaluates whether the proposed code adheres to previously agreed-upon security requirements. This approach surfaces design regressions and missing controls that traditional static analysis tools miss.


### [Enabling Evolutionary Database Development: Database branching with Lakebase, the conclusion](https://yomu.fyi/post/enabling-evolutionary-database-development-database-branching-with-lak.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Pramod Sadalage, Kevin Hartman
- Published: Jun 12, 2026
- Type: Explainer

The post concludes a series on how copy-on-write database branching in Databricks Lakebase changes team-scale evolutionary database development without changing its underlying methodology. For a team of fifty developers, long-running tier branches and ephemeral feature branches form a parent-linked promotion hierarchy, replacing separately provisioned environment instances and enabling promotion by merge, rollback by repoint, and computable schema divergence. Governance is declared once and inherited per branch, with policies intended to prevent transitions that contradict the parent chain; Unity Catalog captures metadata for attribution and audit. The DBA's role becomes platform engineering, while agents operate inside an executable SCM state machine with documented inputs, outputs, schema validation, and enforced gates. An optional TDD layer adds dedicated roles, acceptance-criterion scenarios, RED-GREEN-REFACTOR cycles, and artifact contracts, and the conclusion presents the resulting workflow as operational for human and agent practitioners.


### [Results from first Anthropic Public Record](https://yomu.fyi/post/results-from-first-anthropic-public-record.md)
- Company: [Anthropic](https://yomu.fyi/company/anthropic.md)
- Published: Jun 12, 2026
- Type: Explainer

Anthropic’s first Public Record survey measures how Americans viewed AI in November and December 2025, using a nationally representative online sample of 51,993 people aged 16 and over. Respondents most often hoped AI would help cure diseases (48%), while job loss was the leading concern (64%), followed by cognitive dependency (56%) and misinformation (52%). More than 70% supported government involvement in AI, especially around privacy, child safety, and liability, but only 15% trusted AI companies to decide how AI should be developed and used. The results describe broad agreement across partisan, geographic, and educational groups, with differences usually reflecting intensity rather than direction; Anthropic says the survey will be repeated to track changing attitudes as capabilities and adoption develop.


### [Talk to all your data, wherever it lives](https://yomu.fyi/post/talk-to-all-your-data-wherever-it-lives.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: John Spencer
- Published: Jun 12, 2026
- Type: Tutorial

Lakehouse Federation addresses the challenge of reasoning across enterprise data spread among AWS Glue, Snowflake, Oracle, BigQuery, Postgres, and legacy formats without first migrating it. By connecting external sources in place and syncing their metadata into Unity Catalog, Databricks applies shared permissions, lineage, and access controls while preserving source data. Federated comments and descriptions give Genie schema context, while Unity Catalog Semantics lets teams define governed metrics such as ROI once for consistent use across Genie, dashboards, and notebooks. The example connects an AWS Glue marketing database, carries its metadata, defines an ROI metric view, and asks Genie which campaigns led ROI last quarter. The post reports an immediate, accurate answer from live Glue data, and describes planned richer semantics, broader federation, and possible performance gains from managed tables.


### [Better, faster, less wrong: Enhancing issue grouping](https://yomu.fyi/post/better-faster-less-wrong-enhancing-issue-grouping.md)
- Company: [Sentry](https://yomu.fyi/company/sentry.md)
- Author: Kush Dubey, Yuval Mandelboum
- Published: Jun 12, 2026
- Type: Problem & solution

Sentry upgraded its AI-driven issue grouping system to better prevent duplicate issues without merging distinct application errors. The team trained lightonai/modernbert-embed-large using Matryoshka Representation Learning on hundreds of thousands of stacktrace pairs labeled by Claude Sonnet 4.5. To optimize the high-throughput ingestion pipeline, embeddings were truncated from 768 to 64 dimensions, combined with bfloat16 precision, PyTorch SDPA, and CUDA graph compilation. A phased live rollout used threshold-gated index backfilling and automatic fallback to prevent issue spikes during migration. In production, the v2 model cuts the overgrouping rate from 8% to 4%, increases prevented duplicate issues to 70%, and delivers 6x faster inference.


### [Unlocking semantics for AI: How Mercedes-Benz Korea built trusted “Talk to Data” at scale](https://yomu.fyi/post/unlocking-semantics-for-ai-how-mercedes-benz-korea-built-trusted-talk.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Sai Yang, Fares Kamal, Alina Kamal, Andreas Jäck, Johannes Laufer, Manuel Culebras
- Published: Jun 11, 2026
- Type: Explainer

Mercedes-Benz Korea piloted a “Talk to Data” architecture that extends its Databricks analytics foundation with a governed semantic layer for enterprise AI, rather than treating the effort as a chatbot project. The design moves Power BI DAX KPI logic into Unity Catalog Business Semantics and Metric Views, keeping sources, joins, measures, dimensions, comments, and synonyms alongside governed Lakehouse data. Genie spaces use curated metric views for domain questions, while Agent Bricks composes persona-based agents, with Unity Catalog enforcing row- and column-level access. An automated DAX-to-Metric-View transpiler parses semantic models, maps tables, generates draft definitions, flags non-automatable measures, and reports conversion gaps. The documented playbook combines gold-layer curation, KPI validation, regression testing, Genie optimization, persona agents, and Databricks Apps; the pilot reports AI answers aligned with established KPI definitions and BI reporting logic.


### [Forward Deployed Engineering: Delivering Business Outcomes with AI](https://yomu.fyi/post/forward-deployed-engineering-delivering-business-outcomes-with-ai.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Jason Martin
- Published: Jun 11, 2026
- Type: Announcement

Databricks is formalizing its Forward Deployed Engineering (FDE) organization to address customers’ shift from migration and data-pipeline requests toward business outcomes with AI. FDE brings Professional Services together around an engineering-led model that embeds engineers with customers, supports modernization and production AI, and works with partners and Databricks R&D. In the cited examples, teams migrated five-plus petabytes of JPMC Consumer and Community Banking Risk data and more than 500 notebooks in four months, while Fox used Lakebase, AI Search, Databricks Apps, and Model Serving to redesign fan experiences. The organization says its engagements use shared OKRs, rapid prototype-to-production delivery, embedded engineering, outcome-aligned commercial options, and global partner coverage, with Fox reporting that Sports AI users spend approximately twice as long in the app.


### [Production-Ready Agents Need A Production-Ready Data Platform](https://yomu.fyi/post/production-ready-agents-need-a-production-ready-data-platform.md)
- Company: [MongoDB](https://yomu.fyi/company/mongodb.md)
- Author: Pablo Stern
- Published: Jun 11, 2026
- Type: Explainer

AI development teams face constant shifts in model providers and agent frameworks, demanding data platforms that provide scalable, real-time context management. Agentic workloads require blending unstructured enterprise data, short-term session state, and persistent long-term memory. MongoDB addresses these requirements through its native JSON document model and integrated retrieval capabilities, combining full-text search, vector search, and hybrid search directly over operational data. Customer implementations such as DevRev, ElevenLabs, and Adobe rely on Atlas to achieve sub-100 millisecond hybrid retrieval and handle billions of requests. Additionally, MongoDB is collaborating with LangChain and ecosystem partners to establish open reference architectures and shared interfaces for portable agent memory across frameworks.


### [Ingesting the Milky Way: Petabyte-Scale with Zerobus Ingest](https://yomu.fyi/post/ingesting-the-milky-way-petabyte-scale-with-zerobus-ingest.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Aleksandar Tomić, Victoria Bukta, Nikola Obradović, Danilo Najkov, Branko Grbić, Milos Milovanovic
- Published: Jun 11, 2026
- Type: Benchmark

The post benchmarks Zerobus Ingest, a managed, serverless, push-based service that writes producer data directly to Delta tables governed by Unity Catalog, against a petabyte-scale telemetry workload. Using NASA’s NEOWISE dataset and Locust, the test modeled fan-in from 2,048 concurrent streams, using Protocol Buffer 2 data over approximately 24 hours. The design replaces static partition-based ordering with stream-connection ordering, allowing heuristic routing across pods, dynamic partitioning, and autoscaling while existing streams drain. It also uses zeroparser, a zero-copy protobuf decoder whose design relies on Rust’s lifetime system and supports dynamic descriptors at about 1 GB/s per CPU core. The test sustained 12 GB/s to one table, ingested 1.04 trillion rows, and reached 1 petabyte within 24 hours; Zerobus Ingest is generally available, with additional APIs on its roadmap.


### [How ERGO Hestia reduced time-to-market with Databricks Lakebase and Model Serving](https://yomu.fyi/post/how-ergo-hestia-reduced-time-to-market-with-databricks-lakebase-and-mo.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Klaudia Ratkowska, Maciej Majewski, Oliver Börner, Alexander Migunov
- Published: Jun 11, 2026
- Type: Problem & solution

ERGO Hestia redesigned its real-time pricing platform to reduce deployment friction across more than 100 models and 1,000 variables while preparing B2C capabilities. Previously, processed data moved from Databricks through extraction jobs, external Azure PostgreSQL, and a custom caching adapter, creating governance overhead, deployment coordination, and latency spikes during large refreshes. The new architecture uses Lakebase Sync Tables as an online serving layer and Databricks Model Serving Endpoints, keeping data, request logic, and model serving within the lakehouse; Unity Catalog supplies lineage, version tracking, access controls, and audit trails. An incremental migration started with a low-criticality endpoint, measuring 20ms latency and less than 5% CPU utilization at 40 requests per second, before expanding toward larger workloads and the planned decommissioning of PostgreSQL.


### [Welcoming the first cohort of Databricks student fellows](https://yomu.fyi/post/welcoming-the-first-cohort-of-databricks-student-fellows.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Elise Hollowed, Joe Nash, Trang Le
- Published: Jun 11, 2026
- Type: Announcement

Databricks announces its inaugural Student Fellows cohort, selected from more than 5,000 applications submitted by students at hundreds of universities and from dozens of countries. The program targets students who contribute on campus, apply data and AI in practice, and intend to pursue careers in the field, with fellows acting as bridges between academic theory and the real-world scale of the Databricks platform. Five students are profiled, with experience spanning large-scale AI systems, ETL pipelines, computer vision, machine learning platforms, robotics, data modeling, and local retrieval-augmented generation architectures. During the coming academic year, the cohort will receive training from Databricks experts and hands-on experience solving complex data challenges, while building a launchpad for future internship opportunities. The program invites applications for its next cohort in Fall 2026 and points readers to Databricks Free Edition.


### [Geospatial Unbounded: Spatial SQL GA with AI/BI Maps, Delta Sharing, and Iceberg v3](https://yomu.fyi/post/geospatial-unbounded-spatial-sql-ga-with-ai-bi-maps-delta-sharing-and.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Kent Marten
- Published: Jun 11, 2026
- Type: Announcement

Databricks announces Spatial SQL as Generally Available, positioning its platform for geospatial analysis without separate spatial databases, warehouses, and mapping tools. It supports native GEOMETRY columns in Delta or Iceberg, more than 90 OGC-compliant ST\_\* functions, spatial joins, and boolean set operations. AI/BI dashboards can render Geometry and Geography columns as maps, while Genie can generate spatial queries and dashboards and respect Unity Catalog row filters. Geo columns are supported by Delta Sharing, and Databricks can read and write managed Iceberg tables or read externally written Iceberg tables with geospatial types in Iceberg v3. Benchmarks show eight of twelve SpatialBench queries improved since Public Preview, with gains from 20% to 15X, while areal boolean operations are twice as fast on average versus prior versions.


### [Azure Databricks at Data + AI Summit 2026 featuring Industry Leaders and Partners](https://yomu.fyi/post/azure-databricks-at-data-ai-summit-2026-featuring-industry-leaders-and.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Kiriana Stukas
- Published: Jun 11, 2026
- Type: Announcement

Data + AI Summit 2026 brings Databricks and Microsoft leaders, partners, and customers together June 15–18, with in-person and virtual programming focused on Azure Databricks. The collaboration presents Azure Databricks as a first-party Microsoft offering for unifying data, analytics, and AI on a secure, scalable foundation, with sessions covering ecosystem integration, federated analytics, governance, modernization, and AI applications. One technical example introduces zero-copy federation between Azure Data Manager for Energy and Databricks compute, preserving ADME as the source of truth while avoiding large-scale data copies. Another shows Unity Catalog External Locations extending governed access to Microsoft OneLake without ETL pipelines, while customer sessions describe Apache Iceberg and Apache Spark integration, fragmented data consolidation, and production-grade finance workflows using Azure Document Intelligence.


### [Introducing Postgres to Postgres ClickPipes in ClickHouse Cloud](https://yomu.fyi/post/introducing-postgres-to-postgres-clickpipes-in-clickhouse-cloud.md)
- Company: [Clickhouse](https://yomu.fyi/company/clickhouse.md)
- Published: Jun 11, 2026
- Type: Announcement

Postgres-to-Postgres migrations between providers can require manual schema handling, data movement, CDC, and cutover coordination, with risks around database objects and long-running loads. Postgres to Postgres ClickPipes, now in public beta, provides a fully managed migration service in ClickHouse Cloud designed to reduce operational overhead and support minimal downtime. It automates schema dump and restore, including secure connections, role conflicts, version differences, transactional application, retries, and UI or notification-based error reporting, while PeerDB supplies parallel initial loads and CDC capabilities. Independent pull and push processes use retries and alerting for transient errors, and the roadmap includes features to assist with cutover into Postgres by ClickHouse.


### [Empower your healthcare agents with ready-to-use MCP on Databricks Marketplace](https://yomu.fyi/post/empower-your-healthcare-agents-with-ready-to-use-mcp-on-databricks-mar.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Yen Low, Mark Lee, Matthew Giglia, Nicholas Siebenlist, Jay Bhankharia, Paul Ford, Itai Weiss
- Published: Jun 11, 2026
- Type: Announcement

Databricks announces ready-to-use Model Context Protocol (MCP) servers for healthcare and life sciences through Databricks Marketplace, addressing the need to combine curated biomedical knowledge, timely data, specialized tools, and private records. Listings include services for drug and target intelligence, literature, clinical trials, FDA information, Medicare coverage, ontologies, real-world evidence, clinical semantics, and interoperability, while Climb connects live public sources with private Gold-layer data under Unity Catalog governance. Marketplace and custom MCP servers are centralized in the MCP Catalog and governed by Unity AI Gateway, with Genie Spaces, AI Search, Unity Catalog functions, and SQL Warehouses available as managed MCP servers. Users can assemble agents in AI Playground, Agent Bricks, or notebooks, then deploy endpoints or apps with MLflow tracing, evaluation, human feedback, and AI guardrails; examples span molecular-property lookup, clinical questions, and drug research.


### [How Ecolab rebuilt retail intelligence on Databricks and Anthropic Claude](https://yomu.fyi/post/how-ecolab-rebuilt-retail-intelligence-on-databricks-and-anthropic-cla.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Babu Chinnaswamy, Nicholas Dylla, Alissa Ellingson, Harish Gaur
- Published: Jun 11, 2026
- Type: Problem & solution

Ecolab needed to combine audits, health inspections, pest telemetry, and other data from nine systems so retail teams could answer location-specific compliance questions. Its Retail Intelligence application is a native Databricks App using Lakebase Postgres, Lakeflow, and Spark Declarative Pipelines to move governed data into a Unity Catalog lakehouse, while Foundation Model APIs serve Claude Sonnet, Claude Haiku, and Gemini. A Coordinator Agent delegates requests to specialized agents that use Vector Search, SQL, Unity Catalog Functions, and an external MCP server; a Response Agent returns cited answers, with short- and long-term memory stored through Lakebase. The system also applies five Judge LLMs, MLflow tracing, and ai\_query() batch inference. Report preparation fell from two weeks to under two minutes, while the assistant supports approximately twelve languages at about 98% accuracy.


### [Agentic Testing: Where Agents Fit in the E2E Testing Stack](https://yomu.fyi/post/agentic-testing-where-agents-fit-in-the-e2e-testing-stack.md)
- Company: [Slack](https://yomu.fyi/company/slack.md)
- Author: Sergii Gorbachov
- Published: Jun 11, 2026
- Type: Benchmark

Traditional end-to-end tests validate rigid user journeys, whereas agentic tests verify whether broad goals can be achieved by adapting actions dynamically. To evaluate agentic testing tradeoffs, researchers executed over 200 runs across Playwright Model Context Protocol (MCP), Playwright CLI, and agent-generated Playwright tests using Claude models. Playwright MCP demonstrated high reliability with failure rates of 0% on simple thread replies and approximately 12% on complex search discovery flows. Playwright CLI and generated code struggled more on complex workflows, exhibiting failure rates of approximately 20% and 48% respectively. Although generated tests were faster with average runtimes of roughly three minutes, agentic testing provides a distinct exploratory layer atop deterministic CI test suites.


### [Simplifying Data and Product Integrations with a Data Abstraction Layer](https://yomu.fyi/post/simplifying-data-and-product-integrations-with-a-data-abstraction-laye.md)
- Company: [Uber](https://yomu.fyi/company/uber.md)
- Published: Jun 11, 2026
- Type: Explainer

Uber built a domain-agnostic Data Abstraction Layer (DAL) to decouple data consumers from changing physical datasets and simplify advertiser reporting. The DAL is an RPC service that accepts a logical table, schema, time range, and filters; logical tables define the interface, while configuration describes locations, relationships, availability windows, and rollup transforms. It generates database-specific queries, runs them in parallel across systems such as an internal OLAP database, Docstore, and Apache Hive, and assembles responses with aggregation and rollup behavior determined by the request. Removing a dimension can produce an account-level response with metrics automatically rolled up, while mixed realtime and daily tables can cover different portions of a requested time range. For advertiser reporting, the approach reduced new report delivery from several weeks or months to under two days and enabled dynamic filters, report builders, and third-party API integrations.


### [How to make the case for giving your AI Agent system access](https://yomu.fyi/post/how-to-make-the-case-for-giving-your-ai-agent-system-access.md)
- Company: [Intercom](https://yomu.fyi/company/intercom.md)
- Author: Dawn Perrott
- Published: Jun 11, 2026
- Type: Problem & solution

AI Agents can answer support questions without backend access, but they cannot complete changes such as payment-plan updates, claims, or account edits. Connecting an Agent to CRM, billing, order-management, or other systems moves support from explanation to end-to-end resolution, and the source frames that shift as the basis for an engineering request. Data from a 2026 Customer Service Transformation Report shows improved metrics among 87% of teams with mature AI deployment, versus 62% overall, while only 10% report reaching that stage; an internal comparison found Procedures with system access produced the largest gains in workflows requiring judgment, branching, live data, or handoffs. The recommended case starts with one high-volume, repeatable workflow, maps its data and actions, and defines a narrow pilot. Teams can then progress from no integration to read-only access and finally write actions, using measured results to justify further work.


### [Making FlashAttention-4 faster for inference](https://yomu.fyi/post/making-flashattention-4-faster-for-inference.md)
- Company: [Modal](https://yomu.fyi/company/modal.md)
- Author: Charles Frye
- Published: Jun 11, 2026
- Type: Explainer

FlashAttention-4, originally designed for pre-training, required modifications to efficiently handle LLM inference workloads dominated by the memory bandwidth-limited decode phase. Modal’s contributions include adjusting parallelism strategies from query parallelism to key/value parallelism, implementing split KV to parallelize across KV tiles, and adding a heuristic for optimal splits. They added support for FP8 inputs, arbitrary KV page sizes via cp.async loads, and reduced wasted work for small query sizes by using a single query tile. The kernel also gained extended GQA packing for irregular head ratios, using cp.async for query tiles to bypass TMA alignment restrictions. These changes, measured in throughput improvements up to 3x for single-token decode and up to 2.4x for small page sizes, demonstrate the leverage of flexible parallelism and tile-based programming for inference optimization.


[Newer posts](https://yomu.fyi/posts/page/114.md) · [Older posts](https://yomu.fyi/posts/page/116.md)