--- 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 ### [AI agents are a confused deputy with the keys to your kingdom](https://yomu.fyi/post/ai-agents-are-a-confused-deputy-with-the-keys-to-your-kingdom.md) - Company: [Stack Overflow](https://yomu.fyi/company/stack-overflow.md) - Author: Fabio Salvadori - Published: Jun 17, 2026 - Type: Problem & solution Attackers recently compromised over twenty thousand Instagram accounts by manipulating Meta's AI support assistant to rebind recovery email addresses without verifying account ownership. This incident illustrates the classic confused deputy security problem, where a privileged process is persuaded by an unprivileged user to perform unauthorized operations. Because large language model interfaces operate purely on natural language and cannot distinguish instructions from data, the model itself cannot serve as an authorization boundary. Securing AI agents requires verifying caller identity through external policy checks against authenticated sessions rather than relying on chat context or prompt engineering. Teams must enforce least privilege with short-lived scoped credentials, place irreversible actions behind hard policy gates or human approvals, and maintain audit trails of agent actions. ### [The Partner Well-Architected Framework: What's New and What's Next](https://yomu.fyi/post/the-partner-well-architected-framework-what-s-new-and-what-s-next.md) - Company: [Databricks](https://yomu.fyi/company/databricks.md) - Author: David Porter - Published: Jun 17, 2026 - Type: Announcement The Partner Well-Architected Framework (PWAF) has moved partner guidance from static PDFs to AI-ready guidance spanning Built-On, Connected, and Data Collaboration architectures. It combines an architecture center with technical standards, patterns, and instrumentation guidance intended to align integrations with partner-engineering validation while making adoption and DBU impact measurable. Since February, Databricks has added a Dev Kit containing 15+ tested AI-developed skills, new or refreshed guidance for Clean Rooms, software-defined storage, Marketplace apps, Genie, Lakebase, and MCP server onboarding, and an open-source Firefly Analytics reference implementation. The framework is positioned as an evolving, agent-compatible way to shift routine integration work to AI tools, freeing partner and Databricks engineers to focus on complex architecture; more patterns, skills, reference implementations, and demos are planned. ### [What’s coming next to Free Edition](https://yomu.fyi/post/what-s-coming-next-to-free-edition.md) - Company: [Databricks](https://yomu.fyi/company/databricks.md) - Author: Will Valori, Trang Le - Published: Jun 17, 2026 - Type: Announcement Databricks is expanding Free Edition, launched twelve months ago to help people learn modern data and AI, after providing more than $10M in credits to over 500,000 learners. The five additions are Genie Code, serverless GPUs subject to availability, Lakebase, Agent Bricks, and Lakeflow Designer. Genie Code can generate, run, interpret, and refine code autonomously for tasks such as dataset analysis, pipeline cleaning, and visualization, while GPUs support deep-learning workloads including training, fine-tuning, inference, and large-dataset processing. Lakebase adds a fully managed Postgres-compatible database for data apps and AI agents; Agent Bricks supplies composable tools, memory, orchestration, and evaluation; and Lakeflow Designer enables visual pipeline construction. Together, these additions are presented as a complete free toolkit covering data engineering, analytics, machine learning, app development, and AI agents, allowing users to build end-to-end data and AI projects in Free Edition. ### [Becoming the most comprehensive data & AI ecosystem on earth](https://yomu.fyi/post/becoming-the-most-comprehensive-data-ai-ecosystem-on-earth.md) - Company: [Databricks](https://yomu.fyi/company/databricks.md) - Author: Stephen Orban - Published: Jun 17, 2026 - Type: Announcement Databricks describes a year of expanding its partner ecosystem for independent software vendors and data providers, responding to requests for stronger go-to-market support, technical guidance, and Marketplace transactions. It says it introduced partner tiering, the Partner Well-Architected Framework, a Marketplace Commit Drawdown pilot, and the ability to list Databricks Apps and Genie Agents. Under the pilot, customers with a Universal Commit can submit invoices for eligible solutions that run on or share data to Databricks; validated purchases reduce their commitment obligation, while Databricks compensates its sales team. OpenSharing is presented as an open-source, vendor-agnostic protocol for cross-cloud, cross-platform sharing of structured and unstructured data, volumes, agent skills, AI models, and semantics. The post says Apps adoption has grown fivefold since last year's summit, with more than 5,000 accounts running Apps in production weekly, and that more than 20,000 customers rely on Databricks. ### [Design Beautiful Dashboards in AI/BI](https://yomu.fyi/post/design-beautiful-dashboards-in-ai-bi.md) - Company: [Databricks](https://yomu.fyi/company/databricks.md) - Author: Maggie Li, Mohit Hingorani - Published: Jun 17, 2026 - Type: Tutorial This guide presents dashboard design as a way to apply brand identity consistently while helping viewers interpret business data and trust the result. It recommends choosing a 3-, 4-, or 6-column subdivision of AI/BI’s 12-column grid according to audience needs, then using F- or Z-pattern hierarchy and unequal widget sizes to prioritize information. The visual system combines readable sans-serif or local fonts, high-contrast text, neutral backgrounds, a 60-30-10 color allocation, and distinct interactive and visualization palettes. For the Wanderbricks example, the final five-color palette is #15AFDD, #2375A8, #52A870, #C85070, and #C89930, tested in light and dark modes and with color-blindness simulations; workspace themes extend the resulting styling across dashboards. ### [What’s new in Genie Code at Data + AI Summit 2026](https://yomu.fyi/post/what-s-new-in-genie-code-at-data-ai-summit-2026.md) - Company: [Databricks](https://yomu.fyi/company/databricks.md) - Author: Julia Powell, Gal Oshri, Weston Hutchins - Published: Jun 17, 2026 - Type: Announcement At Data + AI Summit 2026, Databricks announced expansions to Genie Code for complex, agentic data and ML work. The changes include a full-page command center for managing concurrent threads and assets, upgrades across production ML engineering, and scheduled tasks that run prompts while users are away. For ML workflows, Genie Code uses Databricks production expertise and Genie Ontology, integrates with MLflow and Model Serving, and can move GPU jobs to AI Runtime while using workspace environment features. It can write features, coordinate edits, run and debug code, compare candidates, inspect endpoint health, and diagnose issues, with users deciding what to keep. Scheduled tasks are described as coming soon, creating reviewable threads from prompts and optional Databricks assets. ### [What’s new in Databricks Data + AI Platform security and compliance at Data + AI Summit 2026](https://yomu.fyi/post/what-s-new-in-databricks-data-ai-platform-security-and-compliance-at-d.md) - Company: [Databricks](https://yomu.fyi/company/databricks.md) - Author: Jason Wu, Samrat Ray, Filippo Seracini, Alex Esibov, Vijay Raja, Kelly Albano, Robert Zhang, Mia Penfold Lopez - Published: Jun 17, 2026 - Type: Announcement At Data + AI Summit 2026, Databricks announced security and compliance capabilities for scaling Genie, Lakebase, serverless workloads, and AI-powered applications without relying solely on manual provisioning, static network controls, or siloed compliance programs. Automatic Identity Management (AIM) for Microsoft Entra ID is generally available on AWS and Google Cloud, AIM for Okta is in Public Preview, and Context-Based Ingress is in Public Preview across all three clouds for policies based on network source, identity, and access scope. Private Network Gateway, in Private Preview on Azure Databricks, provides one secure connection from serverless workloads to private networks, while expanded Private Link support extends to Lakebase and other services. Compliance additions include Azure Serverless coverage, HITRUST across AWS, Azure, and Google Cloud, ISMAP on Azure and AWS, expanded AWS GovCloud availability, and planned FedRAMP High support on Azure Commercial. ### [92x faster queries: How Open Electricity uses ClickHouse to track Australia’s energy transition in real time](https://yomu.fyi/post/92x-faster-queries-how-open-electricity-uses-clickhouse-to-track-austr.md) - Company: [Clickhouse](https://yomu.fyi/company/clickhouse.md) - Published: Jun 17, 2026 - Type: Problem & solution Open Electricity uses ClickHouse to serve live Australian energy data through a public platform and API spanning roughly one billion records. Migrating from Postgres and TimescaleDB addressed queries that could take more than five minutes, reducing a benchmark to just over three seconds and to 60 milliseconds with a materialized view. The new setup keeps heavy relational workloads in Postgres while ClickHouse handles analytics, using ReplacingMergeTree base tables and more than 20 materialized views for different aggregation patterns. It also uses substantially less hardware than the previous configuration: four cores, four GB RAM, and 200 GB disk versus 16 cores, 32 GB RAM, and 1.6 TB, while serving data added daily and API users. ### [From the Hugging Face Hub to robot hardware with Strands Agents and LeRobot](https://yomu.fyi/post/from-the-hugging-face-hub-to-robot-hardware-with-strands-agents-and-le.md) - Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md) - Author: Sundar Raghavan, Cagatay Cali - Published: Jun 17, 2026 - Type: Tutorial Strands Robots integrates Hugging Face’s LeRobot stack with Strands Agents to connect dataset recording, policy execution, simulation, hardware deployment, and fleet coordination in one agent loop. Its integration keeps LeRobot responsible for hardware drivers, calibration, recording, and dataset handling, while Strands supplies AgentTools, a shared Robot abstraction, policy providers, and a Zenoh peer mesh; simulation and hardware use the same LeRobotDataset format. The walkthrough records demonstrations in MuJoCo, optionally pushes them to the Hub, runs policies through a common interface, and switches from simulation to a physical SO-101 with mode="real". The companion script and notebook run the default simulation workflow on a laptop without hardware, a GPU, or Hugging Face credentials, although the default Mock policy produces structurally valid but behaviorally unhelpful random demonstrations. ### [Building an open ecosystem for AI governance with Unity AI Gateway](https://yomu.fyi/post/building-an-open-ecosystem-for-ai-governance-with-unity-ai-gateway.md) - Company: [Databricks](https://yomu.fyi/company/databricks.md) - Author: David Nasi, Kelly Albano, Ashish Kathapurkar - Published: Jun 17, 2026 - Type: Announcement Databricks announced the Unity AI Gateway partner ecosystem, extending enterprise AI governance beyond models to runtime interactions among models, agents, MCP servers, skills, and AI tools. Built on Unity Catalog, the gateway lets organizations apply policies, monitor activity, manage spend, and govern AI across providers and frameworks, while integrating security, identity, and governance products they already use. The announcement groups the integrations into runtime AI security, observability and guardrails; agent identity and access governance; and AI observability and risk monitoring. Named integrations include Alice, CrowdStrike Falcon AI Detection and Response, Cyera, HiddenLayer, Netskope, Noma Security, Obsidian Security, Openlayer, Okta, Ping Identity, SailPoint, and Saviynt, with described capabilities including prompt-injection detection, data-loss prevention, agent discovery, authorization, and lifecycle governance. ### [GLM-5.2: Built for Long-Horizon Tasks](https://yomu.fyi/post/glm-5-2-built-for-long-horizon-tasks.md) - Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md) - Author: Z.AI - Published: Jun 17, 2026 - Type: Announcement GLM-5.2 is presented as a flagship model for long-horizon tasks, extending GLM-5.1’s capability to a solid 1M-token context for sustained engineering work. It was trained extensively on 1M-context coding-agent scenarios involving large-scale implementation, automated research, performance optimization, and complex debugging, and adds effort-level controls to balance capability, latency, and computational cost. Its architecture uses IndexShare, sharing one lightweight indexer across every four transformer layers and reducing per-token FLOPs by 2.9× at 1M context; MTP changes for speculative decoding increase acceptance length by up to 20%. On reported long-horizon and standard coding benchmarks, GLM-5.2 is described as the highest-ranked open-source model: it trails Opus 4.8 by 1% on FrontierSWE, ranks second only to Opus 4.8 on PostTrainBench, and scores 81.0 on Terminal-Bench 2.1 versus GLM-5.1’s 63.5. ### [What’s New in the AI Platform: Agents for ML Engineering, Our Deep Learning Platform, and New Capabilities for Real-Time ML](https://yomu.fyi/post/what-s-new-in-the-ai-platform-agents-for-ml-engineering-our-deep-learn.md) - Company: [Databricks](https://yomu.fyi/company/databricks.md) - Author: Tejas Sundaresan, Mike Del Balso - Published: Jun 17, 2026 - Type: Announcement The announcement presents three additions to the Databricks AI Platform: Genie Code support for ML engineering, AI Runtime’s serverless GPU environment, and expanded real-time ML capabilities. Genie Code integrates with Unity Catalog, Feature Store, training, serving, monitoring, and MLflow, assisting with feature engineering, model training, deployment, evaluation, and production operations. AI Runtime provides on-demand serverless NVIDIA A10 and H100 GPUs, supports high-performance multinode training with RDMA and high-performance data loading, and adds Lakeflow Jobs, DABs, MLflow, and Unity Catalog integration. For real-time ML, the platform adds declarative feature engineering, streaming features, online feature serving on Lakebase, and enhanced Model Serving targeting 300K+ QPS with under 10ms p99 latency overhead. Reported customer examples include faster workflows, lower infrastructure costs, and production scaling beyond 100K QPS. ### [Introducing the Agentic CDP: A New Species of CDP for a New Era of Agents](https://yomu.fyi/post/introducing-the-agentic-cdp-a-new-species-of-cdp-for-a-new-era-of-agen.md) - Company: [Databricks](https://yomu.fyi/company/databricks.md) - Author: Tasso Argyros, Ali Ghodsi, Reynold Xin - Published: Jun 17, 2026 - Type: Announcement Traditional customer data platforms (CDPs) were built for human-managed, batch-based campaigns, but the post argues that agentic buying requires millisecond speed, hyper-personalization, and richer context. It contrasts the familiar Golden Record with Golden Context, which combines customer data with current business goals and the history and outcomes of prior decisions. The proposed Agentic CDP uses “Infinity Campaigns,” always-on engagement loops that use LLMs and agents to adapt messaging, timing, and channels for individuals. It is also embedded in the data foundation, bringing customer, business, and decision context together under existing governance, and is designed for agents and humans from the outset. Databricks presents CustomerLake as an implementation of these principles for its platform. ### [Cloud Environment Setup and Cloud Subagents in Agents Window](https://yomu.fyi/post/cloud-environment-setup-and-cloud-subagents-in-agents-window.md) - Company: [Cursor](https://yomu.fyi/company/cursor.md) - Published: Jun 17, 2026 - Type: Announcement This release updates cloud agents in the Agents Window of the Cursor desktop app, adding cloud environment setup, cloud subagents, and more reliable movement between local and cloud sessions. Cursor can help configure a development environment in under 10 minutes while showing progress in a shared terminal, then capture the result as a reusable snapshot for faster startup and software testing by future agents. The /in-cloud command launches a subagent in its own virtual machine and branch, isolating long-running or parallel tasks while the local workspace remains responsive; /babysit lets a cloud agent iterate on a pull request remotely. Cloud subagents can run in the background, and sessions can be pulled back to a local computer for testing, with multiple cloud agents running in parallel. ### [Kimi K2.7 Code vs Claude Fable 5: Landing pages that cost 94% less](https://yomu.fyi/post/kimi-k2-7-code-vs-claude-fable-5-landing-pages-that-cost-94-less.md) - Company: [Together AI](https://yomu.fyi/company/together-ai.md) - Published: Jun 17, 2026 - Type: Benchmark The experiment compares Kimi K2.7 Code and Claude Fable 5 across 12 landing-page prompts covering B2B SaaS, a rooftop speakeasy, developer tools, and other categories. Kimi cost about 94% less overall, averaging roughly 16 times cheaper than Fable, while producing similar-quality output, especially when given visual references. The team first established a prompt-only baseline, then used a custom design MCP server to provide screenshots, UI elements, and other references directly to multimodal Kimi; this improved hierarchy, typography, composition, readability, loading behavior, and image handling. GPT-5.5 scored screenshots and source code on a 0–100 rubric, and although Fable scored higher, the relatively small quality gap led the authors to consider Kimi’s lower cost a reasonable trade-off for iterative landing-page generation. ### [Announcing the Agentic Resource Discovery specification](https://yomu.fyi/post/announcing-the-agentic-resource-discovery-specification.md) - Company: [Google](https://yomu.fyi/company/google.md) - Author: Junjie Bu, Srinivas Krishnan - Published: Jun 17, 2026 - Type: Announcement Agentic Resource Discovery (ARD) is an open specification for publishing, discovering, and verifying AI capabilities across the web, addressing the lack of a standard that works across organizations and ecosystems. It uses organization-hosted catalogs, including an ai-catalog.json file at a well-known domain path, plus federated registries that crawl, index, and return capabilities with trust metadata. Clients can query a registry with plain-language intent or fetch a known catalog directly, verify the publisher’s cryptographic identity, then connect at runtime through the capability’s native protocol or API. Google Cloud is bringing ARD to Gemini Enterprise Agent Platform through Agent Registry, which supports hosted discovery and governance features including namespaced URNs, egress policies, specification pinning, and Agent Identity trust-manifest verification. The specification is available under Apache 2.0, with native Agent Platform support planned in the coming months. ### [A2UI + MCP Apps: Combining the best of declarative and custom agentic UIs](https://yomu.fyi/post/a2ui-mcp-apps-combining-the-best-of-declarative-and-custom-agentic-uis.md) - Company: [Google](https://yomu.fyi/company/google.md) - Author: Google A2UI Team, Ido Salomon, Liad Yosef - Published: Jun 17, 2026 - Type: Explainer Agentic UIs must balance deep customization with seamless integration: MCP Apps provide standard-web flexibility in an iframe, while A2UI renders declarative JSON through the host application's native components. The post presents three architectural patterns for combining them, including A2UI over MCP, where MCP servers return application/a2ui+json resources for native rendering and can separate static MCP Resources from dynamic Tool calls. This arrangement avoids iframe-related visual fragmentation, keeps backend tool access separate from frontend rendering, and supports rendering across React, Flutter, or Angular through a predefined component catalog. The broader combination also reserves MCP Apps for highly tailored experiences and describes A2UI in MCP Apps, where an embedded app can process A2UI responses and route user actions through an AppBridge; the conclusion recommends choosing among patterns according to project constraints. ### [Clustering billions of products for agentic commerce with Catalog API](https://yomu.fyi/post/clustering-billions-of-products-for-agentic-commerce-with-catalog-api.md) - Company: [Shopify](https://yomu.fyi/company/shopify.md) - Author: 2023-10-18 - Published: Jun 17, 2026 - Type: Explainer Shopify’s Catalog must reconcile billions of listings whose merchants use different product and variant structures, so AI shopping agents can identify the same real-world product. Product clustering groups related listings under a Universal Product Identifier, with precision prioritized over recall because wrong products can lead to incorrect purchases while missed variants remain findable. The intra-store system starts with rules-based singleton detection, then uses ANN and sparse average linkage for pre-chunking, and applies a two-stage LLM process that proposes clusters and critiques them using the core value proposition framework. Dynamic per-chunk strict JSON schemas enforce complete product coverage, support arbitrary chunking, and improved recall by 8% on the Toloka evaluation dataset in one schema change. The resulting pipeline is presented as a scalable intra-store foundation, while cross-store clustering into global UPIs is identified as the next step. ### [Agentic Resource Discovery: Let agents search](https://yomu.fyi/post/agentic-resource-discovery-let-agents-search.md) - Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md) - Author: ben burtenshaw, shaun smith - Published: Jun 17, 2026 - Type: Explainer Agentic Resource Discovery (ARD) is a draft, open specification for discovering agent capabilities at runtime, addressing a model in which users and developers must pre-install, integrate, and maintain each MCP tool, skill, or A2A agent. It defines a static ai-catalog.json manifest and a dynamic POST /search registry API, using indexed signals such as publisher identity, representative queries, compliance attestations, and tags to move capability selection outside the LLM. Hugging Face's Discover Tool adapts Hub semantic search into ARD catalog entries for running Spaces, exposing skills, MCP servers, or raw Space metadata according to the requested media type and wrapping agents.md files into installable SKILL.md artifacts. The tool is available through the hf CLI, REST, and MCP, while planned work includes federation modes and Hub support for profile-level manifests. ### [Building AI Agents for AR Glasses and XR Devices with NVIDIA XR AI](https://yomu.fyi/post/building-ai-agents-for-ar-glasses-and-xr-devices-with-nvidia-xr-ai.md) - Company: [NVIDIA](https://yomu.fyi/company/nvidia-developer-blog.md) - Author: Greg Barbone - Published: Jun 16, 2026 - Type: Announcement Building AI experiences for augmented reality and wearable devices requires bridging hardware with live media streams, multimodal models, enterprise tools, and runtime infrastructure. NVIDIA XR AI provides an open-source, modular framework connecting extended reality headsets and smart glasses to GPU-accelerated services across cloud, edge, and workstations. In this architecture, camera frames and microphone audio ingest into an XR Media Hub that routes data while keeping raw video pixels in shared memory to minimize overhead. The ecosystem uses NVIDIA Cosmos models for vision-language grounding, NVIDIA Nemotron models for reasoning and tool invocation, and the Model Context Protocol for enterprise integrations. Optional agent orchestration via NVIDIA NeMo Agent Toolkit and spatial streaming through NVIDIA CloudXR support complex workflows across healthcare and manufacturing. [Newer posts](https://yomu.fyi/posts/page/110.md) · [Older posts](https://yomu.fyi/posts/page/112.md)