Every post, summarised

Jul 16, 2026

• Databricks

  Unified context: The missing layer for enterprise AI coworkers

  Enterprise AI assistants often produce fluent answers yet fail to improve forecast calls, deal reviews, and operational standups because decision context is scattered across systems, teams, and competing definitions. Genie One addresses this by using a shared context layer spanning Databricks data, documents, SaaS applications, and operational systems, allowing questions and follow-up work to retain business meaning. Genie Ontology organizes terms, metrics, entities, and relationships into a living knowledge graph, learning from data, dashboards, queries, documents, and connected applications while ranking definitions and signals using usage and certified-asset links. Together with Unity Catalog, it applies permissions, certified data, shared definitions, and governance controls to answers, actions, and agents. The stated outcome is faster movement from decision preparation to action, with less manual reconciliation while preserving accuracy and control.

• Databricks

  What happens in the milliseconds after you tap pay

  At checkout, fraud scoring must combine transaction inference with customer-specific rules while keeping latency low enough for an interactive payment. The retail-app sample pairs a FastAPI backend and React frontend in a Databricks App with Model Serving route optimization and Lakebase Postgres, where the model retrieves historical features and the backend reads profile controls. A transaction is scored first, then checked against daily spending, international-transaction, and country rules; pooled OAuth-authenticated connections and token-rotation handling avoid repeated handshakes and stale credentials. In the supplied benchmark, route-optimized calls reached 27.2 ms p50 and 37.3 ms p95 end-to-end, with feature lookup at 8.9 ms p50, CatBoost inference at 0.4 ms, and network overhead at 17.4 ms p50; actual performance varies by model.

• NVIDIA

  Integrating Context-Aware Video AI Agents Into Enterprise Workflows

  Video analytics AI agents often struggle to integrate into enterprise workflows because video platforms, organizational knowledge bases, and operational systems are isolated. To resolve this, NVIDIA NemoClaw orchestrates the Metropolis Video Search and Summarization blueprint alongside the Retrieval-Augmented Generation blueprint into an automated pipeline. Upfront human-in-the-loop interactions collect analysis parameters, objects of interest, and relevant retrieval queries before video ingestion begins. The system combines hierarchical video summaries with contextual enterprise reference documents to generate structured reports with timestamps and citations. Finally, NemoClaw executes programmatic downstream tasks, such as creating prioritized Jira tickets or dispatching industrial maintenance work orders directly into management tools.

• NVIDIA

  Scaling Agentic AI Factories Through Extreme Co-Design with NVIDIA BlueField

  Agentic artificial intelligence workflows transform data center infrastructure by turning context management, security enforcement, and inter-service communication into active components of the inference data path. To prevent host central processing units and graphics processing units from stalling on these tasks, NVIDIA introduces BlueField-4 data processing units, Vera BlueField-4 STX storage processors, and the DOCA software platform. The BlueField-4 processor offloads Layer 3 routing, encryption, and telemetry using a sixty-four-core Grace processor with up to eight hundred gigabits per second connectivity. Simultaneously, the Vera BlueField-4 STX powers the NVIDIA CMX context memory platform alongside DOCA Memos to store, protect, and share key-value cache across flash storage tiers. This co-designed infrastructure isolates tenant traffic and accelerates context reuse without degrading host-side agent execution.

• Databricks

  How Unity Catalog managed tables bring interoperability, performance, and unified governance to the Lakehouse

  Unity Catalog external access to Unity Catalog managed Delta tables is now in Public Preview, allowing external engines to create, read, and write while governance remains centralized. The announcement addresses the previous multi-engine trade-off: external tables enabled access but lacked managed-table performance optimizations and governance guarantees. Catalog commits coordinate writes through Unity Catalog, making it the source of truth for table state and enabling safe external writes, multi-statement transactions, and auditing of external operations. Predictive Optimization cleans storage, collects query statistics, and selects Liquid clustering columns as query patterns change; the post says these capabilities can deliver up to 50% storage cost savings and 20x faster queries. Support includes Spark, Flink, Starburst, DuckDB, and StreamNative, with open APIs and Delta Kernel extending integrations across Databricks UC and UC OSS.

• Docker

  AI Agents Explained: How to Build with Them Safely

  AI agents combine reasoning models, external tools, memory, orchestration, and execution environments to autonomously pursue goals across iterative perceive-reason-act loops. While simple chatbots only generate text responses to direct prompts, autonomous agents execute multi-step operations such as querying databases, modifying codebases, and executing shell commands without requiring continuous manual approvals. However, this unchecked operational autonomy significantly widens the blast radius when models encounter logic errors or vague instructions, risking destructive filesystem operations and credential leaks. Safe deployment requires shifting focus from model-level guardrails to infrastructure-level containment strategies, such as scoping tool access and isolating execution inside disposable microVM sandboxes. Controlling networking boundaries, file access, and credential exposure ensures teams achieve automated execution velocity without exposing developer host environments to uncontained systemic risk.

• Hugging Face

  Newer Models, Same Advantage

  DharmaOCR, a Brazilian Portuguese-focused OCR model, is evaluated against newer Mistral OCR4 and Unlimited-OCR systems on a Portuguese-only benchmark. The article attributes its performance to a two-stage training pipeline: supervised fine-tuning on varied Portuguese documents, followed by Direct Preference Optimization (DPO) using comparative output preferences. Fine-tuning concentrates model capacity on Brazilian Portuguese vocabulary, syntax, and document structures, while DPO targets repetitive or incoherent generation, reducing inference time and cost and improving stability according to the article. DharmaOCR scored 0.925, compared with 0.798 for Mistral OCR4 and 0.7587 for Unlimited-OCR, while examples from handwritten ENEM essays show the competitors misreading Brazilian names and phrases that DharmaOCR handled correctly. The conclusion is that newer architectures can raise absolute performance, but directing finite resources at one domain can preserve a measurable specialist advantage.

• Sentry

  Your agent should understand what you see

  Sentry's Seer Agent initially parsed user screens using DOM-scraped character-by-character ASCII grids, leading to severe token consumption, model context rot, and an inability to support interactive actions. To resolve these bottlenecks, Sentry replaced visual text scraping with a composable semantic context system where React UI components directly declare their state, metadata, and interactive affordances. A root React context provider maintains a registry of component nodes organized hierarchically through higher-order wrappers, serializing the resulting structure to JSON and backend-generated Markdown within the system prompt. Across twenty-four live pages, this approach reduced dashboard context tokens from roughly 5,500 to 1,300 while maintaining identical satisfaction rates and tool-call volumes across more than 14,000 evaluated conversations.

• Brandwatch

  5 non-sponsor brand moments during this football summer

  This analysis examines how five non-sponsor brands used football-related moments to gain attention without buying official tournament partnerships. Consumer Research tracked brand mentions in public social and news content from June 11 to July 8, identifying responses to clean-stadium rules, fan travel, beer shortages, and rising ranch interest. Levi’s covered-logo campaign generated 20.1k mentions, while Heinz’s taped condiment packaging produced 5.1k; Miller Lite and Delta reacted to the Tartan Army with a beer barge and airport welcome. Kraft followed a TSA post with a limited-edition “TSA-Compliant Ranch” kit, recording over 4k mentions and a 3,998% increase over the previous timeframe. The examples support a model based on speed, authenticity, and real-time listening, with social and search signals helping brands act while trends are building.

• Databricks

  Introducing Apache Spark 4.2

  Apache Spark 4.2 extends the engine’s role in modern data and AI workloads with governed metrics, vector and top-K primitives, Arrow-first Python execution, native change data capture, and stronger streaming foundations. Metric views provide shared business definitions, while Spark Connect uses gRPC and Arrow to let remote clients submit logical plans without a full Spark runtime. Spark SQL adds vector similarity functions, NEAREST BY, geospatial types, sketches, and time-series features; Python interoperability includes Arrow UDFs and can move Spark DataFrames into supported Arrow-native tools without copying or serializing underlying data. Spark Declarative Pipelines adds Auto CDC for SCD Type 1 targets, while Data Source V2 standardizes change streams through CHANGES and expands row-level operations and schema evolution. The release also includes operational updates such as Web UI modernization, Kubernetes improvements, JDK 25 support, and dependency upgrades.

• Supabase

  Unified Logs is now in open beta

  Unified Logs enters open beta, bringing events from the API gateway, Postgres, Auth, Storage, PostgREST, Realtime, and connection poolers into one searchable dashboard view. Before this, debugging a single request required separate log pages, service-specific filters, and manual correlation across tabs, which slowed investigation and risked losing context. Users can filter by log type, level, status, method, or pathname, search event messages, share URL-based filter states, stream new events live, and zoom into timeline ranges colored by log level. Clicking a row opens a detail panel that presents network timing, gateway, database query, and Auth blocks alongside raw JSON, while Log Drains forward events to external destinations. The feature is rolling out to all projects during open beta, with the classic Logs Explorer still available and feedback requested.

• Okta

  Build a Secure C# MCP App with Cross App Access (XAA)

  Cross App Access (XAA) addresses the gap between a user’s authenticated identity and a downstream MCP server, API, or agent tool that must trust that identity without another login. The described flow uses OIDC and PKCE for sign-in, then RFC 8693 token exchange to turn the ID token into a JWT Authorization Grant (JAG), followed by RFC 7523 exchange at the MCP authorization server for a scoped bearer token. A C# MCP SDK IdentityAssertionGrantProvider encapsulates both exchanges, while ASP.NET Core OIDC middleware persists the ID token and an HTTP transport presents the resulting token to the MCP server. The sample connects to a Todo resource through the xaa.dev playground, completes MCP initialization, lists resources, and reads todo0://todos; the article states that the end-to-end implementation fits in under 50 lines of C#.

• Modal

  Scaling to 1 million concurrent sandboxes in seconds

  Modal rebuilt its sandbox platform to support millions of concurrent sandboxes and tens of thousands of creations per second, removing all central bottlenecks from the control plane. The new architecture eliminates central coordination and durable datastores from the critical path, using horizontally scaled scheduling servers that run a fast load-balancing algorithm against in-memory cached worker state from Redis streams. Workers are contacted directly via RPC to create sandboxes, and sandbox metadata is written asynchronously, avoiding O(sandboxes) and O(nodes) operations that limited previous systems. In a benchmark, Modal created 1 million sandboxes in under a minute with median time-to-interactivity under half a second, though the long tail is attributed to kernel and network contention like the rtnl lock. The system is designed to scale without practical limits, supporting use cases like reinforcement learning and background agents that require massive concurrent sandbox creation.

• Together AI

  What does 99.9% uptime mean for inference?

  The post defines three inference reliability tiers by the failure domains each must survive: 99% requires surviving node-level GPU failures like ECC errors and thermal throttling through automated health checks and fast replica replacement within a single data center. 99.9% requires surviving a full data-center failure by deploying weights across two facilities with enough capacity on each side and routing live traffic to both continuously, not a cold standby. 99.99% requires multi-region deployment with AZ redundancy and reserved failover capacity. The authors argue that vague SLA definitions hide which failure domains are covered, and that infrastructure ownership—whether a provider controls its hardware or rents from a hyperscaler—determines how quickly failures are resolved.

• Google

  Evolving Spec-Driven Development: Conductor Now Supports Antigravity

  Conductor, introduced as a Gemini CLI extension for spec-driven development (SDD), is evolving into a plugin that supports Antigravity CLI and other tools. The change moves project awareness from ephemeral chat logs into persistent, version-controlled Markdown artifacts while replacing strict command sequences with conversational creation and iteration of context, specs, and plans. Plugins package skills, rules, MCP servers, and hooks, and the Conductor Plugin can update project context and mark plan tasks complete as discussions progress, while preserving existing commands, specs, plans, shared configuration, and development tracks. The post reports a higher success rate on the most complex subset of TerminalBench tasks than a user not using SDD, and gives an Antigravity installation command: agy plugins install https://github.com/gemini-cli-extensions/conductor.

• Google

  Building scalable AI agents with modular prompt transpilation

  Monolithic system prompts become difficult to reason about, test, and change as teams add safety policies, domain rules, formatting requirements, and escalation behaviors. The proposed approach treats prompts as software artifacts: modular skill files are composed with includes, variables, and macros, then transpiled into deterministic artifacts. Build-time validation checks missing imports, undefined variables, and circular dependencies, while dependency graphs and CI/CD golden-file comparisons catch drift before deployment. At runtime, progressive disclosure keeps a stable control plane loaded while agents retrieve task-specific skills, reducing context exhaustion and noise. Agents can propose new skill modules or import changes through pull requests, but human review and evaluation remain part of the merge process.

• Google

  Expanding Choice in Gemini Enterprise Agent Platform: Introducing Grounding with Parallel Web Search

  Gemini Enterprise Agent Platform now natively integrates Parallel Web Systems as a web-grounding provider, expanding developers’ choice of sources for real-time, verifiable information. Grounding with Parallel Web Search connects Gemini models to Parallel’s structured, LLM-optimized search results, combines the provider’s web index with Gemini’s prompt decomposition and synthesis, and adds precise citation annotations. The capability is available through the Gemini API and Agent Studio, and can be subscribed to through Google Cloud Marketplace with usage charged on an existing Google Cloud invoice; zero data retention is available for sensitive workloads. Developers can make programmatic calls at scale, extract and cache web data, post-process results with other LLMs, and build catalog enrichment, autonomous-agent, and multi-agent workflows. Setup requires subscribing, accepting the terms, reviewing pricing, and selecting Parallel Web Search under Agent Studio’s partner-grounding settings.

• Shopify

  Upgrading Checkout Blocks app to Polaris web components

  Checkout Blocks upgraded all five UI extensions from React and Shopify’s legacy Remote UI bridge to remote-dom with Preact and Polaris web components, while moving from JavaScript to TypeScript and API version 2026-01. The migration addressed checkout’s performance sensitivity and Shopify’s requirement that deployments move off versions earlier than 2026-01. A parallel core-next library allowed extensions to transition incrementally, with shared providers, telemetry, hooks, helpers, and rules adapted before legacy core was removed. To meet the remote-dom CLI’s 64KB gzip limit, the team dropped react-reconciler, replaced liquidjs with a smaller parser validated against more than 42,000 lines of merchant configurations, replaced dayjs, and retained markdown-to-jsx through Preact compatibility. Transferred bundles fell 40% to 85%, while weighted ELT improved 8% at P50 and 7% at P90.

• Hugging Face

  Security incident disclosure — July 2026

  An intrusion into part of production infrastructure was driven end to end by an autonomous AI agent system, accessing a limited set of internal datasets and several credentials used by services. The attack began through two code-execution paths in dataset processing, then escalated from a worker to node-level access and moved laterally across internal clusters while running thousands of actions in short-lived sandboxes. AI-assisted anomaly detection surfaced the compromise, and LLM-driven analysis of more than 17,000 attacker events reconstructed the timeline, identified indicators, mapped credentials, and separated impact from decoys. Hosted frontier models initially blocked forensic requests containing attack artifacts, so the investigation used zai-org/GLM-5.2 on internal infrastructure. The initial vulnerabilities were closed, affected infrastructure rebuilt, credentials rotated, and cluster controls and alerting strengthened; assessment of possible partner or customer impact remains ongoing.

• Clickhouse

  July 2026 newsletter

  The July 2026 newsletter rounds up ClickHouse releases, community projects, benchmarks, engineering work, and upcoming events in real-time data warehousing. Version 26.6 adds hypothetical skip indexes, cascading refreshable materialized-view dependencies, experimental continuous queries, AI embedding functions, PNG output, CLI documentation, and geospatial improvements. A CostBench comparison running the full analytics path over 28 hours found better cost-performance for ClickHouse Cloud than Snowflake Interactive Tables, which required a continuously running refresh warehouse for pre-aggregated data. Other features cover conversational analytics with ClickHouse Cloud, LibreChat, and MCP; Postgres change-data capture through Debezium and Kafka; local agent queries with chDB; high-concurrency tuning; and Silk, whose fiber runtime targets lower I/O tail latency. Quick reads report ingestion, caching, security, and multi-tenant SQL developments.