---
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

### [LLM Vs AI: A Practical Guide to Differences, Use Cases, and Tools](https://yomu.fyi/post/llm-vs-ai-a-practical-guide-to-differences-use-cases-and-tools.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Databricks Staff
- Published: May 1, 2026
- Type: Explainer

This guide distinguishes artificial intelligence, a broad field covering systems that perform tasks associated with human intelligence, from large language models (LLMs), specialized generative AI models for language and code. It places LLMs within generative AI and deep learning, and explains how transformer self-attention processes tokens while training data, parameter scale, and context windows shape capability and limitations. Examples include content drafting, code generation, translation, customer-service chatbots, sentiment analysis, extraction, summarization, and tool-connected agentic workflows, while traditional machine learning remains suited to structured labels and numeric predictions. It recommends retrieval-augmented generation, human review, bias testing, privacy controls, and evidence-based pilots with defined workflows, metrics, budgets, realistic data, and logged outputs.


### [Model risk governance is not the same as risk intelligence](https://yomu.fyi/post/model-risk-governance-is-not-the-same-as-risk-intelligence.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Kim Hatton
- Published: May 1, 2026
- Type: Explainer

Financial institutions have invested heavily in model governance frameworks, stress testing infrastructure, limit monitoring, data feeds, and dashboards, but risk leaders may still lack fast access to what those models are telling them. When a CRO must assess credit concentration, scenario sensitivity, or relationships between market positions and credit exposures, answering can require navigation across model outputs, analyst interpretation, and disconnected data systems. The proposed approach uses Databricks AI/BI Genie to let leaders query risk data in natural language, while retaining access controls, audit logging, Unity Catalog lineage, cross-risk data, and stress-test outputs in one environment. The stated distinction is that governance establishes necessary controls, whereas conversational risk intelligence supports questions that fixed dashboards did not anticipate, including comparisons with internal limits.


### [Generative AI for Business: A Complete Strategy and Implementation Guide](https://yomu.fyi/post/generative-ai-for-business-a-complete-strategy-and-implementation-guid.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Databricks Staff
- Published: May 1, 2026
- Type: Explainer

Generative AI is presented as an enterprise technology shift with potential value across customer operations, marketing and sales, software engineering, and research and development, which together are described as accounting for approximately 75% of use-case value across industries. The guide distinguishes generative systems, which create text, images, code, audio, or structured data from predictive models, and explains how foundation models and LLMs support open-ended business applications. Its implementation strategy prioritizes reliable data infrastructure, high-impact low-complexity pilots, and governance covering sensitive data, model limitations, monitoring, human review, and compliance. Recommended execution includes a cross-functional squad, predefined KPIs, user training, baseline measurements, and a 90-day executive review with scale, iterate, or discontinue decisions. Retrieval-augmented generation is identified as the most widely adopted way to reduce hallucinations by grounding responses in verified proprietary data, while ROI is expected within six to twelve months for a well-structured pilot.


### [Data Science vs Data Engineering: Choosing Analysis or Infrastructure](https://yomu.fyi/post/data-science-vs-data-engineering-choosing-analysis-or-infrastructure.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Databricks Staff
- Published: May 1, 2026
- Type: Explainer

This guide distinguishes data engineering from data science by their roles in the data value chain. Data engineers build and maintain ingestion pipelines, warehouses, lakes, access controls, and production systems, using tools such as SQL, Python, Scala, Java, Apache Spark, Kafka, orchestration platforms, and cloud infrastructure. Data scientists work with clean, accessible data to perform exploratory analysis, engineer features, train and validate statistical or machine-learning models, and communicate findings through visualization and storytelling. The roles collaborate through feedback on data quality, shared documentation, model deployment infrastructure, and versioned schemas, feature pipelines, and experiments. For choosing a path, the guide recommends trying a two-week pipeline project and a two-week ML project; it also outlines portfolio deliverables for each and says both roles require strong analytical and computer-science fundamentals.


### [AI Applications: Tools, Use Cases, and Platforms](https://yomu.fyi/post/ai-applications-tools-use-cases-and-platforms.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Databricks Staff
- Published: May 1, 2026
- Type: Explainer

The guide maps AI applications for data scientists, machine learning engineers, and technical leaders, covering predictive AI, generative AI, conversational AI, and autonomous agents across consumer, developer, and enterprise settings. It distinguishes consumer-facing tools from developer platforms and describes production concerns including model lifecycle management, vector search, data lineage, deployment, monitoring, governance, and evaluation. Generative systems create text, images, code, audio, and video from prompts, while large language models and mixture-of-experts architectures are presented as important foundations for enterprise applications; open models offer control over weights, governance, and deployment. The guide recommends defining use cases, assessing data readiness, and building privacy, bias-auditing, and monitoring controls before production, while noting that agents coordinate multi-step workflows across tools, APIs, and databases.


### [Database modeling: a practical guide to techniques and best practices](https://yomu.fyi/post/database-modeling-a-practical-guide-to-techniques-and-best-practices.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Databricks Staff
- Published: May 1, 2026
- Type: Tutorial

Database modeling defines the structure, relationships and constraints that keep systems coherent across transactional, analytical and flexible workloads. The guide presents a three-phase design process: conceptual modeling captures entities and relationships, logical modeling adds attributes, keys, cardinality and normalization, and physical design translates that model into tables, indexes, constraints, partitioning and other platform-specific choices. It compares relational, document/NoSQL, dimensional, hierarchical and network models, linking each to data shape, workload and consistency requirements. It recommends explicit keys, consistent naming, appropriate normalization, query validation and version-controlled DDL, while warning against premature physical design, missing foreign keys, unclear NULL handling and poorly balanced schemas. It concludes that Databricks Lakebase combines a transactional database engine with the Databricks Lakehouse Architecture so one model can support operational and analytical workloads.


### [MLOps vs DevOps: A Practical Guide for Data Scientists and IT Teams](https://yomu.fyi/post/mlops-vs-devops-a-practical-guide-for-data-scientists-and-it-teams.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Databricks Staff
- Published: May 1, 2026
- Type: Explainer

The guide compares DevOps and MLOps, framing both as practices for reliable production systems but distinguishing traditional application code from machine-learning systems involving data and models. DevOps uses source control, automated testing, staging, and CI/CD, while MLOps governs the “holy trinity” of code, data, and models through separate versioning, quality checks, lineage, and access controls. Its central operational difference is Continuous Training: MLOps pipelines can validate model quality, monitor drift, and trigger retraining when data distributions shift, alongside testing model-serving infrastructure and promoting models through a registry. The guide also assigns responsibilities across data scientists, ML engineers, data engineers, and IT operations, and recommends dedicated MLOps for business-critical, frequently retrained models, DevOps for applications without ML, and split pipelines for hybrid products.


### [Top Data Warehouse Tools For Modern Data Analytics](https://yomu.fyi/post/top-data-warehouse-tools-for-modern-data-analytics.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Databricks Staff
- Published: May 1, 2026
- Type: Explainer

Data warehouse tools are presented as a strategic choice for analytics and ML teams facing fragmented estates of warehouses, lakes, and standalone ML systems. The guide proposes evaluating platforms across query performance, scalability, data integration, BI connectivity, total cost of ownership, and governance and security, with attention to MPP, columnar storage, and decoupled compute and storage. It contrasts traditional warehouses, data lakes, and lakehouses: warehouses favor structured SQL analytics, lakes offer native-format flexibility but weaker quality and performance guarantees, and lakehouses combine these capabilities using open formats such as Delta Lake and Apache Iceberg. The stated conclusion is that a lakehouse can provide a single governed foundation for SQL, BI, streaming, ML, and AI workloads, while teams should select tools according to workload, scale, budget, and future AI needs.


### [Agentic AI vs Generative AI: Comparing Autonomy, Workflows, and Use Cases](https://yomu.fyi/post/agentic-ai-vs-generative-ai-comparing-autonomy-workflows-and-use-cases.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Databricks Staff
- Published: May 1, 2026
- Type: Explainer

Agentic AI and generative AI differ primarily in whether a system autonomously pursues a multi-step goal or produces content in response to a prompt. The post defines agentic systems through a perceive-plan-act cycle: agents maintain memory and state, decompose goals, call tools or sub-agents, evaluate conditions, and recover from errors, while generative AI typically performs bounded, reactive inference. It presents workflow examples such as sales follow-up and market-intelligence summarization, showing how APIs connect agents to CRMs, databases, communication platforms, and news services while LLMs provide text generation or reasoning at individual steps. RAG can ground generative outputs in external knowledge, but agentic deployments add operational concerns around repeated inference loops, human oversight, provenance logging, and access controls. The conclusion recommends choosing by task structure: generative AI for single-turn creation or summarization, agentic AI for autonomous coordination, and both together for complex enterprise workflows.


### [Welcoming Pedro Ivo Hudson, our new Design Engineer](https://yomu.fyi/post/welcoming-pedro-ivo-hudson-our-new-design-engineer.md)
- Company: [Resend](https://yomu.fyi/company/resend.md)
- Published: May 1, 2026
- Type: Announcement

Resend welcomes Pedro Ivo Hudson as a design engineer, presenting him as someone who has worked across design and code for more than 15 years, before the title was common. He began with Macromedia classes aimed at Flash animation, learned tools including Freehand, Fireworks, Dreamweaver, HTML, and CSS, then built WordPress sites and studied graphic design at university. His work includes The Good Man, a web experiment combining code, design, and storytelling, while his motivation for joining Resend includes its people, leadership, design team, and the opportunity to work directly with code under an engineer title. He advises ambitious designers to master fundamentals, seek out people they admire, keep producing work, and develop the extroversion and persuasion needed to bring designs into the world.


### [Goodbye limitations, hello data: How Qonto is rethinking observability with ClickHouse Cloud](https://yomu.fyi/post/goodbye-limitations-hello-data-how-qonto-is-rethinking-observability-w.md)
- Company: [Clickhouse](https://yomu.fyi/company/clickhouse.md)
- Author: ClickHouse Team
- Published: May 1, 2026
- Type: Problem & solution

Qonto struggled with slow queries, system instability, and aggressive data sampling when handling distributed traces in Grafana Tempo. To enable wide-event querying without strict cardinality limits, the team migrated their telemetry storage to ClickHouse Cloud. Telemetry from applications, Kubernetes, and GitHub routes through OpenTelemetry collectors over AWS PrivateLink into ClickHouse, while Grafana remains the primary dashboard interface. By compressing 231 TB of uncompressed trace attributes down to 376 GB, Qonto achieved substantial storage savings and integrated an AI incident companion using the ClickHouse Model Context Protocol. The new architecture eliminated cardinality policing, allowed product and support teams to self-serve incident investigations, and enabled real-time streaming pre-aggregations using Apache Flink.


### [How Ansible® Automation Powers the Uber Corporate Network at a Global Scale](https://yomu.fyi/post/how-ansible-automation-powers-the-uber-corporate-network-at-a-global-s.md)
- Company: [Uber](https://yomu.fyi/company/uber.md)
- Published: Apr 30, 2026
- Type: Explainer

Uber’s corporate network spans offices across six continents and around 5,000 devices, creating a configuration-management problem involving continuous updates, regional variation, and hardware from multiple vendors. The post explains why Uber uses Ansible for on-premises network configuration while Terraform handles cloud provisioning and Puppet manages configuration on running machines. Its Daily Nightly Enforcement workflow backs up each region’s running configuration to a private GitHub repository, gathers device facts, renders vendor-specific golden configurations through inventory variables and Jinja templates, and pushes them overnight, with failures triggering alerts. Inventory groups encode desired state across regions, functions, and operating systems, while custom roles, formatters, cleanup jobs, and occasional Ansible or Python modules address scale and vendor-specific gaps. The conclusion says this automation makes the diverse network manageable, stable, updated, and ready for daily use, although some hardware still requires other portals.


### [City of Boston Delivery Insurance Addendum January 9, 2026](https://yomu.fyi/post/city-of-boston-delivery-insurance-addendum-january-9-2026.md)
- Company: [Uber](https://yomu.fyi/company/uber.md)
- Published: Apr 30, 2026
- Type: Announcement

Effective January 9, 2026, this City of Boston addendum describes insurance Portier, LLC and/or Schleuder, LLC maintains for delivery services performed under its agreements. For motorized bicycles below 30 mph and transportation modes requiring registration under M.G.L. c. 90, § 1A, coverage is $50,000/$100,000/$50,000 while available before matching, then $1 million for death, bodily injury, and property damage after accepting a request until delivery completion or cancellation; physical-damage coverage may apply with a $2,500 deductible when personal comprehensive and collision coverage exists. For electric bicycles below 30 mph, accepted-trip coverage is $50,000/$100,000/$30,000. No other periods are covered, personal policies may exclude delivery activity, and the Company may verify insurance information.


### [Unlocking SAP business context in Databricks with semantic metadata Delta Sharing](https://yomu.fyi/post/unlocking-sap-business-context-in-databricks-with-semantic-metadata-de.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Akram Chetibi, Katie Cummiskey, Moe Derakhshani, Abhijit Chakankar
- Published: Apr 30, 2026
- Type: Announcement

SAP Business Data Cloud now offers generally available semantic metadata synchronization with Databricks Unity Catalog for mounted SAP BDC Delta Shares. When a table is accessed, Unity Catalog receives table-level business-friendly display names, descriptions, context, and governance tags, while SAP BDC remains the single source of truth and subsequent changes are reflected. The capability builds on BDC Connect and Delta Sharing, allowing governed SAP data products to be discovered and combined with other enterprise sources without recreating business context or governance separately. Column descriptions, table relationships such as primary and foreign keys, and PersonalData namespace tags give Databricks AI Assistant and AI/BI Genie explicit context for natural-language questions and join-ready queries. The stated result is more understandable, discoverable, and AI-ready SAP data, with automated classification signals supporting compliance, access control, and responsible AI.


### [Ready, Set, Build with the NHS Federated Data Platform](https://yomu.fyi/post/ready-set-build-with-the-nhs-federated-data-platform.md)
- Company: [Palantir](https://yomu.fyi/company/palantir.md)
- Author: Palantir
- Published: Apr 30, 2026
- Type: Explainer

The NHS Federated Data Platform (NHS FDP), delivered by NHS England through a consortium led by Palantir, connects operational data held in separate NHS systems while keeping each organisation’s data under local control. Built on Palantir Foundry, its federated tenants use the Canonical Data Model, encryption, purpose-based access, and Privacy Enhancing Technology for national data flows. As of end December 2025, the post reports 110,078 additional theatre procedures, 797,728 patients safely removed from waiting lists, and 297,943 safely discharged patients, alongside around a 15% reduction in observed discharge delays. The inaugural Build with FDP hackathon brought together over 120 NHS developers and analysts, who built 25 working prototypes on a notional Canonical Data Model to address frontline operational challenges. Projects included early-warning, bed-demand prediction, CAMHS demand balancing, and genomic-optimised waitlist tools.


### [Validating Bounding Box Annotations](https://yomu.fyi/post/validating-bounding-box-annotations.md)
- Company: [Uber](https://yomu.fyi/company/uber.md)
- Published: Apr 30, 2026
- Type: Explainer

Video bounding-box annotations can contain ID swaps and position jumps that degrade training data for object-tracking models, especially when long videos are split among annotators and later merged. Uber's system runs in uLabel, combining visual, motion, and coordinate features from an 11-frame sliding window with an XGBoost classifier trained on synthetic anomalies from six open-source datasets. It scores each frame for error probability, then groups predictions with frame-index and confidence clustering into regions that operators can review, fix, or dismiss. The current iteration prioritizes jump and ID-swap detection, while freeze and scale/aspect errors remain planned for future releases; the deployed workflow is intended to reduce the cost and time of sequential edit-review while processing client data statelessly without retaining it or using it to train models.


### [The marketing activation gap has a fix: Databricks and Stitch partner to turn data infrastructure into marketing performance](https://yomu.fyi/post/the-marketing-activation-gap-has-a-fix-databricks-and-stitch-partner-t.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Michael Burton, Bobby Tichy, Katy Yuan
- Published: Apr 30, 2026
- Type: Announcement

Databricks and Stitch are partnering to connect enterprise data infrastructure with marketing execution, addressing a gap that leaves campaigns dependent on stale segments, delayed data, and disconnected tools. The partnership positions Stitch as a marketing implementation layer that structures Databricks data for real-time segmentation, personalization, AI-driven decisioning, and self-service analytics while building applications and agents directly on the platform. Its work spans campaign-ready architecture, full-stack marketing applications, Genie-based access for nontechnical users, AI-powered campaign operations, and migrations from legacy platforms. Examples include real-time transaction data reaching customer marketing at a convenience-store brand, measurable campaign results within weeks for a medical testing company, and a global QSR rebuilding campaign workflows on Databricks as AI tools improve.


### [We Tested Marketing Incentives to AI Agents. Here's What Happened.](https://yomu.fyi/post/we-tested-marketing-incentives-to-ai-agents-here-s-what-happened.md)
- Company: [Ramp](https://yomu.fyi/company/ramp.md)
- Author: Grace Cummins
- Published: Apr 30, 2026
- Type: Benchmark

Ramp tested whether AI agents would relay a tracked referral incentive to people researching spend-management software. Across roughly 50 marketing pages, Cloudflare Workers served bot-specific variants—Markdown, stripped HTML, or schema-heavy content—while unique URLs and logs attributed downstream activity. Markdown surfaced most reliably, and bot classification proved difficult: major assistants were labeled “AI Assistants,” OpenAI SearchBot cached aggressively, and DeepSeek required TLS fingerprinting plus ASN detection. Over 32 days, agent relays rose from roughly 40 at 2.5 weeks to nearly 10 times that total, with Claude responsible for most matches; Perplexity moved from vague references to one specific branded mention, while ChatGPT remained at zero. The experiment concludes that agents can relay offers, but model-specific content strategies, citation-aware page selection, and better attribution are still needed.


### [Alert fatigue is a business risk](https://yomu.fyi/post/alert-fatigue-is-a-business-risk.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Taylor Kain
- Published: Apr 30, 2026
- Type: Announcement

Enterprise security operations centers may receive tens of thousands of alerts daily, making prioritization necessary and leaving lower-priority signals uninvestigated. Alert fatigue is presented as a data architecture problem: fragmented endpoint, network, identity, and cloud telemetry, combined with proprietary SIEM collection-and-discard practices, limits correlation and overwhelms analysts. Lakewatch proposes an open lakehouse foundation that unifies security, IT, and business telemetry, applies automated OCSF normalization, and uses Agent Bricks for data wrangling and alert triage. Databricks Genie is positioned as a natural-language AI security agent whose autonomous agents can hunt, summarize, and neutralize threats, while Unity Catalog logs queries and actions for audit and forensic purposes. Lakewatch is currently available in Private Preview.


### [Continually improving our agent harness](https://yomu.fyi/post/continually-improving-our-agent-harness.md)
- Company: [Cursor](https://yomu.fyi/company/cursor.md)
- Author: Stefan Heule & Jediah Katz
- Published: Apr 30, 2026
- Type: Explainer

Cursor describes its agent harness as an iterative product process: vision-driven hypotheses are tested through offline evals, real-world A/B experiments, and instrumentation. Its context strategy has shifted from static codebase context and guardrails toward dynamic retrieval as models improve, while model-specific prompts and tools match training conventions. Quality measurement combines CursorBench with latency, token efficiency, tool-call errors, cache behavior, code Keep Rate, and language-model analysis of user responses. The team classifies expected and unknown tool errors, uses per-tool and per-model anomaly baselines, and automates log investigations and backlog tickets; one sprint reduced unexpected tool-call errors by an order of magnitude. The harness also supports model switching and subagents, although switching can cause cache misses and summary information loss, and the post argues that multi-agent orchestration will make harness engineering increasingly central.


[Newer posts](https://yomu.fyi/posts/page/134.md) · [Older posts](https://yomu.fyi/posts/page/136.md)