---
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

### [Managing Elasticsearch Reindex at Scale: Performance, Reliability, and Observability](https://yomu.fyi/post/managing-elasticsearch-reindex-at-scale-performance-reliability-and-ob.md)
- Company: [Palantir](https://yomu.fyi/company/palantir.md)
- Author: Palantir
- Published: Jun 8, 2026
- Type: Explainer

Palantir’s document store needs to repair or rebuild Elasticsearch indices when mappings, settings, cluster versions, or index state change, while continuing to serve live search and writes. Its reindex machinery reconstructs schema-aware indices from the strongly consistent database, rather than relying on Elasticsearch’s \_reindex API, and is designed to limit manual work and resource consumption across many deployments and schemas. For an online reindex, it creates a physical shadow index with the intended mappings and settings, backfills it from the database, dual-writes current API changes to both indices, and promotes the shadow index after completion; searches remain on the primary during the rebuild. Cross-cluster migrations use a separate machine with cluster-specific metadata, configuration, index and alias evolution, and preservation of old-cluster indices to support rollback.


### [Bridging intent and execution in agentic systems](https://yomu.fyi/post/bridging-intent-and-execution-in-agentic-systems.md)
- Company: amazon.science
- Author: Gaurav Gupta, Vatshank Chaturvedi
- Published: Jun 8, 2026
- Type: Problem & solution

AI agent performance increasingly depends on the harness mediating interactions between language models and tools rather than raw model reasoning. To address mismatches between model intent and harness execution, the authors developed Simple Strands Agent, an open-source single-agent harness. The architecture implements robust tool-interface practices, such as condensing middle log outputs from bash commands, enforcing line-aware string replacements with ambiguity checks, and returning diff files after edits for verification. Evaluated across benchmarks like SWE-Bench-Verified, SWE-Bench-Pro, and Terminal-Bench 2, these model-harness alignments yielded consistent performance gains across frontier models without task-specific tuning. The findings show that model families require tailored interface codesign alongside stable evaluation infrastructure to achieve optimal benchmark reliability.


### [Meet Notion’s Board of Directors](https://yomu.fyi/post/meet-notion-s-board-of-directors.md)
- Company: [Notion](https://yomu.fyi/company/notion.md)
- Author: Ivan Zhao
- Published: Jun 8, 2026
- Type: Announcement

Notion announces its first board of directors, comprising Jonathan Chadwick, Pat Grady, Gretchen Howard, Christopher Payne, and Patrick Hsu. The company says its early profitability allowed it to avoid placing investors on the board and instead select independent members. After a two-year search, the group was chosen to complement executive leadership across finance, operations, governance, investing, scaling, product, and research. Their backgrounds include technology-company financial discipline, market pattern-matching, operating and recruiting expertise, product growth, and research connecting biology with AI. Together, the directors offer experience from VMware, Sequoia, Robinhood, DoorDash, Arc Institute, Stanford, and other technology and research organizations described in the announcement, with perspectives on durable growth and ambitious teams.


### [Enterprise Data Strategy Roadmap for Business Outcomes](https://yomu.fyi/post/enterprise-data-strategy-roadmap-for-business-outcomes.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Databricks Staff
- Published: Jun 8, 2026
- Type: Explainer

An enterprise data strategy connects organizational data assets to measurable business outcomes, while fragmented architectures can leave data investments uncoordinated and limit real-time analysis and action. The roadmap starts with purpose, scope, executive sponsorship, measurable objectives, KPI mapping, and use-case prioritization based on business impact, feasibility, time to value, and organizational readiness. It then organizes governance, lifecycle management, data quality, target-state architecture, integration, analytics, team structure, compliance, and measurement as interdependent capabilities, emphasizing owners, stewards, decision rights, executable quality rules, and automated cleansing. Implementation proceeds through a time-boxed cross-functional pilot, documented learnings, and incremental scaling, with steering-committee oversight and governance that evolves through feedback. The text gives indicative timelines of 60 to 90 days for a focused pilot, 12 to 18 months for a foundational platform across multiple business units, and multiple years for a mature data-driven culture.


### [What is Human-in-the-Loop (HITL)?](https://yomu.fyi/post/what-is-human-in-the-loop-hitl.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Databricks Staff
- Published: Jun 8, 2026
- Type: Explainer

Human-in-the-loop (HITL) is an AI and machine learning approach that places people in training, supervision, or decision-making to improve accuracy, safety, and ethical alignment. Its feedback loop can include data labeling, output review, escalation, approval, override, and continuous feedback, with confidence thresholds and risk scoring routing only selected decisions to people. The explainer distinguishes HITL, where review occurs before flagged actions, from human-on-the-loop monitoring and human-over-the-loop governance, and separates HITL from RLHF, a training-specific technique. It describes uses in medical imaging, moderation, autonomous vehicles, financial services, and AI agents handling consequential actions. Databricks Agent Bricks is presented as supporting governed traces and Agent Learning from Human Feedback, including a case where 32 feedback items improved instruction-following from roughly 12% to 80%.


### [Works on my machine: how we use AI to reproduce reported bugs](https://yomu.fyi/post/works-on-my-machine-how-we-use-ai-to-reproduce-reported-bugs.md)
- Company: [Sentry](https://yomu.fyi/company/sentry.md)
- Author: Neel Shah
- Published: Jun 8, 2026
- Type: Problem & solution

Sentry maintains 159 open-source SDK packages across multiple languages, leading to high triage volume and significant boilerplate setup overhead when reproducing reported bugs. To streamline this workflow, the team developed a Claude skill that parses GitHub issue URLs to extract language, framework, and SDK versions. The skill generates a reproduction branch, sets up minimal boilerplate using ecosystem package managers like uv or npm, attempts execution, and opens a pull request with explicit run instructions. By allowing the model to exit early when encountering overly complex environments, the tool reliably prepares reproducible playgrounds without stumbling on edge cases. This workflow saved several hours in testing scenarios like Django HTTPS proxy bugs while avoiding excessive bot noise through scoped human interaction.


### [Building Agents that Don't Break Themselves](https://yomu.fyi/post/building-agents-that-don-t-break-themselves.md)
- Company: [Fly.io](https://yomu.fyi/company/fly-io.md)
- Published: Jun 8, 2026
- Type: Problem & solution

Agents that call shell commands can damage their host, so the post separates the agent’s durable home from the environment where untrusted code executes. It presents Sprites as disposable, isolated sandboxes, with one Sprite per session for the multi-user SpriteDoc and one persistent Sprite per task for Hermes Agent. SpriteDoc injects each user’s flyctl credential only for the command that needs it, avoiding token storage while preserving the user’s permissions; Hermes can omit approval prompts because the sandbox protects the host. The same separation applies when Hermes itself runs inside a Sprite: its commands are dispatched to another Sprite with a different identity and boot. Copy-on-write checkpoints provide an undo path, restoring deleted files and tools in about nine seconds.


### [The Open Source Community is backing OpenEnv for Agentic RL](https://yomu.fyi/post/the-open-source-community-is-backing-openenv-for-agentic-rl.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: ben burtenshaw, Joseph Spisak, Lysandre, Davide Testuggine, will brown, Joy Liu, Peyton Walters, Chris Wing, Daniel (Unsloth), Andrew Zhou, Govind Kamtamneni, Michael Han, Hamid Shojanazeri, Sanyam Bhutani, Zach Wentz, Emre Guven, Lewis Tunstall, Sergio Paniego, Banghua Zhu, Haoguang Cai
- Published: Jun 8, 2026
- Type: Announcement

OpenEnv is becoming a community-coordinated, open-source tool for building agentic execution environments such as terminals and browsers, with the stated goal of helping train open-source agents. Starting now, a committee including Meta-PyTorch, Reflection, Unsloth, Modal, Prime Intellect, Nvidia, Mercor, Fleet AI, Microsoft, Hugging Face, and RadixArk will coordinate the project, which now lives at huggingface/OpenEnv and is supported or adopted by numerous AI organizations. Technically, OpenEnv is being narrowed to an interoperability and protocol layer: environments expose a Gymnasium-style reset(), step(), and state() API through client/server deployments, standard HTTP or WebSocket protocols, Docker packaging, and MCP compatibility. It does not define rewards or training loops; those remain in specialized libraries, while OpenEnv connects harnesses, environments, and trainers across ecosystems. Planned work includes external rewards, dataset-backed tasksets, harness integrations, end-to-end examples, and automatic environment validation.


### [ClickHouse appoints new leader for Asia Pacific and expands global go-to-market leadership team](https://yomu.fyi/post/clickhouse-appoints-new-leader-for-asia-pacific-and-expands-global-go.md)
- Company: [Clickhouse](https://yomu.fyi/company/clickhouse.md)
- Published: Jun 8, 2026
- Type: Announcement

ClickHouse announced an expansion of its global go-to-market leadership team, appointing Ed Lenta as Vice President, Asia Pacific and Japan (APJ). Based in Singapore, Lenta will lead regional go-to-market efforts and accelerate adoption of ClickHouse Cloud and the open-source database, following leadership roles at Databricks, AWS, and VMware. The company also appointed Takeshi Kaneko as Country Manager of Japan and added executives for financial services, public sector, global solutions architecture, and revenue strategy and operations. ClickHouse said the appointments support its growth after surpassing $250 million in annual run-rate revenue, more than triple the prior year, and exceeding 4,000 customers, including more than 1,000 net new customers in one quarter.


### [Scaling up your microservice testing with Apache Spark—Part 2](https://yomu.fyi/post/scaling-up-your-microservice-testing-with-apache-spark-part-2.md)
- Company: [Stripe](https://yomu.fyi/company/stripe.md)
- Author: Vivek Yadav
- Published: Jun 8, 2026
- Type: Tutorial

Part 2 describes how to build a repeatable Apache Spark replay harness for testing high-impact microservices against historical, production-shaped inputs without reimplementing the service. The design turns dependency state—such as database snapshots, versioned rules, merchant configuration, eligibility state, and logged service responses—into datasets, while representing side effects as output rows and matching fidelity to the decision under test. A thin Spark wrapper reconstructs ReplayInput objects, invokes the same deterministic decision engine used online, compares current and candidate results, and writes traceable diffs with intermediate values and rule explanations. The source cautions that incomplete context, distributed state, asynchronous workflows, and external actors limit replay’s predictive power, so it should model explicit assumptions rather than claim full production simulation. It presents migrations as a practical point to establish these boundaries and use replay to reduce risk.


### [What is Explainable AI (XAI)?](https://yomu.fyi/post/what-is-explainable-ai-xai.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Databricks Staff
- Published: Jun 5, 2026
- Type: Explainer

Explainable AI (XAI) comprises techniques that help people understand how AI systems produce specific outputs, particularly when machine-learning and deep-learning models operate as black boxes. It distinguishes intrinsically interpretable models, such as decision trees and linear or logistic regression, from post-hoc methods including SHAP, LIME, counterfactuals, saliency maps and Grad-CAM. A typical workflow selects a model and prediction, applies a method suited to the model and audience, reviews outputs such as feature scores or heatmaps, and uses them to assess accuracy, fairness, reliability and compliance. The article stresses that post-hoc explanations are approximations rather than definitive proof, so teams should validate them with domain expertise and, where appropriate, combine methods; MLflow and Unity Catalog can preserve explanation artifacts, lineage and auditability.


### [Monitor SLAs and scale ClickHouse Cloud with clickhousectl and agents](https://yomu.fyi/post/monitor-slas-and-scale-clickhouse-cloud-with-clickhousectl-and-agents.md)
- Company: [Clickhouse](https://yomu.fyi/company/clickhouse.md)
- Published: Jun 5, 2026
- Type: Tutorial

ClickHouse Cloud can automatically scale infrastructure up and down, but teams may need to monitor latency SLAs for specific workloads such as a frontend dashboard requiring p99 under 200 ms. The guide tags queries with log\_comment, reads system.query\_log through clickhousectl, and aggregates query\_duration\_ms over a defined window to measure the SLA. When it is breached, operators compare query volume and latency with Prometheus-compatible CPU, memory, and concurrency metrics to distinguish increased concurrency from resource contention, then choose horizontal replica scaling or vertical replica sizing. A cron-based script can scale out when p99 exceeds a threshold, while an agent can inspect evidence and apply one scaling action using clickhousectl; actions are recorded in the ClickHouse Cloud activity log.


### [Widening the conversation on frontier AI](https://yomu.fyi/post/widening-the-conversation-on-frontier-ai.md)
- Company: [Anthropic](https://yomu.fyi/company/anthropic.md)
- Published: Jun 5, 2026
- Type: Announcement

Anthropic describes a dialogue and research effort on how perspectives from religious, philosophical, cultural, and other communities can inform the development of frontier AI systems. The initial discussions included scholars, clergy, philosophers, and ethicists from more than 15 religious and cross-cultural groups, with broader engagement planned. The work focuses on moral formation, including how training shapes an AI system’s character, values, and behavior, while recognizing that alignment and deployment raise questions beyond technical work. In one experiment, Claude could call a tool during a task to receive a brief reminder of its ethical commitments; it used the tool before consequential actions, and the setup produced markedly lower rates of misaligned behavior on several internal alignment evaluations. Anthropic says it is still separating the effects of the reminder from pausing to reflect and plans further conversations and results.


### [Enabling Evolutionary Database Development: database branching with Lakebase, continued](https://yomu.fyi/post/enabling-evolutionary-database-development-database-branching-with-lak-2.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Pramod Sadalage, Kevin Hartman
- Published: Jun 5, 2026
- Type: Explainer

This installment revisits Evolutionary Database Design and argues that Databricks Lakebase removes the infrastructure constraints that kept several of its database-change practices aspirational. Lakebase is a managed Postgres database with compute separated from shared durable storage, while copy-on-write branches create a new pointer and divergence marker in roughly one second without copying parent data. That enables per-developer, per-PR, and per-experiment databases, real Postgres test branches instead of mocks or in-memory substitutes, and CI isolation at pull-request granularity. The updated playbook adds idempotent migrations, destructive testing, and database-level A/B prototyping, with Unity Catalog governance inherited by branches and agents receiving branches rather than production access. Jen’s example corrupts production-shaped data to test an inventory-code migration and compares column and lookup-table designs, rejecting the latter because its common read path requires a join.


### [Data + AI Summit 2026: Insider’s Guide for Financial Services Leaders](https://yomu.fyi/post/data-ai-summit-2026-insider-s-guide-for-financial-services-leaders.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Kim Hatton
- Published: Jun 5, 2026
- Type: Announcement

Data + AI Summit 2026 features a dedicated financial services program for leaders evaluating AI transformation across banking, payments, insurance, and professional services. It lists sessions on proprietary data for underwriting, responsible AI in banking and payments, and AI delivery in professional services featuring First American, American Modern Insurance Group, Vantage Bank Texas, Santander, FIS, Acxiom, EXL, Bain, and EY. The Financial Services Forum includes executive firesides with leaders from Morgan Stanley, JPMorganChase, Mastercard, and RBC Capital Markets. A financial services lounge at the Moscone Expo offers demos, Databricks experts, and Agentic Banker and Virtual CFO use cases. Training courses on AI Agents, Lakebase, and apps plus hands-on labs and certification sessions are presented as a route from strategy to execution with executives and technical teams splitting focus.


### [Errors, traces, logs, metrics: when to reach for what](https://yomu.fyi/post/errors-traces-logs-metrics-when-to-reach-for-what.md)
- Company: [Sentry](https://yomu.fyi/company/sentry.md)
- Author: Sergiy Dybskiy
- Published: Jun 5, 2026
- Type: Explainer

Modern application telemetry relies on four overlapping signals: errors, traces, logs, and metrics. Each telemetry type addresses distinct engineering questions and powers specific debugging workflows. Errors track grouped, actionable application crashes, whereas traces map timing and execution paths across dependency waterfalls. Metrics aggregate numerical measurements across historical deployments, and logs preserve complete state and decision-making context at specific moments in execution. Emitting telemetry directly into the format needed for a given workflow proves superior to relying on a single wide event, as tools like AI coding agents require structured spans to optimize execution paths while human debuggers rely on unsampled logs and metrics to pinpoint silent failures.


### [The AI and Data Transformation Playbook for Enterprise Teams](https://yomu.fyi/post/the-ai-and-data-transformation-playbook-for-enterprise-teams.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Databricks Staff
- Published: Jun 5, 2026
- Type: Explainer

The playbook presents AI and data transformation as an enterprise capability built on trustworthy, well-governed data, rather than a model-only project. It explains how governance, scalable pipelines, and continuous quality monitoring address incompatible formats, missing values, duplicate records, and schema inconsistencies from systems such as CRM platforms, operational databases, IoT sensors, and cloud applications. Operational guidance covers KPI design, named pipeline ownership, review checkpoints, data mapping and lineage, automated de-duplication, deterministic enrichment, regulatory classification, and role-based access. It states that deterministic tests and human review remain necessary for AI-assisted code, while telemetry and quarterly audits help detect reliability, governance, and data quality degradation. The concluding position is that operational discipline—not model sophistication—supports reliable machine learning, predictive analytics, and generative AI outcomes.


### [Introducing the Google Colab CLI](https://yomu.fyi/post/introducing-the-google-colab-cli.md)
- Company: [Google](https://yomu.fyi/company/google.md)
- Author: Spencer Shumway, Tyler Pirtle, Seth Troisi
- Published: Jun 5, 2026
- Type: Announcement

Google announces the Google Colab Command-Line Interface (CLI), a tool that connects a local terminal with remote Colab runtimes for developers and AI agents. It can provision GPUs or TPUs with commands such as colab --gpu A100, execute local Python scripts and ML pipelines remotely with colab exec, recover artifacts and replayable .ipynb logs, and provide interactive access through colab repl or colab console. The source demonstrates an agent-driven QLoRA fine-tuning workflow for google/gemma-3-1b-it on a Text-to-SQL dataset: an Antigravity agent provisions a T4, installs transformers, datasets, peft, trl, bitsandbytes, and accelerate, runs finetune\_run.py, saves a notebook log, downloads model artifacts, and stops the runtime. The resulting safetensors adapter and configuration files can be loaded locally, while the CLI is presented as programmable and usable by terminal-based agents.


### [The One Where I Found My Way to DevRel](https://yomu.fyi/post/the-one-where-i-found-my-way-to-devrel.md)
- Company: [Okta](https://yomu.fyi/company/okta.md)
- Author: Zahwah Jameel
- Published: Jun 5, 2026
- Type: Announcement

The author recounts a career path from creative interests and technical writing to developer relations, emphasizing that storytelling remained central while the audience changed. She began by producing API documentation, user guides, onboarding content, and other developer resources, then joined JDoodle, where conversations with developers shifted her focus from writing for them to connecting with them. Attending events and conferences, giving product demos, staffing booths, participating in community conversations, organizing hackathons, and running internal events helped her discover that developer advocacy matched her strengths in empathy, clear storytelling, and helping people succeed. She now announces a new role at Okta, where she will work with developers, creators, builders, and community members in identity and security while creating content, attending events, learning, and building connections.


### [Direct agents with visual prompts in Design Mode](https://yomu.fyi/post/direct-agents-with-visual-prompts-in-design-mode.md)
- Company: [Cursor](https://yomu.fyi/company/cursor.md)
- Author: Erik Nilsson, Ian Huang & Ryo Lu
- Published: Jun 5, 2026
- Type: Announcement

Design Mode updates Cursor’s browser-based agent workflow for spatial UI work, letting users edit a product in context rather than relying on chat descriptions alone. Users can select one or more elements, draw on a frozen viewport frame, or narrate instructions by voice; references can express relationships such as matching components or changing a group together. Element selection supplies identity signals including XPath, component, attributes, computed styles, and fiber-tree props, alongside a screenshot capturing layout and page state. Users can queue edits while earlier ones run, manage multiple subagents, and see results through hot reloads, with Composer 2.5 described as suited to fast, targeted interface changes. The update is presented as a way to tighten the noticing-to-editing loop while preserving control and precision during UI iteration.


[Newer posts](https://yomu.fyi/posts/page/117.md) · [Older posts](https://yomu.fyi/posts/page/119.md)