---
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 context in long-run agentic applications](https://yomu.fyi/post/managing-context-in-long-run-agentic-applications.md)
- Company: [Slack](https://yomu.fyi/company/slack.md)
- Author: Dominic Marks
- Published: Apr 13, 2026
- Type: Problem & solution

Long-running multi-agent systems struggle with context management because accumulating raw message histories degrades inference quality, increases latency, and exceeds context window limits. In a collaborative security investigation platform, passing unrestricted history can also introduce confirmation bias across specialized agents. To maintain coherence across unbounded rounds of investigation, the system eliminates raw message history carryover between invocations. Instead, it coordinates agents through three structured context channels: a Director's Journal for orchestration memory, a Critic's Review that scores findings to filter hallucinations, and a Critic's Timeline of validated chronological events. This architecture provides agents with tailored context without overwhelming their inference capacity.


### [Lovable + Databricks: Build Data-Driven Apps at the Speed of Thought](https://yomu.fyi/post/lovable-databricks-build-data-driven-apps-at-the-speed-of-thought.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Evan Pandya
- Published: Apr 13, 2026
- Type: Announcement

Databricks users outside data teams often depend on requests to access business data because they may not write SQL or have a Databricks license. The official Lovable connector lets teams connect Lovable to a Databricks environment and build custom internal applications with plain English. Lovable's AI-powered agent examines accessible data and builds and deploys an application, while Databricks remains the source of truth and data stays within its security perimeter. Data is queried from Databricks at runtime, avoiding ETL, data replication, and sync jobs. Examples include live revenue and pipeline dashboards, spreadsheet-replacing operational tools, internal Slack chatbots, and other business applications that teams can build without engineering or data-team support.


### [Automating Receipt Collection: Apple Intelligence for On-Device Inference](https://yomu.fyi/post/automating-receipt-collection-apple-intelligence-for-on-device-inferen.md)
- Company: [Ramp](https://yomu.fyi/company/ramp.md)
- Author: Kabir Oberai
- Published: Apr 13, 2026
- Type: Problem & solution

Ramp built automatic receipt detection for its iOS app to reduce the effort of finding receipt photos while keeping private images on device. An initial design used PhotoKit, Vision OCR, background processing, local storage, and exact checks for merchant, amount, and date, but formatting differences, aliases, and OCR errors produced many false negatives. FoundationModels enabled a local structured-output LLM, yet a single prompt performed poorly in evals because the small 4096-token model hallucinated and took shortcuts. Splitting the merchant, date, and amount questions and requesting rationale improved evaluation results, but the alpha release reached 66% precision and about 18% recall. Version 3.0 combined one LLM merchant-name check with deterministic iOS 26 data detectors for dates and monetary values; it cut processing time, more than doubled recall, and raised precision to 87%.


### [Using AI agents to build Stripe-Salesforce integrations faster](https://yomu.fyi/post/using-ai-agents-to-build-stripe-salesforce-integrations-faster.md)
- Company: [Stripe](https://yomu.fyi/company/stripe.md)
- Author: Vishnu Samavedula
- Published: Apr 13, 2026
- Type: Problem & solution

An experiment using Claude Code to build a Stripe App for Salesforce Flow exposed context gaps: the generated integration misnamed fields, targeted a nonexistent custom field, and omitted AsyncAfterCommit, causing a “Callout from triggers not supported” deployment error. The proposed remedy is a repository of grounding context files that present invocable signatures, request models, platform constraints, LWC patterns, and validated examples in concise, machine-readable form. Core files are about 35K tokens, while the full reference catalog is about 230K tokens and can be loaded on demand. With the context loaded, the agent selected the v02\_CreateCustomers invocable directly and generated a helper Apex class for nested Checkout Session inputs, along with callout-safe Flow structure and other safeguards. The author reports minutes instead of hours and fewer iterations in personal usage, while noting that org-specific details still require human verification.


### [Re-imagining ML Serving Infra: My Winter Internship at Ramp](https://yomu.fyi/post/re-imagining-ml-serving-infra-my-winter-internship-at-ramp.md)
- Company: [Ramp](https://yomu.fyi/company/ramp.md)
- Author: Michael Jiang
- Published: Apr 10, 2026
- Type: Problem & solution

Ramp’s ML Platform team needed to separate flexible model development in ml-pipelines from the Intelligence Platform’s 99.9%+ uptime and low-latency requirements. The internship project, Bring-Your-Own-Model-Weight Serving (mw-serve), built a dedicated serving layer that pulls model weights from MLflow and a training-environment base image from ECR, then runs each model in an isolated instance. To protect uptime, it added deployment safeguards, pre-traffic liveness checks, and monitors, while latency work instrumented client TCP/TLS connections and server processing. The investigation traced extreme tail latency to connection churn, which improved with longer keepalives and startup warmups, and to garbage-collection pauses associated with memory drops; tuning thresholds and freezing objects removed more outliers. By the final day, one Intelligence Platform model was serving production traffic through mw-serve, with additional models in shadow testing.


### [Introducing clickhousectl: the CLI for ClickHouse local and cloud (beta)](https://yomu.fyi/post/introducing-clickhousectl-the-cli-for-clickhouse-local-and-cloud-beta.md)
- Company: [Clickhouse](https://yomu.fyi/company/clickhouse.md)
- Author: Al Brown
- Published: Apr 9, 2026
- Type: Announcement

ClickHouse released the beta version of clickhousectl, an official command-line interface designed to unify local operations and cloud infrastructure management for both humans and AI agents. The tool acts as a version manager that stores reusable binaries globally in ~/.clickhouse/versions/ while offering optional project directory scaffolding for SQL files. Developers and agents can run multiple isolated local server instances concurrently with automatic free-port detection and dedicated data directories. For ClickHouse Cloud, the CLI provides complete management coverage with structured JSON output, using read-only OAuth or scoped API key authentication to safeguard modifying operations. Additionally, the tool can install ClickHouse Agent Skills directly into supported coding agents to facilitate automated local and cloud interactions.


### [Enabling Multi-Region Data Systems at Notion](https://yomu.fyi/post/enabling-multi-region-data-systems-at-notion.md)
- Company: [Notion](https://yomu.fyi/company/notion.md)
- Author: Justin Lee, Adam Hudson
- Published: Apr 9, 2026
- Type: Explainer

Notion’s data residency work keeps customer data processed and stored in the region where it was generated, supporting EU requirements across Search, analytics, scheduled events, and AI. To make this possible, Notion modularized infrastructure around isolated private networks and workspace IDs, then deployed regional data lakes, Kafka clusters, Spark jobs, Elasticsearch, and vector databases. Debezium captures Postgres changes into regional Kafka, while Airflow remains a centralized orchestration layer that routes jobs to regional EMR clusters; event logging similarly routes traffic by workspace and sanitizes data before Snowflake. Centralized mapping tables, shared region helpers, Terraform, and localized sanitization let teams retain a unified Snowflake environment without exporting customer data. The work took months, and Notion says it is applying these patterns to Japan and South Korea while aiming to provision future regional data stacks within days rather than months.


### [The cure for "execution tax" | Notion](https://yomu.fyi/post/the-cure-for-execution-tax-notion.md)
- Company: [Notion](https://yomu.fyi/company/notion.md)
- Author: Áine Dundas
- Published: Apr 9, 2026
- Type: Problem & solution

Brainlabs CEO Dan Gilbert describes “execution tax” as the gap between a decision and its outcome, where meeting action items are recorded, chased, or lost. He argues that AI has improved engineering productivity while leaving strategists, account managers, and operators with fragmented context and a wide gap between thinking and doing. Brainlabs chose Notion as a company-wide context layer and built “Get Stuff Done,” a factory of Notion Custom Agents that captures action items, assigns owners, and executes suitable work. Its automation uses Notion Custom Agents for native tasks, Notion Workers for external integrations, company-specific Skills and selected LLMs for complex tasks, and human-in-the-loop workflows when judgment remains necessary; Gilbert says some decisions now become completed work in minutes rather than weeks.


### [AI Agents Know About Supabase. They Don't Always Use It Right.](https://yomu.fyi/post/ai-agents-know-about-supabase-they-don-t-always-use-it-right.md)
- Company: [Supabase](https://yomu.fyi/company/supabase.md)
- Author: pedro\_rodrigues
- Published: Apr 9, 2026
- Type: Announcement

Supabase is releasing Supabase Agent Skills, an open-source instruction set for AI coding agents working with Supabase through Claude Code, Codex, GitHub Copilot, Cursor, and compatible Agent Skills implementations. The skill addresses recurring errors such as omitted RLS policies, hallucinated CLI commands, views missing security\_invoker = true, and reliance on outdated training data by requiring documentation checks and embedding critical security guidance in SKILL.md. It also guides CLI and MCP workflows and recommends direct schema changes on local or staging databases, followed by database advisors and a migration after the schema stabilizes. Early evaluations across six scenarios found MCP + Skill scores of 67% for Claude Opus 4.6, 71% for Claude Sonnet 4.6, 88% for Codex GPT-5.4, and 71% for GPT-5.4 Mini, though the sample was small.


### [Waypoint-1.5: Higher-Fidelity Interactive Worlds for Everyday GPUs](https://yomu.fyi/post/waypoint-1-5-higher-fidelity-interactive-worlds-for-everyday-gpus.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Andrew Lapp, Louis Castricato, Scott Fox, Shahbuland Matiana, David Rossi
- Published: Apr 9, 2026
- Type: Announcement

Overworld’s Waypoint-1.5 is a real-time video world model aimed at making interactive generative worlds usable on consumer hardware rather than limited to datacenter-scale compute. It offers two tiers: a 720p model for higher-performance desktop GPUs, capable of up to 60 FPS on RTX 3090 through 5090 hardware, and a 360p model for broader deployment, including gaming laptops and soon Apple Silicon Macs. Training used nearly 100 times more data than Waypoint-1, while more efficient video-modeling techniques reduce redundant computation across frames to support coherent motion and responsive exploration. Users can run it locally through the Biome desktop client, try it in a browser via Overworld Stream, or use the World Engine inference library and third-party clients. The release presents improved visual fidelity, broader local hardware support, and continued progress toward real-time interactive world simulation.


### [Multimodal Embedding & Reranker Models with Sentence Transformers](https://yomu.fyi/post/multimodal-embedding-reranker-models-with-sentence-transformers.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Tom Aarsen
- Published: Apr 9, 2026
- Type: Tutorial

Sentence Transformers v5.4 adds multimodal embedding and reranking support for text, images, audio, and video through its Python API. Embedding models map modalities into a shared space, while multimodal Cross Encoder rerankers score relevance for mixed-modality pairs, enabling cross-modal similarity, retrieval, and multimodal RAG workflows. The guide shows model loading, URL-based image encoding, encode\_query() and encode\_document() prompt handling, similarity calculation, and ranking, with a Qwen3-VL-Embedding-2B example producing 2,048-dimensional image vectors and matching text queries to images. It notes that cross-modal scores can be lower because of the modality gap, while relative ordering can still support retrieval, and that rerankers generally offer higher quality at the cost of slower per-pair processing; installation extras and GPU memory requirements vary by modality and model.


### [Selective Test Execution at Stripe: Fast CI for a 50M-line Ruby monorepo](https://yomu.fyi/post/selective-test-execution-at-stripe-fast-ci-for-a-50m-line-ruby-monorep.md)
- Company: [Stripe](https://yomu.fyi/company/stripe.md)
- Author: Aditya Anchuri
- Published: Apr 9, 2026
- Type: Problem & solution

Stripe’s Ruby monorepo contains about 50 million lines, 100,000 test files, and roughly 1.2 million test units, making sequential execution impractical at an estimated four months. To keep CI within minutes, Selective Test Execution (STE) runs tests whose recorded file accesses intersect files changed since a suitable baseline, averaging about 5% of the suite and under 10% of always-run compute. A dynamically linked C++ library loaded with LD\_PRELOAD intercepts file opens, associates them with hierarchical test scopes, and propagates tracing to child processes; logs are aggregated into a selection index outside the syscall hot path. Guardrails cover tests affected by directory discovery, previously failing tests, selective linting, generated files, and reproducible database-backed baselines ordered by Monotonic Revision IDs. The system is presented as a way to preserve safety and affordability while scaling CI for a highly dynamic language.


### [ClickHouse at FOSDEM 2026](https://yomu.fyi/post/clickhouse-at-fosdem-2026.md)
- Company: [Clickhouse](https://yomu.fyi/company/clickhouse.md)
- Author: Tyler Hannan
- Published: Apr 8, 2026
- Type: Announcement

The ClickHouse community and development team participated in FOSDEM 2026 in Brussels, hosting a community dinner and delivering technical presentations across multiple developer tracks. Presentations covered a range of engineering topics, including building geospatial analytical applications with Leaflet and ClickHouse, as well as integrating LLVM XRay to dynamically hot-patch production logging without redeployments. Additional ClickHouse sessions addressed the engineering challenges of integrating Rust libraries into large C++ codebases, optimizing low-level memcpy routines, and implementing specialized inverted indexes for large-scale text processing. Contributed community sessions detailed workflows for upstream patches in MariaDB and Postgres, alongside WebShield, an open-source Python daemon that streams web accelerator access logs into ClickHouse for bot analysis.


### [The three villains to agentic observability: retention, sampling and rollups](https://yomu.fyi/post/the-three-villains-to-agentic-observability-retention-sampling-and-rol.md)
- Company: [Clickhouse](https://yomu.fyi/company/clickhouse.md)
- Author: Mike Shi
- Published: Apr 8, 2026
- Type: Problem & solution

Observability practices increasingly depend on data sampling, short retention windows, and rollups to control storage costs. While human operators historically compensated for these compromises with intuition, AI agents lack implicit operational context and require full-fidelity telemetry to diagnose issues and justify conclusions. Head sampling drops unobserved spans early, tail sampling risks missing implicit non-error anomalies, and aggressive log expiration prevents long-term cyclical trend analysis. Addressing these constraints requires decoupling storage and compute via high-compression object storage and dedicated compute pools. Deploying real-time analytical databases such as ClickHouse enables high-concurrency, low-latency SQL querying, log clustering, and structured in-database summarization necessary for automated reasoning loops.


### [Bugbot now self-improves with learned rules](https://yomu.fyi/post/bugbot-now-self-improves-with-learned-rules.md)
- Company: [Cursor](https://yomu.fyi/company/cursor.md)
- Author: Michael Zhao
- Published: Apr 8, 2026
- Type: Announcement

At its July 2025 beta exit, Bugbot resolved 52% of identified bugs by the relevant PR merge; that rate is now nearing 80%. In the public-repository comparison, Cursor Bugbot reached 78.13% across 50,310 analyzed PRs, versus Greptile’s 63.49%; an LLM judge checked whether comments were addressed by merge. It now turns reactions and replies to Bugbot comments, along with human-reviewer comments, into live feedback rather than relying exclusively on offline experiments. Bugbot converts those signals into candidate rules, evaluates them on incoming PRs, promotes candidates to active status as signal accumulates, and can disable rules receiving consistent negative feedback. More than 110,000 repositories have enabled learning, generating over 44,000 rules, which users can edit or delete in the Cursor Dashboard.


### [Custom OIDC Providers for Supabase Auth](https://yomu.fyi/post/custom-oidc-providers-for-supabase-auth.md)
- Company: [Supabase](https://yomu.fyi/company/supabase.md)
- Author: cemal\_kilic
- Published: Apr 8, 2026
- Type: Announcement

Supabase has launched Custom OIDC Providers, enabling projects to connect standards-compliant external OpenID Connect identity providers beyond its built-in social options. Configuration requires an issuer URL, client credentials, and scopes; Supabase automatically resolves the discovery document, endpoints, and JWKS, and verifies ID tokens against the provider’s JWKS. After enablement, users use the standard OAuth sign-in flow through existing JavaScript, Flutter, or Swift clients, while the auth server handles redirects, code exchange, profile retrieval, and user creation or linking. Custom providers include default PKCE, authorization-parameter support, multi-platform audience validation through acceptable\_client\_ids, and an email\_optional setting for providers that do not return email addresses. They can be created, listed, updated, or deleted via the Dashboard or Admin API, with a limit of three per project.


### [Safetensors is Joining the PyTorch Foundation](https://yomu.fyi/post/safetensors-is-joining-the-pytorch-foundation.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Luc Georges, Lysandre
- Published: Apr 8, 2026
- Type: Announcement

Safetensors has joined the PyTorch Foundation as a foundation-hosted project under the Linux Foundation, alongside DeepSpeed, Helion, Ray, vLLM, and PyTorch. It began as a Hugging Face project addressing the risk of arbitrary code execution in pickle-based model-weight formats. Its format stores tensor metadata in a JSON header capped at 100MB, followed by raw tensor data, and supports zero-copy mapping and lazy loading. The move places the trademark, repository, and governance with the Linux Foundation, while Luc and Daniel remain on the Technical Steering Committee and lead day-to-day work. Existing users get the same format, APIs, and Hub integration without breaking changes, while contributors gain a documented maintainer path; planned work includes PyTorch core serialization, accelerator-aware loading, parallel loading, and quantization support.


### [How Eisan made POS analytics faster, cheaper, and more reliable with ClickHouse Cloud](https://yomu.fyi/post/how-eisan-made-pos-analytics-faster-cheaper-and-more-reliable-with-cli.md)
- Company: [Clickhouse](https://yomu.fyi/company/clickhouse.md)
- Author: ClickHouse
- Published: Apr 8, 2026
- Type: Problem & solution

Eisan System Development moved a retail analytics workload from a QlikView-based platform to ClickHouse Cloud after rising ID-POS data volumes caused slower processing, failed analyses, and increasing licensing and server costs. Client records from supermarkets and drugstores support basket analysis, cross analysis, and real-time personalization, with some datasets nearing 200 million records annually. The team compared open-source options including PostgreSQL and YugabyteDB, then tested ClickHouse configurations, including a 30-core, 120-GB setup, while accounting for cache memory usage through load testing. In comparison, ClickHouse ran on slightly lower-spec hardware under high-load conditions without observed performance deterioration, and Eisan reports no cases so far where it failed to return a result; the team is now targeting 100 billion records and exploring off-hours processing and scheduled scaling.


### [MongoDB Predictive Auto-Scaling: An Experiment](https://yomu.fyi/post/mongodb-predictive-auto-scaling-an-experiment.md)
- Company: [MongoDB](https://yomu.fyi/company/mongodb.md)
- Author: A. Jesse Jiryu Davis, Matthieu Humeau
- Published: Apr 7, 2026
- Type: Problem & solution

MongoDB Atlas initially relied on a reactive auto-scaler that took minutes to adjust instance sizes and only transitioned between adjacent tiers. Because these delays caused transient server over-utilization or unnecessary customer costs, researchers prototyped predictive auto-scaling to forecast demand. The experimental architecture used short-term and long-term forecasters for customer-driven metrics, an estimator using boosted decision trees to project CPU utilization, and a planner to pick the most cost-effective tier. In testing, the prototype kept replica sets closer to target CPU ranges while saving an average of nine cents per replica set hourly. MongoDB subsequently implemented a production version that scales replica sets up proactively before expected spikes while retaining reactive downscaling.


### [Frontend Engineering at Palantir: Plotlines in Three.js](https://yomu.fyi/post/frontend-engineering-at-palantir-plotlines-in-three-js.md)
- Company: [Palantir](https://yomu.fyi/company/palantir.md)
- Author: Palantir
- Published: Apr 7, 2026
- Type: Explainer

Palantir’s frontend engineers are building a 3D implementation of Gaia to visualize Foundry Ontology objects with geospatial properties, including ground locations, satellite positions, and paths through space. The system uses Zodiac, a Three.js library backed by Foundry-based APIs: the backend stores, filters, and computes data, while the frontend receives simplified geometry and style information for rendering. Performance techniques include converting latitude and longitude to Earth-fixed coordinates once, batching similarly styled lines into single draw calls, and using instanced meshes plus batched updates for dense satellite scenes; orbital propagation uses TLEs client-side, while heavier analysis remains server-side. The article also describes frame-synchronized animation callbacks that update material properties without rebuilding geometry, while noting that 3D APIs continue to iterate across usability, platform integration, and performance as new data sources and workflows are added.


[Newer posts](https://yomu.fyi/posts/page/147.md) · [Older posts](https://yomu.fyi/posts/page/149.md)