Engineering blogs, all in one place.

Loading
How we raised Databricks cluster rate limits by 7.5×
Databricks' Compute Platform team describes how fixed request-rate limits failed to protect long-running cluster-creation workflows, and how adaptive concurrency limits with slot-based tracking, bounded queues, and fair scheduling let them raise default cluster-creation rate limits by 7.5×. The post covers retry storms, distinguishing system degradation from tenant overload, and reported outcomes including over 99.99% fewer rate-limit errors.
How we scaled metrics aggregation by moving durable state into storage
Datadog describes how its metrics aggregation system evolved across three generations, from static partition ownership with local RocksDB state, to dynamically assigned consumers with state snapshots in blob storage, to a best-effort streaming layer where durable reconciliation of partial aggregates is delegated to the timeseries storage engine. The post explains the recovery, scaling, and cost trade-offs behind each design and why the final architecture lets the streaming layer resume at the...
Building the Agent Host Protocol for sessions that continue across devices
GitHub describes the Agent Host Protocol (AHP), an open standard that keeps Copilot agent sessions continuous across VS Code, the GitHub Copilot app, mobile apps, and cloud sandboxes. The post explains why per-client integrations failed, how a URI-channel, reducer-based state design handles reconnection and concurrent mutations, and what was learned from building two independent hosts in TypeScript and Rust. It also covers how the protocol stays agnostic to agent behavior and where to connect...
Smooth Cruiser at Lyft: Built for Safety and Transparency
Lyft describes how Smooth Cruiser, its driver safety scoring feature, measures driving signals relative to local road conditions, regional peer groups, and a rolling window of recent rides. The post also covers the data platform behind the score, including ML-based harsh event detection, an Apache Airflow ETL pipeline, and DynamoDB for low-latency score retrieval, along with transparency features that show drivers the rides behind their scores.
DuckDB User Group Workshop on AI-Powered Review Analysis with Hugging Face
A DuckDB User Group workshop built a pipeline over 2.1 million Amazon appliance reviews to find products with falling ratings. DuckDB SQL selects the largest rating drops and the most helpful recent complaints, and only those 40 reviews go to an LLM for theme summarization. The post also covers running the job on Hugging Face and deploying the workflow as a Gradio app with API endpoints.
Introducing eve 1.0
Vercel announces eve 1.0, an open-source framework for production AI agents, and details the engineering behind it. Median hosted turn latency fell from 3.04s to 414ms through a single-orchestrator workflow design and WebSocket event writes, and estimated workflow cost for a 50-turn session dropped about 76% by storing only changed conversation data. The post also covers OpenTelemetry-based tracing, multi-tenant agent configuration, and dynamic tool loading.
Using a "chaos loop" to harden the Claude Docs launch: 60 server errors across billions of requests
Vivek Nair describes how a team hardened the Claude Docs backend before its September 2026 launch by running Claude in a long-lived loop against a chaos-testing staging cluster. Key lessons include using copy-on-write to fix per-keystroke memory growth, which cut projected pods from over 500 to about 50, and choosing Rust with minimal dependencies so telemetry traces back to owned code. The launch saw 60 server errors across 2 billion requests with no rollbacks.
Engineering AI Discover
Netflix describes the intelligence layer behind its AI Discover TV feature, an agent harness that combines LLMs with recommendation systems. The post covers a plan-and-execute architecture with controller and executor components, validated plans built from composable capabilities, model-agnostic design, asynchronous page generation, and safety rules enforced in code rather than prompts. It is an engineering write-up of the trade-offs and decisions made along the way.
How AI Slashed 600-Test-Failure Triage From Days to 90 Minutes
Salesforce engineers describe building AI-Assisted Test Failure Buddy, a Python and FastMCP tool exposing eight MCP tools to Claude Code and Cursor, to triage over 600 test failures caused by retiring the SOAP API login mechanism. The post explains how deterministic code handles API calls, batching, signature matching, and reassignment while AI interprets unmatched stack traces and ambiguous ownership, reducing estimated two to three days of triage to about 90 minutes.
Introducing Snapshot Migration to Heroku Postgres Advanced
Heroku has released heroku data:pg:migrate, a guided CLI workflow for moving Postgres Classic databases to Heroku Postgres Advanced. The post explains the two-phase design: an online preparation phase, then an offline snapshot copy that blocks writes, restores constraints and indexes, and validates the result. It also covers rollback behavior, rehearsing on a fork to measure downtime, and upgrading the Postgres major version during migration.
The pioneering coding tricks that built Doom and Quake
In a podcast recorded at WeAreDevelopers 2026, John Romero, creator of Doom and the WAD file format, discusses the self-modifying code and blitting techniques that let Wolfenstein run quickly on early PCs. He also covers the mod-friendly architecture behind Doom's success and the creative problem-solving behind Quake, arguing that human ideas outperform AI coding agents.
Quad9’s withdrawal from France: A canary in the coal mine
Cloudflare argues that Quad9's withdrawal from France, after a court imposed daily penalties for not blocking domains via its public DNS resolver, shows the harms of mandating DNS-level blocking. The post explains why domain-level DNS blocking is easy to bypass, causes collateral damage to legitimate content on the same domain, and fails silently for users. It warns that forcing public resolvers out of markets weakens the open Internet.
Built on object storage, served from cache
Explains how Databricks Lakebase Postgres uses a tiered architecture so that object storage almost never sits on the query read path. Production stats show 99.46% of page reads hit compute-node caches, with pageservers serving most of the rest from local NVMe, and object storage handling only about 1 in 28 million accesses. The post also covers how image and delta layers keep pageserver replay chains short.
Rebuilding Data Lineage at LinkedIn: From Storage to Compute
LinkedIn rebuilt its data lineage platform to capture lineage from executed query plans across more than 15 compute and data-movement systems. The design routes events through Kafka into an append-only log, stores the graph in MySQL with a breadth-first traversal engine, and attaches type, confidence, and granularity to every edge. The post reports a production graph of roughly 6 million datasets with P99 traversal latency near 200 ms.
Split-and-Scale Latent 3D Representations
Presents split-and-scale, a method that increases latent capacity of pretrained 3D tokenizers at inference by applying the same tokenizer to smaller sub-regions of a scene, since 3D scenes are represented as continuous functions of coordinates. The authors ablate compute, memory, latent capacity, and reconstruction quality, and report competitive results against larger models exceeding single-GPU memory, plus an autoregressive 3D generator built on the approach.
Scheduling the removal of the kube-proxy IPVS backend
Dan Winship of Red Hat explains why the Kubernetes kube-proxy ipvs backend is being deprecated and scheduled for removal in Kubernetes 1.40, covering its original data-plane and control-plane performance motivations and its later compatibility, batch-update, and scheduler limitations. The post recommends migrating to the nftables mode, or to the substantially improved iptables mode on older clusters, and gives concrete configuration guidance for kubeadm clusters.
From Predictive to Generative – How Michelangelo Accelerates Uber’s AI Journey
Uber's engineer write-up traces the evolution of its centralized ML platform, Michelangelo, across three phases from 2016 to the present. It details the shift from tree models to deep learning, including the move from Spark to Ray-based trainers, elastic Horovod, and Triton model serving, along with the platform changes that followed. It also covers model quality tiering, Canvas for code-driven pipelines, and the Gen AI Gateway for LLM access.
Give sandboxed agents live web access with the Firecrawl kit for Docker Sandboxes
The post introduces a Firecrawl kit for Docker Sandboxes that gives isolated coding agents live web search, scraping, and crawling through one allowlisted host, api.firecrawl.dev. It explains how the kit's mixin descriptor declares install, credential, phased network-policy, and agent-context capabilities, with the API key injected by a host-side proxy so it never enters the sandbox. It also covers verification steps and known limitations such as proxy 403s and organization policy overrides.
How the World’s Most Advanced AI Infrastructure Supply Chain Invents the Future
NVIDIA's operations leader Deb Shoquist describes how the company builds supplier relationships to scale AI infrastructure production. The post walks through a GB200 compute board test-handler throughput failure, the cross-team response that followed, and a traceability process that cut chip-to-system lead time from five weeks to two. It is written by NVIDIA about its own manufacturing operations.