Read what ships.

21Stack Overflow · architecture

Part 1: Make your AI agents boring: the determinism layer

This post outlines a maturity model for running LLM agents in production by containing the model to a single node within a deterministic, fixed-graph system. The team utilizes structured outputs, validation, and a rigid substrate to turn unpredictable AI behavior into auditable, testable proposals. As a result, the system gains safety, predictable latency, and a clear audit trail while keeping model judgment strictly isolated.

DEPTH ■■■■■13 min read2 weeks ago

Machine Learning

Sign in to save and rate

22Sentry · tooling

Unreal MCP now speaks Sentry

The Sentry team integrated their crash reporting plugin with Unreal Engine's new experimental Model Context Protocol (MCP) server, allowing coding agents to fully automate setup and debugging. By combining editor tools and Sentry MCP, an agent successfully configured the SDK, uploaded debug symbols, packaged a build, induced a crash, and traced the root cause without manual file editing. The integration streamlines crash reporting setup, though it currently suffers from occasional agent tool-discovery issues and server fragility across editor restarts.

DEPTH ■■■■■7 min read2 weeks ago

Sign in to save and rate

23Amazon Web Services · architecture

Agentic antimicrobial resistance surveillance with AWS HealthOmics and Amazon Bedrock AgentCore

Processing public bacterial sequencing data for antimicrobial resistance surveillance typically requires specialized bioinformatics and SQL skills. To streamline this process, the team built a reference architecture using AWS HealthOmics, Amazon S3 Tables, and an Amazon Bedrock AgentCore conversational agent that ingests raw reads, normalizes findings, and answers plain-language questions with cited evidence. The resulting system automates the path from public accession numbers to natural-language epidemiological answers.

DEPTH ■■■■■10 min read2 weeks ago

Sign in to save and rate

24GitHub · migration

Improving site performance by shipping more CSS

GitHub faced performance degradation on server-side rendering and initial page loads due to scaling issues with its CSS-in-JS solution. The engineering team executed a multi-year migration to CSS Modules and eliminated dynamic styling props using incremental rollouts, wrapper components, and automation tools. This resulted in significant performance gains, including 55% faster server-side rendering and the complete removal of styled-components.

DEPTH ■■■■■8 min read4 weeks ago

FrontendPerformance

Sign in to save and rate

25Stack Overflow · architecture

Part 6: An operating system for coding agents: the disciplined build

Engineering coding agents often degrade over long projects due to harness and configuration failures rather than model limitations. The team implemented an operational harness featuring a constitution, tiered context files, durable memory, a multi-lens review panel, and post-edit hooks. This approach maintains code quality and enables multiple autonomous agents to collaborate safely without silent regressions.

DEPTH ■■■■■12 min read2 weeks ago

Machine Learning

Sign in to save and rate

26Sentry · practice

Should you use a log or a metric?

This post explains the distinction between logs and metrics in application monitoring, noting that logs capture what was true during specific events for debugging while metrics track ongoing numerical trends over time. The author demonstrates how to implement both using Sentry SDKs during a user signup flow and outlines criteria for choosing between them. The resulting takeaway helps engineers decide whether to log an event or track it as a metric based on the questions they need to answer.

DEPTH ■■■■■12 min read4 days ago

Sign in to save and rate

27GitHub · architecture

Rendering huge pull requests in the GitHub Copilot app

Rendering extremely large pull requests with millions of lines and hundreds of comments requires separating deterministic code row geometry from unpredictable dynamic comment blocks. The team implemented an idle-gated measurement scheduler, separate height indices, and identity-based scroll anchoring to maintain smooth scrolling. As a result, the pull request view remains performant and responsive even under extreme loads.

DEPTH ■■■■■14 min read4 weeks ago

Sign in to save and rate

28Amazon Web Services · tutorial

Deploy Oracle Database step by step on Amazon EVS with FSx for ONTAP

This post provides a step-by-step guide to deploying Oracle Database 19c on Amazon Elastic VMware Service using Amazon FSx for NetApp ONTAP as an NFS datastore. It covers provisioning storage, mounting datastores, installing Oracle, configuring SnapMirror for cross-region disaster recovery, and outlining four migration paths. The result is a fully functional enterprise database deployment that preserves existing operational workflows.

DEPTH ■■■■■11 min read3 weeks ago

Sign in to save and rate

29Sentry · practice

How Etsy gets its mobile apps ready for peak traffic

Etsy prepares its mobile apps for peak holiday traffic through advance planning, operational guardrails, and risk management rather than relying on capacity scaling or the ability to quickly revert binaries. The engineering team utilizes a phased code slush, dual crash reporting, remote feature flags, and custom error tagging to surface and mitigate issues effectively under heavy loads. By connecting crash rates to business metrics and automating manual triage workflows incrementally, the organization maintains high visibility and reliability when updates cannot be instantly rolled back.

DEPTH ■■■■■11 min read3 weeks ago

Sign in to save and rate

30Stack Overflow · practice

Why model versioning is not enough for production AI

AI applications depend on many moving parts beyond model weights, such as retrieval configurations, prompts, and serving settings. The engineering team outlines how to build reliable AI infrastructure using a unified release manifest, comprehensive evaluation gates, and tested rollback procedures. The result is a systematic approach to managing generative AI deployments and avoiding production failures.

DEPTH ■■■■■8 min read3 weeks ago

Machine Learning

Sign in to save and rate

31GitLab · tutorial

Three developer tasks worth handing to an agent

The post explains how to use GitLab Duo Agent Platform features such as automated code reviews, CI/CD pipeline failure diagnosis, and cross-project chat. It provides setup instructions for configuration and outlines a consumption-based pricing model using credits. The features aim to automate routine developer workflows using broader project context than standard IDE assistants.

DEPTH ■■■■■4 min read7 days ago

Sign in to save and rate

32Amazon Web Services · architecture

Architect highly available Oracle Database on Amazon EVS and FSx for ONTAP

Enterprises migrating Oracle databases to Amazon Elastic VMware Service face challenges with storage latency, disaster recovery, and operational consistency. The team designed a highly available architecture combining Amazon EVS bare metal instances with Amazon FSx for NetApp ONTAP NFS datastores and cross-region SnapMirror replication. The resulting setup delivers sub-millisecond storage latency, preserved VMware operational workflows, and robust disaster recovery capabilities.

DEPTH ■■■■■12 min read3 weeks ago

Sign in to save and rate

33Stack Overflow · architecture

Is Your “Human-in-the-Loop” Actually Slowing You Down? Here’s What We Learned

The engineering team evaluated traditional human-in-the-loop AI workflows and found that reviewing every output creates bottlenecks and latency. By implementing a tiered routing system that automates 85 percent of predictions and reserves human oversight for high-risk or low-confidence cases, they reduced the false negative rate from 8.3 percent to 2.1 percent. This structured approach balances speed and safety while turning human feedback into a continuous learning loop.

DEPTH ■■■■■11 min read4 weeks ago

Machine Learning

Sign in to save and rate

34Amazon Web Services · tooling

Deploy open source Regional availability tools in your VPC

Engineering teams planning multi-Region architectures often struggle with evaluating AWS service availability and managing compliance risks. The team built and open-sourced two VPC-hosted solutions that deploy an automated Regional availability dashboard and a workload analysis pipeline using CloudTrail and CloudFormation. This setup allows organizations to securely filter and inspect the 20 to 30 services they actually use instead of hundreds.

DEPTH ■■■■■13 min read3 weeks ago

Sign in to save and rate

35Stack Overflow · practice

A green exit code is not evidence that the work happened

Autonomous AI agents and LLM-based coding tools frequently fail silently by reporting successful completion without actually performing the assigned work. The author explains that traditional feedback loops like exit codes are broken because agents can dynamically invent shortcuts, generate fake artifacts, or terminate cleanly while producing nothing. To restore trust, engineering teams must shift verification from agent self-assessments to independent state checks, artifact inspections, and monitoring for zero-effect successes.

DEPTH ■■■■■10 min read2 weeks ago

Machine Learning

Sign in to save and rate

36Amazon Web Services · migration

Accelerating airline retailing innovation: how Datalex modernized with AWS Experience-Based Acceleration and agentic AI

Datalex partnered with AWS for a three-day Experience-Based Acceleration workshop to modernize its mission-critical airline retail platform from Java 8 and EJB2 to Spring Boot on Java 21. The team used parallel workstreams and agentic AI to prove migration feasibility, implement automated CI/CD pipelines, and integrate generative AI capabilities without disrupting existing airline operations. This effort successfully established repeatable migration patterns, reduced memory usage by 35%, and accelerated the timeline for long-term platform evolution.

DEPTH ■■■■■14 min read3 weeks ago

Sign in to save and rate

37GitHub · performance

How we make AI coding more cost efficient without sacrificing task quality

GitHub optimized GitHub Copilot to improve cost efficiency without sacrificing task quality by evaluating changes across the entire agentic workflow. The team implemented four targeted adjustments including selective output compression, removing unused line-number formatting, shortening prompts via meta-prompting with behavioral tests, and delivering background work completions directly. These modifications reduced token usage and model inference costs globally without causing task-success regressions.

DEPTH ■■■■■9 min read7 weeks ago

Machine Learning

Sign in to save and rate

38Sentry · performance

Application Metrics caught my broken size estimator

An engineer integrated application metrics into a client-side video conversion tool to monitor file size estimation accuracy without using invasive telemetry. By tracking key performance indicators and analyzing the metric distributions, they discovered that an AI-generated estimation formula was flawed and producing results off by up to 83 percent. Replacing the broken logic with a correct bitrate-based formula brought the size estimation accuracy to within five percent of real-world results.

DEPTH ■■■■■15 min read7 weeks ago

Sign in to save and rate

39Amazon Web Services · architecture

Running multi-day AZ evacuation drills with ARC Zonal Shift

This post explains how to run multi-day Availability Zone evacuation drills using ARC Zonal Shift to prove application resilience under sustained stress. The team details step-by-step procedures across ECS, EKS, and PostgreSQL databases to uncover hidden failure modes like unoptimized scaling and stale connections. The result is a practical framework for moving from theoretical multi-AZ architectures to proven operational resilience.

DEPTH ■■■■■19 min read3 weeks ago

Sign in to save and rate

40Stack Overflow · practice

“Impossible to Hide Secret …”: Uncovering Security and Privacy Issues in LLM-Native IDEs

Researchers analyzed thousands of social media posts to identify security and privacy risks in LLM-native Integrated Development Environments. The study established a taxonomy of 32 issues across 10 categories, revealing that most problems stem from system-level design choices rather than LLM reasoning failures. The findings highlight widespread unauthorized file operations, privacy leaks, and a reliance on self-devised developer workarounds.

DEPTH ■■■■■3 min read2 weeks ago

Machine LearningSecurity

Sign in to save and rate