Read what ships.

01GitLab · tutorial

PHP2Shell: GitLab helps find and remediate critical PHP flaws

Critical remote code execution vulnerabilities known as PHP2Shell affect the PHP engine across multiple versions, requiring immediate runtime updates to fixed versions or patched distribution packages. The team utilized platform features like container scanning, code search, and automated agent workflows to locate PHP projects and remediate vulnerabilities. Operators must also check logs and environments for signs of compromise as framework updates and input validations cannot prevent these engine-level flaws.

DEPTH ■■■■■10 min read3 days ago

ArchitectureSecurity

Sign in to save and rate

02Amazon Web Services · architecture

Automate medical coding with Step Functions and Amazon Bedrock AgentCore

Automating medical coding requires a hybrid approach that combines deterministic orchestration with bounded agentic reasoning to ensure safety, auditability, and human oversight. The team built a workflow using AWS Step Functions, AWS Lambda, and Amazon Bedrock AgentCore that evaluates terms cheapest-first via block-lists, exact matching, and finally an LLM agent for ambiguous cases. This design successfully autocodes confident cases while routing ambiguous ones to human reviewers with full audit trails and decision explanations.

DEPTH ■■■■■15 min read4 days ago

AWS

Sign in to save and rate

03Meta · architecture

The Thin Orchestrator: How We Made Our AI Agents More Reliable by Giving the Router Less to Do

Meta engineers reduced hallucinations and improved reliability in their data pipeline agents by replacing a single heavyweight LLM orchestrator with a thin deterministic router and fourteen specialized subagents. The thin orchestrator handles routing and reliability checks through a fixed protocol, while isolated subagents execute domain reasoning. This architecture reduced configuration preparation time from a day to under an hour.

DEPTH ■■■■■7 min read6 days ago

Machine Learning

Sign in to save and rate

04Stack Overflow · architecture

MCP standardized tools. Now we need the infrastructure around them.

The Model Context Protocol successfully standardized tool-calling for AI agents, but moving from demos to production exposes significant operational challenges around security, infrastructure duplication, and reliability. Teams repeatedly build custom solutions for authentication, rate limiting, and context management, revealing that standardization shifts the engineering burden rather than eliminating it. Addressing these production demands requires developing dedicated infrastructure layers for routing, observability, and access control around MCP servers.

DEPTH ■■■■■8 min read10 days ago

Machine Learning

Sign in to save and rate

05Meta · architecture

Inside Prometheus: Meta’s Journey to a Gigawatt-Scale Supercluster

Meta built Prometheus, a gigawatt-scale AI supercluster designed to scale up to one million GPUs using multi-generation NVIDIA hardware and specialized backend Ethernet networks. The team achieved high goodput and significantly reduced system interruptions by implementing an in-rack sparing strategy, parallelism-aware fault tolerance, and close co-engineering with vendors. These infrastructure advancements allowed the team to successfully train frontier foundational models like Muse Wonder.

DEPTH ■■■■■17 min read6 days ago

InfrastructureMachine Learning

Sign in to save and rate

06Amazon Web Services · architecture

Multi-region disaster recovery for Amazon API Gateway WebSocket APIs

Real-time applications using WebSocket connections face disruptions during regional AWS outages because connections are tied to specific regions. The team implemented an active-passive multi-region disaster recovery architecture using Route 53 DNS failover, DynamoDB Global Tables, an automated canary health probe, and client-side exponential backoff with jitter. This design automatically detects failures, redirects traffic, and restores client state without manual intervention.

DEPTH ■■■■■10 min read11 days ago

Sign in to save and rate

07GitLab · scaling

Make every AI credit count: See, cap, and reduce agent spend

Uncontrolled AI agent spending can be mitigated by combining open-weight models, centralized context graphs to reduce retries, and usage analytics with credit caps. GitLab introduced these capabilities in its Duo Agent Platform to help platform teams trace, limit, and optimize AI credit consumption. The resulting architecture matches specific tasks to lower-cost models while maintaining task completion quality.

DEPTH ■■■■■6 min read12 days ago

Sign in to save and rate

08Meta · practice

How Meta Built Forum With AI-Native Engineering

Meta engineers built the Forum app using a human-on-the-loop AI agent workflow that automated planning, building, testing, and verification. By shifting focus from code generation to automated verification, tooling improvements, and architectural legibility, the team reached feature parity in eight weeks while catching systemic memory issues early.

DEPTH ■■■■■8 min read10 days ago

FrontendMobile

Sign in to save and rate

09Stack Overflow · architecture

Part 5: Operating an LLM system: observability, cost, routing, and the platform underneath

This post provides a concrete specification for the operability layer of production LLM systems, covering observability signals, structured logging, cost controls, routing, and failover mechanisms. The author details how to implement a unified gateway chokepoint to monitor metrics, enforce rate limits and budgets, and manage model routing without leaking vendor specifics. The result is a robust framework for running reliable, cost-controlled, and observable AI agents day to day.

DEPTH ■■■■■19 min read2 weeks ago

Machine Learning

Sign in to save and rate

10Amazon Web Services · architecture

How UTS established a modern curriculum data services foundation on AWS

University of Technology Sydney rearchitected its curriculum data integration using serverless AWS services to decouple systems of record from downstream consumers. By implementing domain-driven design with an event-driven architecture and purpose-built persistence layers, the team achieved zero production incidents, low latency, and reduced operational overhead while managed by a single engineer.

DEPTH ■■■■■9 min read11 days ago

Sign in to save and rate

11Stack Overflow · architecture

Part 4: Safety and governance for LLM systems: guardrails, PII, audit, and memory

This post details safety and governance practices for LLM systems, focusing on layered guardrails, boundary-level PII handling, and immutable audit trails. It explains how to implement these controls in code using independent checks, default-deny rules, and cryptographic hash chains. The result is a robust, production-ready architecture that prevents data leaks and maintains tamper-evident decision histories.

DEPTH ■■■■■19 min read2 weeks ago

Machine Learning

Sign in to save and rate

12Amazon Web Services · tooling

Scope workloads and share resilience policies with AWS Resilience Hub

Engineering teams often struggle to scope workloads and maintain up-to-date resilience policies in shared Kubernetes clusters after migrations or deployments. AWS Resilience Hub introduced features enabling Kubernetes label-based resource scoping, generative AI-powered dependency insights, and cross-account resilience policy sharing via AWS Organizations. These capabilities allow teams to isolate specific workloads, prioritize dependency investigations, and enforce centralized recovery standards.

DEPTH ■■■■■14 min read12 days ago

Sign in to save and rate

13Meta · architecture

Meta’s Generative Ads Model (GEM): Scaling the Central Model and Compute Engine for Frontier Ads AI

Meta developed GEM, a unified recommendation foundation model using an LLM-style architecture called Kunlun to handle heterogeneous ads data across multiple surfaces. The team implemented block attention, custom low-precision kernels, and post-training intelligence transfer techniques like LoopFM and Solaris to scale training efficiency and bypass real-time serving latency bottlenecks. The resulting system delivered an 18.9% conversion improvement and a 12% click-through rate increase across Meta ads surfaces.

DEPTH ■■■■■15 min read12 days ago

Machine Learning

Sign in to save and rate

14Stack Overflow · architecture

Part 3: Knowing when your agent doesn’t know: the confidence layer

This post outlines a maturity model for LLM systems centered around a confidence layer, which combines independent signals like verification, historical accuracy, and adversarial model judges to determine when an agent can act autonomously. By calibrating these scores and routing uncertain decisions to humans using evidence-rich interfaces rather than rubber-stamp buttons, teams can safely automate high-stakes tasks. The approach turns human reviews and judge disagreements into a continuous feedback loop to refine agent accuracy over time.

DEPTH ■■■■■12 min read2 weeks ago

Machine Learning

Sign in to save and rate

15Amazon Web Services · architecture

Stopping business email compromise with AI-driven email security: How VIPRE protects modern enterprises on AWS

VIPRE developed an AI-driven, cloud-native email security solution on AWS to protect enterprises against business email compromise and advanced phishing attacks. The system uses layered machine learning, semantic analysis, and dynamic sandboxing orchestrated via serverless containers and message queues to evaluate over half a million messages daily. In production testing, the architecture successfully identified thousands of BEC attempts while maintaining low-latency processing and reducing administrative overhead.

DEPTH ■■■■■12 min read12 days ago

Sign in to save and rate

16Meta · architecture

OCP Summit 2026: Powering AI with Open Innovations in Scale-Up, Scale-Out, and Scale-Across Networks

Meta shared its next-generation open networking infrastructure for AI at the OCP Summit 2026, including liquid-cooled 102.4T switch platforms, multiplane scale-out fabrics, and Ethernet-based scale-up solutions. The team also highlighted collaborative industry standards like ESUN and OSPA to unify hardware and transport layers. These open innovations aim to support massive gigawatt-scale AI clusters across diverse data center environments.

DEPTH ■■■■■12 min read13 days ago

Machine Learning

Sign in to save and rate

17Stack Overflow · architecture

Part 2: Evals as a deployment gate — and how to know when they drift

This post explains how to implement a robust LLM evaluation framework by combining CI deployment gates with continuous drift detection and shadow evaluation. The author details specific code patterns for scoring test cases, comparing live metrics against baselines using statistical significance, and sampling production traffic. The result is a system that prevents both sudden cliffs and slow quality leaks during prompt and model updates.

DEPTH ■■■■■8 min read2 weeks ago

Machine Learning

Sign in to save and rate

18Amazon Web Services · architecture

Bulk Executor for Amazon DynamoDB, Part 2: Lessons we learned the hard way

Engineering a bulk execution tool for Amazon DynamoDB using AWS Glue required addressing several architectural challenges, including cost estimation, graceful job termination, and error handling across hundreds of parallel workers. The team overcame limitations in CloudWatch logging and the Spark connector by combining serverless execution with direct API calls and distributed rate limiting. As a result, the tool provides a scalable, script-like interface for managing large-scale table operations safely.

DEPTH ■■■■■14 min read12 days ago

Sign in to save and rate

19Stack 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

20Meta · architecture

GenRecs Tokenization: Transforming Ads Recommendation at Meta with Stable Model Vocabulary

Meta implemented GenRecs Tokenization to replace dedicated item IDs with a stable semantic vocabulary for ads recommendation. Using a three-stage encoding and quantization pipeline, the system enables language models to reason about ad content and user preferences simultaneously. This approach resulted in a +0.35% lift in conversions and improved cold-start performance for new entities.

DEPTH ■■■■■6 min read6 days ago

Machine Learning

Sign in to save and rate