Read what ships.

21Stack 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 read4 weeks ago

Machine Learning

Sign in to save and rate

22Datadog · architecture

Making Rust observability reliable at scale with OpenTelemetry

Datadog engineers faced inconsistent tracing, broken spans, and context loss across Rust services due to fragmented tooling and unopinionated OpenTelemetry configurations. To fix this, they contributed upstream to OpenTelemetry to improve interoperability and built an opinionated Rust tracing library called dd-trace-rs. This reduced backend ingestion volume by 20x while increasing the rate of indexed spans per service by 3x.

DEPTH ■■■■■10 min read8 weeks ago

Sign in to save and rate

23GitLab · 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 read8 days ago

Sign in to save and rate

24Figma · tooling

How Coinbase used Code Connect to guide agents and shrink token costs

The Coinbase Design System team updated their Figma Code Connect mappings to improve agentic design-to-code workflows. By providing agents with better component context, the team reduced token costs by 22.5% and implementation time by about 22% while eliminating common hallucinations.

DEPTH ■■■■■5 min read7 weeks ago

Sign in to save and rate

25Stack 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

26Figma · practice

4 team rituals that drive AI adoption

To drive team-wide AI adoption beyond isolated power users, several companies introduced collaborative team rituals such as peer-led study groups, process-focused sharing forums, cross-disciplinary training, and prototype-first critiques. These forums helped bridge knowledge gaps, reduce intimidation, and build consistent habits. As a result, teams were able to move from individual experimentation to collective AI usage.

DEPTH ■■■■■7 min read2 weeks ago

Sign in to save and rate

27Stack 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

28GitHub · 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

29Stack 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

30Figma · tutorial

Workflow lab: Staying in the flow with Figma’s agent

A fictional designer at Offtrail updates a permission settings flow using the Figma agent to handle repetitive maintenance, compliance checks, and component specs. By offloading busywork and context gathering to the agent, the designer focuses on feature logic and design decisions while keeping outputs connected in a shared canvas.

DEPTH ■■■■■8 min read2 weeks ago

Sign in to save and rate

31Stack Overflow · practice

The Regression Tests Nobody Writes: Capturing How Software Actually Behaves

Standard regression tests usually only verify developer intent rather than the actual, unwritten behaviors that systems accumulate in production over time. By capturing real production traffic and network-level interactions, teams can build characterization test suites to automatically detect unintended behavioral shifts. This approach prevents accidental regressions during legacy refactoring, rewrites, and major framework upgrades.

DEPTH ■■■■■6 min read4 days ago

Testing

Sign in to save and rate

32Figma · tooling

How to lighten design system upkeep with the Figma agent

Design systems often suffer from maintenance overhead like documentation debt, naming inconsistencies, and drift between product screens and libraries. The Figma agent automates these upkeep tasks by drafting specs, auditing token and component usage, and bulk-replacing disconnected elements. This reduces manual toil and helps teams keep their design systems aligned with product work.

DEPTH ■■■■■5 min read2 weeks ago

Sign in to save and rate

33Stack Overflow · practice

Survey Says: You'll swap the model, but everything you build around it is staying put

Stacklok surveyed technical leaders to understand enterprise AI adoption and vendor lock-in concerns. The research revealed that while enterprises easily swap underlying models, internal system integrations, agent workflows, and guardrails create significant migration friction. Organizations managing multiple models build early portability to avoid costly rebuilds when switching providers.

DEPTH ■■■■■4 min read5 days ago

Machine Learning

Sign in to save and rate

34Stack Overflow · architecture

Don't forget about the UI for AI

OpenAI developed ChatGPT Space, a real-time collaborative workspace designed to allow software engineering teams and individual AI agents to work together on shared artifacts. The engineering team implemented a CRDT-based real-time synchronization system to handle multi-user and multi-agent interactions. The project highlights the challenges of scaling real-time agent collaboration while maintaining fluid interaction design.

DEPTH ■■■■■26 min read7 days ago

Machine Learning

Sign in to save and rate

35Figma · architecture

Behind the build: Generative plugins and shaders at Figma

Figma developed generative plugins and shaders by replacing a prototype WebGL system with an enterprise-scale WebGPU pipeline, sandbox isolation, and custom UI kits. Through rapid prototyping and cross-functional collaboration, the team shipped the feature suite in two months for Config.

DEPTH ■■■■■8 min read7 weeks ago

Sign in to save and rate

36Stack Overflow · practice

Production-grade LLMs and agents: a field guide

Deploying LLMs and agents to production requires surrounding probabilistic models with deterministic machinery like evaluations, guardrails, and audit trails rather than relying on the model alone. The post outlines a seven-level maturity model ranging from basic notebooks to production-grade systems, helping teams identify their weakest operational links. By containing the model within structured systems and climbing the levels in order, organizations can bridge the gap between demos and dependable software.

DEPTH ■■■■■4 min read7 days ago

Machine Learning

Sign in to save and rate

37Figma · tooling

How do you actually measure the impact of AI on design?

Figma conducted a multi-year research project to track the impact of AI on product design by building an AI sentiment index and running hundreds of AI-moderated interviews. To process the massive volume of qualitative data, the team engineered a custom thematic analysis tool and an internal dashboard to serve as a cross-functional source of truth. The results showed that AI's impact on workflows and collaboration nearly doubled over three years.

DEPTH ■■■■■6 min read8 weeks ago

Sign in to save and rate

38Stack Overflow · practice

AI says you’re right, formal methods say you’re wrong

Engineers often struggle with the intimidating reputation and adoption of formal verification tools like TLA+ and its derivatives, despite their value in catching elusive edge cases and race conditions. Using specification languages to model systems allows teams to test fixes and optimizations mathematically before deploying them to production. This approach helps prevent complex bugs that take weeks to manifest in real-world traffic.

DEPTH ■■■■■28 min read11 days ago

Machine Learning

Sign in to save and rate

39Stack Overflow · practice

Why your platform team shouldn't build an AI context layer (even though they probably could)

Engineering teams often underestimate the long-term maintenance required to build and run an internal AI context layer, mistaking a simple vector database for a fully governed knowledge pipeline. Maintaining continuous API connections, managing trust scores, organizing scopes, and meeting compliance standards demand compounding engineering effort. Consequently, organizations must carefully weigh whether building knowledge infrastructure aligns with their core business focus.

DEPTH ■■■■■6 min read11 days ago

Machine Learning

Sign in to save and rate

40Stack Overflow · practice

Your next job doesn’t have a title yet: Emerging role skills Q&A with Cory Hymel of Andela

Researchers analyzed thousands of job postings to understand how artificial intelligence is changing technical skill requirements. The findings indicate that instead of creating a workforce of pure generalists, the market is developing distinct new specialized skill bundles and hybrid roles. Consequently, organizations are facing talent debt as the half-life of technical skills rapidly shrinks.

DEPTH ■■■■■15 min read12 days ago

Testing

Sign in to save and rate