Tests written by AI may pass without any actual verification, so you must verify the source of the expected values.
Woowahan Brothers trained 100 colleagues as coaches, focusing on supporting rather than replacing them with AI.
A technical guide covering four key size metrics, measurement workflows using App Thinning reports, and specific strategies for reducing binary and asset bloat.
The average test design period was reduced to 1.4 days through code-based analysis.
BankSallad Financial Services is recruiting the second cohort of financial solution experts to build an AI OS-based sales model.
It processes over 1 billion messages per day to provide product information optimized for presentation screens.
Hilt Custom Component regenerates the dependency tree upon login state changes to manage object lifecycles per user.
KT Cloud automated the upgrade of three add-ons, including ArgoCD, and the transition to GitOps using Chkk MCP.
This article summarizes the types and principles of data center cooling pumps, construction requirements, VFD control, and AI predictive maintenance solutions.
To counter HNDL attacks, PQC migration must be executed at the edge using OpenSSL 3.5 and Nginx.
To resolve memory bottlenecks caused by increasing KV Cache, a hierarchical structure utilizing layers from HBM to NVMe SSD is required.
Applying rule files allowed the agent to automatically reflect security settings, resulting in a deployment costing $0.95 per month.
KT Cloud will share insights on platform technology internalization and the use of Observability monitoring services at a webinar on December 2.
Toss implemented agent task continuity in network-segmented environments using bubblewrap isolation and PV-based state storage.
SSE adoption reduces polling load, while a zero-payload design resolves loss and ordering issues.
AI supports customer DB and consultation drafts, enabling experts to focus on coverage diagnosis and design explanations.
MUSINSA used its campaign meta-engine to automatically optimize over half of the hundreds of millions of messages sent monthly.
Toss TASTE boosted recommendation performance by 35.1% using multitask learning and applied it to other services.
Non-developer staff directly used n8n to automate repetitive tasks for the finance and CR teams.
Achieved a 2x contract conversion rate by leveraging AI tools and using easy-to-understand language in consultations.
The team completed work that would have taken 23 business days manually in 3.5 days, expanding the scope of regression testing.
AI Gateway and AI Studio provide integrated management of LLM and Agent calls while controlling costs and security.
Banksalad has filed three patents for technologies that control errors in financial transactions by AI agents.
Customers using Banksalad's data-based card recommendation service received an average benefit of 1.05 million won.
AI Briefing