#toss

Toss TASTE boosted recommendation performance by 35.1% using multitask learning and applied it to other services.

Toss·2026.11.09 15:00

Toss significantly reduced LLM invocation costs by applying Selective Neural Approximation (SNAP).

Toss·1·2026.10.27 16:00

Toss converted log definition tasks into AI skills to achieve consistent specification management based on domain context.

Toss·2·2026.10.23 10:00

Automated model invocation, security, and cost management through the GenAI Portal and Gateway.

Toss·3·2026.10.13 10:00

Reducing the number of candidates by half increased orders per user by 10.13% while decreasing CTR by 3.71%

Toss·1·2026.10.01 10:00

Toss Doctor V2 combines LLMs and Appium MCP to automate everything from test code generation to failure recovery, extending to regression testing via Toss Checker.

Toss·4·2026.09.22 12:00

Toss analyzed the discrepancy between public benchmarks and actual service performance, establishing Toss Benchmark as a domain-specific evaluation standard.

Toss·2·2026.09.16 14:00

Toss has built a knowledge management system through its internal documentation platform 'todoc', which supports AI integration and automated validity management.

Toss·2·2026.09.07 15:00

Toss's technical documentation team is expanding its role from simple documentation to designing organization-specific knowledge systems, automating knowledge through the internal platform 'todoc'.

Toss·2·2026.09.07 15:00

Toss introduced the RAG-based chatbot Mr. Park and the automation tool Sillokbot to reduce developers' burden of searching for documentation and improve knowledge-sharing efficiency.

Toss·2026.09.07 15:00

Toss has unveiled TOI, an AI-based admin creation platform, and reduced first-screen loading time to 1.3 seconds by implementing an in-browser Preview Runtime.

Toss·4·2026.09.04 17:00

The Toss QA team shifted hotfix decision criteria from priority to go/no-go status to align with gradual rollout environments, introducing an AI-based crash reproduction tool and an automated logging system.

Toss·1·2026.08.28 17:00

Toss moved filtering and sorting for its ad dashboard from the server to the browser, improving navigation speed and UX.

Toss·4·2026.08.20 10:00

Toss directly implemented MRAID-standard-based playable ads to improve game ad performance.

Toss·1·2026.08.18 10:00

Toss has built its own platform, Tossion, which integrates QA data and AI-based release verification.

Toss·1·2026.08.11 10:00

Toss resolved monorepo fragmentation by using a catalog to unify dependency versions.

Toss·1·2026.08.10 11:00

Toss built a 'Topic' system that connects documents, code, and messenger conversations so LLMs can accurately understand internal company information, managing trustworthy context.

Toss·2026.07.30 14:00

Toss built its own device farm, 'Nebula,' which can control hundreds of real devices with just an API call.

Toss·4·2026.07.30 11:00

The Toss QA Platform team introduces Tossion, its in-house QA platform built to maintain quality amid weekly large-scale deployments with recurring changes.

Toss·5·2026.06.26 09:00

This covers how es-toolkit, once an internal utility library at Toss, grew into a global project through performance optimization.

Toss·2·2026.06.24 12:00

Toss went beyond simple documentation tools and built a governance system to secure the reliability of knowledge while collaborating with AI.

Toss·1·2026.06.23 11:00

Toss's Technical Writing partner introduces a journey of using AI to automate document writing and review processes.

Toss·2·2026.06.23 11:00

This covers how es-toolkit, created by Toss to address the inefficiencies of lodash, grew into a globally used open-source library.

Toss·1·2026.06.22 21:00

Toss shared strategies for lowering the psychological barriers to knowledge sharing and using AI to improve documentation efficiency.

Toss·3·2026.06.22 11:00