1 source filed · RU 1
Workshop data: coding agents erred on unfamiliar collaboration tools in 4% of attributable requests, chat agents in 6.5%; 94% recovered on their own.
4% vs 6.5%requests with errors on unfamiliar collaboration tools: coding agents (Codex, Claude Code) versus chat agents (ChatGPT, Claude Chat)
1 source filed · RU 1
Over two days and 20 participants: 8,650 sandbox runs, 697 changes and 150 experiments with 1.4 GB of data.
20workshop participants whose own ChatGPT and Claude agents shared one memory layer
2 sources filed · EN 1 · RU 1
Agents and models (July 2026 configurations): Codex with GPT-5.4, Claude Code with Claude Opus 5, Kimi Code with Kimi K3.
1.41-3.31xtoken usage of concurrent versus sequential execution across agents
The specification is the single source of truth; code is treated as secondary and in principle regenerable in another language.
about 90%share of reviewer blockers caused by missing edge-case tests