Alina Dolgikh [JB]
Alina Dolgikh [JB]
Alina Dolgikh [JB]
Alina Dolgikh [JB]
Alina Dolgikh [JB]
Alina Dolgikh [JB]
Alina Dolgikh [JB]
Alina Dolgikh [JB]
Alina Dolgikh [JB]
Alina Dolgikh [JB]
Alina Dolgikh [JB]
Alina Dolgikh [JB]
Alina Dolgikh [JB]
Alina Dolgikh [JB]
Alina Dolgikh [JB]
Alina Dolgikh [JB]
Alina Dolgikh [JB]
Alina Dolgikh [JB]
Alina Dolgikh [JB]
Alina Dolgikh [JB]
Alina Dolgikh [JB]
Alina Dolgikh [JB]
Alina Dolgikh [JB]
Alina Dolgikh [JB]
Alina Dolgikh [JB]
ExecuteShellCommandTool.
• Handling confirmation, sandboxing concerns, and Brave mode.
• How timeouts work and why they matter for LLMs.
• How the agent’s system prompts change to encourage test-driven behavior.
• Benchmark results after adding execution capability.
If you’re experimenting with agents, this post provides a good overview of how tool design works in Koog.
➡️ Read it here: https://kotl.in/koog-tutorial-2Alina Dolgikh [JB]
“Is sticking to ‘Android-only’ a risky career strategy?”
“Convincing iOS teams is harder than writing the code.We need your input for the Q&A: We want to challenge the panel with real problems. Drop your questions in thread regarding: • Career risks (Generalist vs Specialist) • Technical blockers (Tooling, Swift Interop) • Team dynamics 🎓 Catch up on Resources Since this is the finale, the Campaign Hub is fully unlocked. You can now access the 5-hour Compose Multiplatform crash course, the learning matrix, and our ultimate KMP binge-watch list 🍿 all in one place. 👉 Secure your seat & get the resources: https://jb.gg/5k396j
Alina Dolgikh [JB]
Alina Dolgikh [JB]
Alina Dolgikh [JB]
Alina Dolgikh [JB]