LangTalks
Lee Twito, Gal Peretz
Show overview
LangTalks has been publishing since 2023, and across the 3 years since has built a catalogue of 68 episodes. That works out to roughly 30 hours of audio in total. Releases follow a fortnightly cadence.
Episodes typically run twenty to thirty-five minutes — most land between 25 min and 30 min — and the run-time is fairly consistent across the catalogue. None of the episodes are flagged explicit by the publisher. It is catalogued as a HE-language Technology show.
The show is actively publishing — the most recent episode landed 2 weeks ago, with 9 episodes already out so far this year. Published by Lee Twito, Gal Peretz.
From the publisher
פודקסט טכני בעברית על בניית סוכנים ואפליקציות עם מודלי שפה. הצטרפו לקהילת הווטסאפ שלנו לדיונים ושאלות: https://chat.whatsapp.com/JKVFSNFMVQu8G1KWx1jqap ניוזלטר עם סיכום דו-שבועי של כל הנושאים הכי חמים: www.langtalks.ai
Latest Episodes
View all 68 episodes68 - AI-SDLC | Yonatan Maor (Clears.ai)
67 - FinOps for AI | Yizhar (Finout)
66 - Scaling LLMOps | Avi Lumelsky (Oligo)
65 - AI SRE | Asaf Savich (Komodor)
Site Reliability Engineer agent auto fixes production issues
S1 Ep 6464 - AI coding metrics | Liad Elidan (Milestone)
Measure the actual impact of adopting AI across the R&D
S1 Ep 6363 - WAKE UP
Singularity and AGI are around the corner.
S1 Ep 6262 - AI R&D Rollout | Iko Azoulay (Salt Security)
How AI is used across the SDLC in a real R&D org - requirements, tech design, validation, testing, and code review. What worked, what didn’t, and where teams get stuck.
S1 Ep 6161 - Voice Agents | Shay Davidson (Lemonade)
Building and testing voice agents with realtime API or chained approach (TTS->LLM->STT)
S1 Ep 6060 - Brain Memory | Dr. Meytar Zemer
The Neuroscience behind the human brain and memories
S1 Ep 5959 - SLMs | Dr Elad Granot (Trullion)
the production experience and considerations for fine-tuning a small language model for narrow tasks
S1 Ep 5858 - AWS re:Invent 2026 predictions | Shuki Cohen (AI21)
Recap of the major announcements and innovations from the 2025 re:Invent conference, along with our predictions for where things are heading in 2026
S1 Ep 5757 - Memory | Itamar Friedman (Qodo)
Short and long term memory mechanisms for agents
S1 Ep 5656 - n8n | Shay Shitrit
Getting started with no-code agentic automations, popular use cases and tips
S1 Ep 5555 - Context Engineering
The state of best practices for context engineering, focused on AI-coding as a leading use case
S1 Ep 5454 - Permissions | Or Weis (Permit.io)
Enabling secured flexibility to your agents and MCP servers
S1 Ep 5353 - Search & Retrieval | Guy Itach (Fiverr)
techniques to combine classic search with agentic retrieval
S1 Ep 5252 - Agents at scale | Adam Cohen Hillel
The story of building Suna - the open source alternative of Manus the generalist autonomous agent https://github.com/kortix-ai/suna
S1 Ep 5151 - Our AI-driven coding workflow | Oren Melamed
Sharing our workflow with Cursor, Claude Code, GitHub Copilot and others. Listed the useful MCPs and tools, how to measure efficiency gains, and our vision for the future of coding
S1 Ep 5050 - A2A protocol
Is this Agent2Agent new protocol by Google going to be the next MCP?
S1 Ep 4949 - Documents analysis
How to handle long docs like PDF and Docx effectively with LLMs