Agentic Pod

Agentic Pod

By Agentic PodTechnology
Download on the App Store

Agentic Pod episodes

  • What Is DeepSeek Super-Agent? The Coding Agent That Speaks First
    Every coding agent you know waits for a prompt. DeepSeek open-sourced Super-Agent, an MIT licensed research prototype that watches a repo and group chat, spots coding problems on its own, and proposes fixes without being asked.
    Chapters:
    0:00 Intro
    0:52 What Super-Agent actually is
    2:03 How a proactive agent changes the workflow
    3:18 How to try it, carefully
    4:09 Why it matters and the verdict
    Show notes, links and full transcript: https://www.agenticpod.net/episodes/ep34-deepseek-super-agent/
    Stella and Liam are AI hosts with AI-generated voices.
    6 min
  • How Do You Give a WhatsApp AI Agent Memory Between Conversations?
    WhatsApp gives your AI agent zero memory: every message arrives as its own webhook and the model call is stateless. The fix is a load then save pattern on every turn, keyed by phone number.
    Chapters:
    0:00 Intro
    0:39 Why WhatsApp agents forget
    1:42 What the agent should remember
    2:50 The fix, step by step
    4:28 The client angle and the verdict
    Show notes, links and full transcript: https://www.agenticpod.net/episodes/ep33-whatsapp-agent-memory/
    Stella and Liam are AI hosts with AI-generated voices.
    6 min
  • What Is the Best AI Agent Memory for Make Workflows?
    Leave one field blank in Make's AI agent module, the Conversation ID, and every run starts as a brand new agent that knows nothing.
    Chapters:
    0:00 Intro
    0:36 The blank field problem
    1:34 The options, from Data Stores to Mem0
    3:25 Memory that leaves Make
    4:26 The verdict
    Show notes, links and full transcript: https://www.agenticpod.net/episodes/ep31-make-workflows-agent-memory/
    Stella and Liam are AI hosts with AI-generated voices.
    6 min
  • How Do You Give OpenAI Codex a Memory?
    OpenAI Codex only knows what is in front of it, so every session starts cold: no stack, no rules, and none of the decisions you made in ChatGPT or Claude.
    Chapters:
    0:00 Intro
    0:35 Why Codex starts cold
    1:21 The setup, step by step
    2:33 What Codex gets back
    3:35 The client angle, and the verdict
    Show notes, links and full transcript: https://www.agenticpod.net/episodes/ep28-codex-memory-vilix-ai/
    Stella and Liam are AI hosts with AI-generated voices.
    5 min
  • Can You Run a Free AI Coding Model on Your Laptop? Recursive Flint
    Recursive released Flint on October 21, 2026: a free, Apache 2.0 coding model with about 40 billion parameters in total and only 2.5 billion active per token, so it can run on a laptop.
    Chapters:
    0:00 Intro
    0:38 What Flint actually is
    1:35 How to run it on your machine
    2:37 A workflow that fits a small model
    3:36 Gotchas and the verdict
    Show notes, links and full transcript: https://www.agenticpod.net/episodes/ep30-recursive-flint-laptop-coding-model/
    Stella and Liam are AI hosts with AI-generated voices.
    5 min
  • How Do You Share Memory Across AI Tools?
    Every AI tool has its own memory, and each one is private to the app that made it. Teach Claude your deploy rules, open Cursor, and you start from zero.
    Chapters:
    0:00 Intro
    0:36 Why every tool is its own silo
    1:28 Folders and servers, where they break
    2:25 What your tools get back
    3:14 The client angle, and the verdict
    Show notes, links and full transcript: https://www.agenticpod.net/episodes/ep29-share-memory-across-ai-tools/
    Stella and Liam are AI hosts with AI-generated voices.
    5 min
  • What Is Claude Duet, and How Do You Try It?
    Anthropic launched Claude Duet on October 21, 2026: a background agent on Opus 5.5 that sends a morning brief, checks your connected accounts every few hours and keeps working on its own cloud computer.
    Chapters:
    0:00 Intro
    0:39 What Duet actually is
    1:29 The approval gate
    2:32 How to try it today
    3:33 Gotchas and the verdict
    Show notes, links and full transcript: https://www.agenticpod.net/episodes/ep27-claude-duet-background-agent/
    Stella and Liam are AI hosts with AI-generated voices.
    5 min
  • Can Notion Agents Really Run for 24 Hours?
    Notion's October 19 release rebuilt its agents so a single task can run more than 24 hours, up from five minutes, and added an Auto model router and a new credit system.
    Chapters:
    0:00 Intro
    0:38 What Notion actually changed
    1:25 Auto, and what it costs
    2:27 How to try it today
    3:08 Gotchas, and the verdict
    Show notes, links and full transcript: https://www.agenticpod.net/episodes/ep26-notion-agents-24-hours/
    Stella and Liam are AI hosts with AI-generated voices.
    5 min
  • Does Cursor Remember Between Sessions?
    Cursor keeps your chat history, Memories, rules files and a codebase index, and it still forgets what you decided yesterday.
    Chapters:
    0:00 Intro
    0:42 What Cursor does keep
    1:31 What none of that gives you
    2:14 The fix: Vilix AI as Cursor's memory
    3:33 Setup, and the client angle
    Show notes, links and full transcript: https://www.agenticpod.net/episodes/ep25-cursor-remember-between-sessions/
    Stella and Liam are AI hosts with AI-generated voices.
    5 min
  • Can You Run Claude Code on DeepSeek's Flash Model?
    DeepSeek's API docs now list Claude Code as a supported agent, and the model behind the name deepseek-flash is DeepSeek-V4.1-Flash-1017.
    Chapters:
    0:00 Intro
    0:37 What DeepSeek actually changed
    1:37 The setup, step by step
    2:44 Gotchas and limits
    3:49 Who it's for, and the verdict
    Show notes, links and full transcript: https://www.agenticpod.net/episodes/ep24-deepseek-flash-claude-code/
    Stella and Liam are AI hosts with AI-generated voices.
    5 min

About Agentic Pod

From the publisher's feed

Agentic Pod is a daily podcast about AI workflows, AI agents and the tools behind them. Stella asks the questions everyone is thinking, and Liam answers with real workflows you can copy today. No hype, no fluff.