Agentic Pod

Agentic Pod

By Agentic PodTechnology
Download on the App Store

Agentic Pod episodes

  • What Is Gemini 4 Hydrogen? Google's Fast Agentic Model Explained
    Google announced Gemini 4 Hydrogen on November 12, 2026, built for speed and efficiency in everyday coding and agentic workflows, 2.5 times faster than Gemini 3.8 Flash.
    Chapters:
    0:00 Intro
    0:49 Speed and scores that matter
    1:46 4 thinking levels and flat pricing
    2:48 How it works in real agentic jobs
    3:49 Partners, rollout and the honest verdict
    Show notes, links and full transcript: https://www.agenticpod.net/episodes/ep44-gemini-4-hydrogen/
    Stella and Liam are AI hosts with AI-generated voices.
    6 min
  • Does Apache Kafka Remember Between Runs? What a Record Keeps and What It Loses
    A Kafka record can sit in its log for 7 days by default, readable again and again, and the next run still starts knowing nothing about the work already done on it.
    Chapters:
    0:00 Intro
    0:39 What a Kafka record actually keeps
    1:54 An offset is only a position
    2:46 Replay gives the record, never the result
    3:48 The Vilix AI fix and the verdict
    Show notes, links and full transcript: https://www.agenticpod.net/episodes/ep43-kafka-remember-between-runs/
    Stella and Liam are AI hosts with AI-generated voices.
    6 min
  • What Is GPT-5.1? Instant, Thinking and 8 Personalities Explained
    OpenAI released GPT-5.1 on November 12, 2026, as an upgrade inside the GPT-5 generation, with Instant, Thinking, Auto routing and 8 personality presets.
    Chapters:
    0:00 Intro
    0:45 Two models and Auto picks for you
    1:32 Instant got warmer and learned when to think
    2:18 Thinking spends time where it counts
    3:04 8 personalities, rollout and the honest verdict
    Show notes, links and full transcript: https://www.agenticpod.net/episodes/ep42-gpt-5-1-instant-thinking/
    Stella and Liam are AI hosts with AI-generated voices.
    6 min
  • Does Amazon Kinesis Remember Between Runs? What a Record Keeps and What It Loses
    A Kinesis record can sit in its stream for 24 hours by default, or up to 8760 hours, and the next run still starts knowing nothing about the work already done on it.
    Chapters:
    0:00 Intro
    0:46 What a Kinesis record actually keeps
    1:55 Checkpoints live outside the stream
    2:39 Replay is not memory of work
    3:53 The Vilix AI fix and the verdict
    Show notes, links and full transcript: https://www.agenticpod.net/episodes/ep41-kinesis-remember-between-runs/
    Stella and Liam are AI hosts with AI-generated voices.
    6 min
  • What Is Claude Fable 5.2? Effort, Fast Mode and the Real Cost per Task
    Anthropic released Claude Fable 5.2 and Claude Mythos 5.2 on November 9, 2026: the same underlying model at two safeguard levels, with Fable as the public one.
    Chapters:
    0:00 Intro
    0:41 What Fable 5.2 and Mythos 5.2 actually are
    1:38 The price, the speed, and fast mode
    2:41 Effort levels and the real cost per task
    4:05 Migration gotchas and the honest verdict
    Show notes, links and full transcript: https://www.agenticpod.net/episodes/ep40-claude-fable-5-2/
    Stella and Liam are AI hosts with AI-generated voices.
    6 min
  • Does Devin Remember Between Sessions? What Carries Over and What Starts Blank
    Devin can take 1 ticket, plan, code, test, and open a pull request on its own, and the next session still starts with no memory of that work.
    Chapters:
    0:00 Intro
    0:45 How Devin runs a session
    1:38 What actually carries over
    3:07 Scheduled sessions and the Desktop split
    4:13 The Vilix AI fix and the verdict
    Show notes, links and full transcript: https://www.agenticpod.net/episodes/ep39-devin-remember-between-sessions/
    Stella and Liam are AI hosts with AI-generated voices.
    6 min
  • What Is Meta Muse Ember? The Tiny Model Built for Agent Tasks
    Meta Superintelligence Labs just launched Muse Ember, its smallest and most efficient model, built for the repetitive work inside agent runs.
    Chapters:
    0:00 Intro
    0:40 What Muse Ember is and why it matters
    1:36 The numbers: pricing, context and benchmarks
    3:08 How to try it and a real workflow
    4:22 Gotchas, who it is for, and the verdict
    Show notes, links and full transcript: https://www.agenticpod.net/episodes/ep38-meta-muse-ember/
    Stella and Liam are AI hosts with AI-generated voices.
    6 min
  • Does NSQ Remember Between Runs? The Next Message Starts Blank
    NSQ can hold 10,000 messages in memory for one topic and channel, and it still remembers no results at all.
    Chapters:
    0:00 Intro
    0:38 How NSQ moves a message
    1:38 Why the next run starts blank
    2:33 Monday, Tuesday, and the repeat flag
    3:24 The Vilix AI fix and the verdict
    Show notes, links and full transcript: https://www.agenticpod.net/episodes/ep37-nsq-remember-between-runs/
    Stella and Liam are AI hosts with AI-generated voices.
    6 min
  • What Is Google's Elephant-Goldfish Plugin? Review the Plan Before the Code
    Google open-sourced the plugin its own engineers use to catch AI coding mistakes, and the reviewer is a goldfish on purpose.
    Chapters:
    0:00 Intro
    0:47 What the Elephant-Goldfish model is
    1:47 The commands, step by step
    2:48 How to install it
    3:45 Gotchas, who it's for, and the verdict
    Show notes, links and full transcript: https://www.agenticpod.net/episodes/ep36-elephant-goldfish-plan-review/
    Stella and Liam are AI hosts with AI-generated voices.
    6 min
  • What Is the Best AI Memory Tool for Coding Agents? 10 Compared
    A coding agent without memory shows up every day with no idea what happened yesterday.
    Chapters:
    0:00 Intro
    0:49 Why your coding agent forgets
    1:47 The ten tools in three buckets
    2:44 How Vilix AI fixes the first two pains
    4:04 How to choose, and the verdict
    Show notes, links and full transcript: https://www.agenticpod.net/episodes/ep35-ai-memory-tools-coding-agents/
    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.