AI Agents & Vibe Coding

AI Agents & Vibe Coding

Evgenii Arsentev
Country USA
Genres Technology
Language EN-US
Episodes 3
Latest 20.11.2026

This podcast offers short, practical notes from a host who runs dozens of AI agents in production every day. It focuses on what actually holds up, what it costs, and what breaks first, using real numbers rather than demos or hype. Full transcripts and a free course are available at arsentev.ai.

Episodes

  • Agent over the wire: Claude Code in phones, cars and TVs, and who is making money on it
    Agent over the wire: Claude Code in phones, cars and TVs, and who is making money on it 20.11.2026 30m
    You have Claude Code or Codex, and on social media you see people plugging an agent into a phone, a car or a TV with a cable. It is hard to tell where the toy ends and a new business begins, and whether all of this will be shut down in a month. From this episode you will understand how an agent actually controls someone else's device and why this started working right now. You will learn how startups make money on cloud phones, what it costs, and where the line runs between this and the gray zone of account farms. I break down what car makers, Google and Xiaomi are already closing off, and wha...
  • Google answers by itself, ChatGPT barely sends visitors: is SEO still worth it
    Google answers by itself, ChatGPT barely sends visitors: is SEO still worth it 18.11.2026 33m
    You built a website, and visitors from search come less and less often. Everyone around says Google will soon be useless, and it is unclear whether to keep spending time and money on promotion. In this episode you will understand why Google more and more often answers questions by itself and which pages lose visitors the most. You will learn why people do not swap Google for ChatGPT but use both, what time frame makes sense for your plans, and how many people AI models send to websites today. I explain how an AI model looks for sources for its answer and why it does not simply retell Google's...
  • Your own AI model instead of a subscription: too early for agents, already cheaper elsewhere
    Your own AI model instead of a subscription: too early for agents, already cheaper elsewhere 17.11.2026 30m
    A subscription to a strong model costs money, while free models come out almost every week, and by their own tables they are barely worse. It is tempting to download one, run it yourself and stop paying. For an agent's main work this is not the answer yet, and speed is not the reason. A big model simply has nowhere to live at home. A small one makes mistakes slightly more often at each step, and on a long task those mistakes add up to failure. You will understand why you should not trust the tables in announcements, and you will learn how to ask your agent to compare models on thirty to a hund...
  • AI agents already get jobs and money. Where this leads in a few years and how to prepare
    AI agents already get jobs and money. Where this leads in a few years and how to prepare 16.11.2026 35m
    The news about AI agents says opposite things every day: one day they are taking jobs, the next day the people fired because of them are being called back. If you are building a project with an agent yourself, it is hard to know what to count on a year or three years from now. From this episode you will take away a simple way to make sense of such news: look not at who promises what, but at what has been measured and how that number changed over a year. I talk about what is already happening with agents and where, in my view, it will lead in two to four years. You will learn what work an agent...
  • An AI-built app can show your users' data to strangers: what to check before launch
    An AI-built app can show your users' data to strangers: what to check before launch 15.11.2026 32m
    On a forum built with AI, any visitor could read more than eighty thousand profiles and two hundred thousand chat messages. Another service left more than a thousand records with passport numbers open in the same way. Nobody hacked anything: the doors were simply never locked. In November, several reports on this came out at once. A German security firm checked sites made with Lovable, an app builder where you describe an app in words and AI builds it. Another team studied apps from a similar builder, Grok, and found a hospital staff list and a briefing on an intensive care patient open to any...
  • LangChain at $3 billion: how the company runs on its own agents
    LangChain at $3 billion: how the company runs on its own agents 14.11.2026 34m
    LangChain raised three hundred million dollars at a valuation of three billion, more than twice what it was worth a year ago. The company grew out of an eight-hundred-line side project by Harrison Chase. The heart of the episode is how LangChain itself runs on agents. Chase estimates that coding agents cost roughly thirty percent of the engineering payroll, and explains how the company keeps that spending in check. A sales agent prepares email drafts for salespeople in Slack and learns from their edits. Another agent looks for new errors after each code deployment and proposes fixes on its own...
  • OpenAI and Anthropic's money: who really makes money from AI
    OpenAI and Anthropic's money: who really makes money from AI 13.11.2026 27m
    Anthropic has almost broken even, while OpenAI spends about two dollars for every dollar it earns. In November both companies' quarterly numbers came out: almost $17 billion in revenue for Anthropic, more than $10 billion for the first time for OpenAI. The headlines said Anthropic had overtaken its rival. But the two companies count revenue differently, and the gap is smaller than it looks. Anthropic has filed for its IPO, and this is the most detailed look inside any company in the industry. Three quarters of its revenue comes from large customers, growth comes from the bottom up, from progra...
  • OpenAI Bought Odessia: A Travel Agency Run by Eight People and AI Agents
    OpenAI Bought Odessia: A Travel Agency Run by Eight People and AI Agents 12.11.2026 22m
    Eight people and AI agents built a real travel agency in under a year. Twenty-seven days after launch, OpenAI bought it. Before Odessia, founder Francis Davidson spent ten years building Sonder: more than a thousand employees, hundreds of millions of dollars in leases, and a bankruptcy. He built the new company the opposite way. Agents handled not only the code but also marketing, customer support, legal and finance. They read meeting recordings and email and kept working at night while the people slept. The episode covers the six rules the team worked by, what a startup can copy tomorrow, and...
  • AI Agent Tests All Green? Why That Proves Nothing When You Compare Setups
    AI Agent Tests All Green? Why That Proves Nothing When You Compare Setups 26.09.2026 6m
    You change the model, the prompt or how often the agent's context is cleared, rerun, and every test is green. That tells you less than it seems. In 36 runs of a coding agent under six context-clearing policies, 4,086 tests passed with zero failures while cost differed by 33.5% between the most and least expensive of the six condition averages. The agent wrote its own tests in every run, from 97 to 127 per run, so the runs had no shared checks to compare. This episode explains why a test suite can be blind to the very difference you are testing, why the tempting "longer sessions did less work"...
  • AI Content Engine: What It Costs When AI Agents Replace a Video Studio
    AI Content Engine: What It Costs When AI Agents Replace a Video Studio 16.09.2026 15m
    An AI content engine is a system where AI writes the scripts, AI avatars appear on camera, a synthetic voice talks and software edits and publishes. This episode walks through a working one: built by one person with no technical background, 1,497 videos across 67 channels in 101 days, 52 cents per 1,000 views. What a human studio or influencers would cost for the same output, why organic reach grows with a delay, a forecast for 100 AI presenters, and four steps for a business. Technical report with every calculation: https://doi.org/10.5281/zenodo.22802228 Full transcript of this episode: arse...
  • When to Clear an Agent's Context: A Measured U-Curve
    When to Clear an Agent's Context: A Measured U-Curve 11.09.2026 4m
    Correction, 15 September 2026: the audio and the transcript below use the prices of report versions 1.0 and 1.1, which were wrong. At the correct prices, a run costs $2.17 when the context is cleared after every task, $1.62 at every third task and $1.78 when it is never cleared (not $2.68, $2.14 and $2.47). Clearing after every task costs 33.5% more than the best policy (not 25%). Never clearing costs 9.7% more (not 16%), and that difference is not statistically significant (p = 0.046; 0.14 after adjustment for multiple comparisons). A cache write costs 20 times a cache read, not twelve and a...
  • AI from Zero: How to Become a Vibe Coder and Stop Fearing the Terminal
    AI from Zero: How to Become a Vibe Coder and Stop Fearing the Terminal 11.09.2026 16m
    A long episode for anyone who has never opened the black window full of text and is sure it isn't for them Full transcript of this episode: arsentev.ai/podcast
  • Claude Code: How to Cut Your Token Spend
    Claude Code: How to Cut Your Token Spend 08.09.2026 5m
    How to cut your token spend in Claude Code, or any other AI, several times over. Why the model rereads the whole conversation on every reply, what the context actually is, and why a bloated context makes the model dumber. One command, one habit of writing to a file, and one rule: one task, one chat, closed. Full transcript of this episode: arsentev.ai/podcast

Popular in

The podcast also appears in the podcast charts of these countries.