Subscribe to AI Agents Podcast Channel: https://link.jotform.com/subscribe-to-podcast

In this episode of the AI Agents Podcast, host Demetri Panici sits down with Bryan Raymond, founder and CEO of Unstructured, to break down one of the least flashy but most important layers in AI: data preparation. They dig into why so many AI prototypes still fail in practice, why RAG systems struggle with messy enterprise data, and how structured inputs like JSON, Markdown, and HTML can dramatically improve model performance.

Bryan explains how Unstructured helps enterprises turn raw files, scanned documents, audio, video, and other messy sources into AI-ready data for RAG pipelines and agent systems. The conversation covers why context quality matters so much, why tables and document layout are still hard for models, how vision-language models changed the game, and what it takes to move from AI prototype to production.

They also get into where AI is heading in 2026: declining failure rates, more practical “bread and butter” use cases, better multi-agent systems, and why companies like Cursor and Lovable have succeeded by packaging great UX around powerful infrastructure. If you want a clearer view of what’s actually missing in enterprise AI stacks right now, this episode is a must-watch.

▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
⏰ TIMESTAMPS:
00:00 – Why AI still feels exciting and broken at the same time
01:03 – Bryan Raymond’s background and the origin of Unstructured
03:03 – What Unstructured does: turning raw data into AI-ready data
06:06 – Why RAG exists and why structured data matters so much
10:42 – The hard part: tables, layouts, scanned PDFs, and document parsing
17:48 – Who needs this most: gen-AI teams vs data engineering teams
20:20 – The industries moving fastest with enterprise AI
26:28 – 2026 predictions: lower failure rates and stronger agent systems
29:33 – Cursor, Lovable, enterprise UX, and where AI infrastructure is heading
33:42 – AI jobs, junior engineers, and where real opportunity still exists
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
Sign up for free ➡️ https://www.jotform.com/

▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
Follow us on:
Twitter ➡️ https://x.com/aiagentspodcast

Instagram ➡️ https://www.instagram.com/aiagentspodcast

TikTok ➡️ https://www.tiktok.com/@aiagentspodcast

▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬

Subscribe to AI Agents Podcast Channel: https://link.jotform.com/subscribe-to-podcast

In this episode of the AI Agents Podcast, host Demetri Panici sits down with Jotform CEO Aytekin Tank to explore Claude Code — a powerful AI development tool that lets you build, edit, and deploy entire applications simply by describing what you want.

They walk through how Claude Code makes it possible to rebuild abandoned websites, deploy them with Vercel, and manage entire projects without writing a single line of code.

By running multiple coding sessions in parallel, developers and non-developers alike can work on several products at once while AI handles the implementation.

The conversation also dives into a live demo showing how Claude Code plans changes, modifies a codebase, creates a contact page using Jotform, and pushes updates to a project in real time.

Along the way, they discuss how AI coding tools are changing the development workflow — from “vibe coding” and parallel agents to automated GitHub workflows that keep projects updated daily.

More importantly, they explore the bigger shift happening in software: when AI handles most of the technical execution, the real bottleneck becomes ideas, product taste, and knowing what to build.

If you're curious about the future of AI-assisted development, autonomous coding agents, and how tools like Claude Code could change the way products are built, this episode is a deep dive into what might be the next era of software creation.

▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬⏰ TIMESTAMPS:

00:00 – Rebuilding multiple abandoned websites with Claude Code

03:26 – Using Claude Code alongside OpenClaw infrastructure

07:18 – Why ideas and product taste are becoming the new bottleneck

16:08 – Watching Claude Code execute the development plan

22:38 – Using GitHub to automate website updates

31:11 – Running multiple AI coding agents simultaneously

35:21 – Brainstorming and planning features with AI skills

39:13 – Executing AI-generated development plans

44:11 – Avoiding conflicts when editing projects in parallel

48:02 – The “ChatGPT moment” for AI coding tools

49:28 – Why 2026 feels like a new era for building software

50:23 – Final thoughts on the future of AI-assisted development

▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬

Sign up for free ➡️ https://www.jotform.com/▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬

Follow us on:

Twitter ➡️ https://x.com/aiagentspodcast

Instagram ➡️ https://www.instagram.com/aiagentspodcast

TikTok ➡️ https://www.tiktok.com/@aiagentspodcast

▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬

Subscribe to AI Agents Podcast Channel: https://link.jotform.com/subscribe-to-podcastIn this episode of the AI Agents Podcast, hosts Aytekin Tank and Demetri Panici break down OpenClaw — a wildly powerful “AI that actually does things.”

They compare it to tools like Claude Co-Work, show a live demo pulling G2 reviews and generating a report + Keynote deck, and talk about what it means when agents can run 24/7 via Telegram/Slack/WhatsApp.They also dig into the real tradeoff: OpenClaw’s insane capability (always-on, self-healing/heartbeat, autonomous computer control, agent teams) versus the security risks of giving an unvetted agent too much access.

If you’re thinking about running agents on a dedicated machine (like a Mac mini), this episode is basically a “do this, not that” starter kit.This episode is a must-watch for anyone curious about autonomous agents, recurring workflows, and the early “AI employee” era — plus how to use these tools safely without nuking your accounts.

▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬⏰ TIMESTAMPS:00:00 – OpenClaw, always-on agents, and “it figured it out”00:54 – Why OpenClaw might be the craziest tool on the show02:15 – OpenClaw’s rise, name changes, and security concerns04:18 – OpenClaw vs Claude Co-Work (control + limits)07:39 – Live demo: pulling G2 reviews and generating insights12:08 – Making the report better + turning it into a Keynote deck18:02 – How to run OpenClaw via VM/Mac mini + messaging it remotely21:25 – Agent teams + “AI departments” doing recurring work32:14 – Safety checklist: what NOT to give agents access to37:39 – Agents making social networks (and weird agent behavior)46:52 – Final thoughts + using agents responsibly49:13 – Wrap-up▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬Sign up for free ➡️ https://www.jotform.com/▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬Follow us on: Twitter ➡️ https://x.com/aiagentspodcastInstagram ➡️ https://www.instagram.com/aiagentspodcastTikTok ➡️ https://www.tiktok.com/@aiagentspodcast▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬