AI Agents Podcast

Subscribe to AI Agents Podcast Channel:
https://link.jotform.com/subscribe-to-podcast
In this episode, we sit down with the founder and CEO of Sift AI to unpack a problem most founders don’t even realize they have: they’re solving the wrong problems.
From customer discovery and validation to the rise of “vibe founding,” we explore why asking for help with fundraising might actually mean you’re not ready yet—and how AI is both helping and hurting founders in that process.
We also dive into how tools like ChatGPT fall short when it comes to iteration, context, and real business building—and what a more structured, founder-first AI platform could look like.
If you're building (or thinking about building) something, this episode will challenge how you think about strategy, validation, and using AI the right way.
⏰ TIMESTAMPS:
00:00 – Most founders don’t know what they need help with
00:23 – The real reason you’re struggling with fundraising
01:34 – From startups to AI: the founder’s journey
03:09 – Why founders still lack real support
05:22 – The problem with ChatGPT for building businesses
07:16 – Founders don’t know what to ask AI
09:04 – ChatGPT’s bias and “people pleasing” issue
10:01 – The rise of “vibe founding”
14:14 – What “structure as a service” actually means
26:40 – The future of solopreneurs and job security
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
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 James Luan from Zilliz to talk about how AI is already changing the day to day work of engineers. James explains why coding agents are already taking over parts of his workflow, how vector databases became a core building block for modern AI systems, and why retrieval still matters even in a world obsessed with bigger models.
They also get into the real mechanics behind RAG, hallucinations, MCP, long term memory for agents, and the challenges of building production grade AI systems that can search, reason, and scale reliably. If you want a practical conversation about where agent infrastructure is going and what engineers should actually pay attention to, this episode is worth watching.
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
⏰ TIMESTAMPS:
00:00 – AI is already taking parts of engineering work
01:03 – James Luan’s background and first AI moments
07:07 – Why Zilliz was built and how vector databases fit in
16:58 – Long term memory, agent search, and reasoning workflows
21:37 – MCP, tooling limits, and real world production issues
31:02 – Are coding agents already replacing parts of engineering?
35:52 – AI for travel planning, presentations, and parallel work
38:57 – NotebookLM, Gamma, and James’s favorite AI tools
39:45 – Where to find James and Zilliz
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
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 Dror Asaf, co-founder and CTO of Coval, to talk about what it actually takes to bring agentic AI into enterprise operations. They get into why supply chain and operations are still surprisingly archaic, why trust and security are some of the biggest blockers to adoption, and how enterprise teams can use AI to remove bottlenecks without removing human decision-making.
Dror also shares how Coval is approaching enterprise AI differently, from on-prem deployments and Microsoft Teams integrations to strong governance and compliance layers. They also dig into the future of jobs, why AI will likely reshape work more than eliminate it, and why the people who know how to leverage these tools will have a massive advantage going forward.
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
⏰ TIMESTAMPS:
00:00 – AI, jobs, and why new skill sets will matter most
01:03 – Dror Asaf’s background and why he started Coval
03:42 – Raising pre-seed funding and finding the right VC partner
08:31 – Key milestones: first deployment, first failures, and building the team
11:05 – How Coval uses agents in enterprise operations and supply chain
14:04 – What Dror learned about agent reliability, governance, and hallucinations
23:58 – Coval’s edge: security, on-prem deployment, and Microsoft Teams
27:56 – The long-term vision for enterprise AI adoption
33:16 – Will AI replace jobs or transform them?
38:33 – Dror’s favorite AI tools: Claude Code, Co-work, and more
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
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 David Wong, Chief Product Officer at Thomson Reuters, to explore how AI agents are starting to reshape legal, tax, audit, and other professional services industries.

They discuss how Thomson Reuters evolved far beyond its well-known news brand into a software and research powerhouse for lawyers, accountants, tax professionals, and risk teams — and why AI is now becoming one of the biggest technological shifts those industries have ever seen.

David shares his journey from engineering, consulting, and ad systems into leading product at Thomson Reuters, along with how his team tested early GPT models on legal research years ago and watched the technology go from failing badly to becoming good enough for serious professional use cases.

Demetri and David also break down how AI can help with legal research, tax preparation, compliance work, and document-heavy workflows, why tax is such a strong fit for AI systems, and how the future of professional services may involve smaller teams supported by highly capable AI agents.

This episode is a must-watch for anyone interested in AI agents, legal tech, tax automation, enterprise workflows, and the future of knowledge work — especially if you want to understand how AI is beginning to transform industries built on expertise, research, and structured judgment.
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬⏰ TIMESTAMPS:00:00 – Smaller teams powered by AI agents
00:52 – Meet David Wong, Chief Product Officer at Thomson Reuters
01:49 – David’s background and journey into product leadership
03:24 – What Thomson Reuters actually does beyond news
06:02 – Early exposure to AI and machine learning
08:39 – Testing GPT-3 on legal research years before the boom
10:20 – Where AI helps in legal research and written work
13:55 – How AI applies to tax preparation and compliance
24:00 – Teaching AI to use tools instead of “doing the math”
33:48 – How AI could flatten team structures in professional services
47:23 – Where to learn more about Thomson Reuters and CoCounsel
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
Sign up for free ➡️ https://www.jotform.com/▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
Follow us on:Twitter ➡️ https://x.com/aiagentspodcastInstagram ➡️ 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 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
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬