Agents at work

In this episode of Agents at Work, Jordi Montes talks with Ben, the builder behind Polsia. Ben is building an AI “founding team” that can spin up and run online businesses end-to-end.Instead of asking “what can agents do in theory?”, He runs the growth loop for real: generate an idea, ship a landing page, wire up Stripe, run outreach/ads, respond to customers, ship fixes, and repeat without a human babysitting every step.They get into:- The autonomous growth loop: idea → build → launch → traffic → revenue → learn → iterate- Why the winning move is speed + distribution, and why startups that aren’t “80% autonomous” get outpaced- What it takes to give agents the full stack (web server, DB, GitHub, email, payments, ad accounts) so experiments run end-to-end- Ben’s approach to shipping fast without breaking everything (model cross-checking + safer deploy decisions)- How per-company memory + shared “best practices” turns one agent into a compounding advantage across many businesses- The real business question: do you sell software, sell tokens, or take a cut of outcomes?If you care about shipping faster than your competitors, turning experiments into compounding systems, and using agents to run the messy parts of a business (not just generate copycats) this one’s for you.

In this episode of Agents at Work, Jordi Montes sits down with Yunfan, an ex-Google / ex-Meta (Llama 3) engineer now building agents at Yutori, to talk about what it actually takes to ship agents that run continuously and stay reliable in the real world.Yunfan breaks down Scouts, Yutori’s agentic web search product that can run on a schedule (daily/weekly/hourly), browse like a human, and only notify you when something meaningfully changes without spamming your inbox. They explore:What “agents” really are: a model + a loop of action → observation → next action (and why that definition matters) Multi-agent orchestration: orchestrator + specialized agents (travel, finance, info gathering) and how “division of labor” improves performance MCP vs function calling: why Yunfan thinks many tool integrations can collapse into simple functions/scripts ( “bash is all you need”) with less complexity and less context overhead Agents need memory: why Yutori is evolving from a report archive to a real “file system” so agents can store progress, preferences, and reusable knowledge The real problem: reliability: why 95% accuracy fails at daily cadence and the push toward 99–99.9% (plus supervision/self-healing) Model economy: why not all tokens are equal, and how mixing frontier models with smaller open models makes agents affordable at scaleIf you’re building agents that have to run long workflows, browse the web, and deliver trustworthy outputs over time, this episode is for you.

In this episode of Agents at Work, Jordi sits down with Gil Feig, co-founder of Merge, to talk about the unglamorous "plumbing" that suddenly matters even more in the age of AI: integrations and data access. Gil breaks down why everyone having access to the same LLMs makes proprietary advantage shift toward who has the best data, the best access patterns, and the most reliable connections and how Merge is evolving from unified, synced integrations to agentic, MCP-style live calling. They explore:Sync vs live access: why copying + normalizing datasets helps retrieval, but comes with real cost and limits- What MCP really is (and isn’t): “list tools” + “call tool” in practiceThe security trap of tool-calling—and why Merge built DLP + approvals into the workflowHow Merge’s Agent Handler shows up in production (an MCP server backed by connectors + security) Pricing in the agent era: per tool call for the new product, and per connected customer for the classic oneIf you’re building agents that need to do real work and you want a sober take on what breaks in production, this one’s for you.

In this episode of Agents at Work, Jordi Montes sits down with Olga Beregovaya, VP of AI at Smartling, one of the leading enterprise translation and localization platforms. Together, they unpack the real state of multilingual AI and what it actually takes to translate at global scale.They explore:- The evolution of translation tech. From rule-based systems to statistical models to modern LLM-driven workflows- Why enterprise translation is a completely different game than consumer tools- The role of data cleanliness, linguistic assets, and centralization in delivering global content- What “agentic translation pipelines” are and why they outperform vanilla LLM translation- How hyper-localization, hallucination mitigation, and post-editing workflows are reshaping global content operations- Why enterprises are rethinking “build vs buy” as LLMs become deceptively easy to prototype but hard to productionize- The surprising limits of current transformer models and why purpose-built, smaller models may be the futureOlga shares 20+ years of experience in NLP, from rule-based MT to neural models to today’s multimodal systems. She explains how Smartling approaches accuracy, latency, brand voice, compliance, and global scalability for customers like Disney and IBM and why translation is becoming a business outcome, not just a linguistic task.

In this episode of Agents at Work, Jordi Montes sits down with Rodrigo Stevaux to explore how logic, formal methods, and AI are converging. Rodrigo is an economist turned technologist, researcher, and builder.They discuss: • How Rodrigo went from venture capital to deep tech and formal verification • What “formal methods” really are and why proving correctness matters more than testing • How logic programming (like Prolog) can make AI agents safer, smarter, and more deterministic • The revival of symbolic reasoning and its link to modern “neuro-symbolic” AI • Why knowledge bases and graph databases are secretly the same thing • The missing link between today’s prompt-based agents and tomorrow’s reliable systemsRodrigo shares his experience bringing old-school rigor to modern AI, from using state machines in agent design to mixing Prolog with LLMs for true reasoning. Together, they unpack why specification is the new code, and how the next breakthroughs in AI might come not from more data, but from better logic.If you’ve ever wondered how we can make AI agents reason, not just predict this conversation is a must-listen.

In this episode of Agents at Work, Jordi Montes sits down with Thais Castello, Head of Marketing & Strategy at Exa.ai, the company building the first search engine designed for AI agents.They explore:Why LLMs need a new kind of search (and why Google won’t cut it)How semantic search turns the web into a “queryable database” for AIThe role of speed, privacy, and customization in powering agent workflowsWhat it takes to build search infrastructure for AI at web scaleWhy the future of AI depends on marrying intelligence with knowledgeThais shares Exa’s vision for the next generation of search, built not only for humans, but for machines. She also dives into the creativity of their customers, the research breakthroughs behind Exa’s tech, and why performance is becoming the biggest bottleneck for AI systems.If you’ve ever wondered how AI agents actually find the information they need, or why search is quietly becoming the foundation for the next wave of AI, this episode is a must-listen.

In this episode of Agents at Work, Jordi Montes sits down with Tom Shapland , product manager at LiveKit, the open-source platform powering real-time audio/video. They power the voice agents behind ChatGPT’s audio interface.They dive into:How a LiveKit side project became the voice pipeline for ChatGPTThe rise of cascaded pipelines vs. audio-to-audio agentsWhat makes voice turn-taking so tricky (and how to fix it)The role of tone, latency, and emotion in building natural-sounding AIWhy voice agents are more than just a feature—they’re the future interfaceTom shares his journey from building agtech startups to surfing the wave of voice AI infrastructure. He unpacks what it really means to bring machines closer to humans, and why we’re entering a golden age of ambient, always-on, emotionally aware assistants.Whether you’re an engineer, product manager, or just someone dreaming of yelling at your printer and getting a helpful response this episode is a must-listen.Try it at https://livekit.io

When generating code becomes 1000x cheaper and code reviews become the bottleneck.In this episode, Jordi interviews Nimrod , co-founder and CTO of BazBaz is a company focused on code review through advanced AI and understanding of code semantics. They discuss the evolution of code analysis tools, the transition from previous ventures, and the importance of context in code reviews. Nimrod shares insights on the use of Abstract Syntax Trees (AST) and how Baz leverages them to enhance code understanding and review processes.We also talk about his journey at BridgeCrew: from writing static analysis tools for infra-as-code to getting acquired by Palo Alto Networks, scaling to 350+ enterprise customers in 3 months, and the moment things got too enterprisey and it was time to start fresh.

In this episode of Agents at Work Jordi Montes interviews Saqib Ameen, a founding engineer at Langbase. They explore the evolution of AI development beyond Silicon Valley, Saqib's journey from working on symbolic programming to building sophisticated AI agents, and the exciting launch of Chai, a platform for building and deploying production-ready AI agents.Discover how Langbase's primitives-first approach and emphasis on developer experience are revolutionizing the way engineers and companies integrate AI into their workflows. Jordi and Saqib unpack topics ranging from the technical intricacies of symbolic programming and transformer models, to practical insights on deploying scalable, version-controlled AI solutions without the DevOps headache.Whether you're an AI enthusiast, developer, or entrepreneur looking to understand how AI agents can streamline and empower your applications, this episode provides invaluable perspectives and actionable takeaways. Tune in to hear about the future of AI infrastructure, what's next for Langbase, and the key trends shaping the AI landscape in the next year.Build your agents today at https://chai.new

In this conversation, Jordi Montes and Anita from Vellum discuss the evolving landscape of AI solutions, particularly in enterprise settings.Anita, Head of Growth at Vellum.ai , emphasizes the importance of building reliable AI systems in the enterprise context. She shares her experiences building solutions for real world use cases in companies like Headspace or Redfin.The discussion also touches on client expectations, the evolution of user satisfaction, and the internal adoption of AI tools within companies.The cherry on the cake is the best definition about AI Agents I heard so far. Long story short, is about control.