https://parlant.io/blogParlant Blog2026-04-25T00:00:00.000Zhttps://github.com/jpmonette/feedParlant Bloghttps://parlant.io/logo/icons/mstile-150x150.png<![CDATA[The Age of Harnesses]]>https://parlant.io/blog/the-age-of-harnesses2026-04-25T00:00:00.000ZYam Marcovitzhttps://www.linkedin.com/in/yam-marcovic/<![CDATA[Parlant 3.3: Scaling Control]]>https://parlant.io/blog/parlant-3-3-release2026-03-15T00:00:00.000ZYam Marcovitzhttps://www.linkedin.com/in/yam-marcovic/<![CDATA[Parlant 3.2: Streaming Responses]]>https://parlant.io/blog/parlant-3-2-streaming-responses2026-02-08T00:00:00.000ZYam Marcovitzhttps://www.linkedin.com/in/yam-marcovic/<![CDATA[Parlant 3.1]]>https://parlant.io/blog/parlant-3-1-release2026-01-01T00:00:00.000ZYam Marcovitzhttps://www.linkedin.com/in/yam-marcovic/<![CDATA[Criticality-Based Resource Allocation]]>https://parlant.io/blog/criticality-in-customer-facing-agents2025-12-23T00:00:00.000ZYam Marcovitzhttps://www.linkedin.com/in/yam-marcovic/<![CDATA[Inside Parlant's Guideline Matching Engine]]>https://parlant.io/blog/inside-parlant-guideline-matching-engine2025-11-01T00:00:00.000ZYam Marcovitzhttps://www.linkedin.com/in/yam-marcovic/<![CDATA[Parlant vs LangGraph]]>https://parlant.io/blog/parlant-vs-langgraph2025-10-18T00:00:00.000ZYam Marcovitzhttps://www.linkedin.com/in/yam-marcovic/<![CDATA[Parlant vs DSPy]]>https://parlant.io/blog/parlant-vs-dspy2025-10-01T00:00:00.000ZYam Marcovitzhttps://www.linkedin.com/in/yam-marcovic/<![CDATA[How Parlant Guarantees Compliance]]>https://parlant.io/blog/how-parlant-guarantees-compliance2025-08-17T00:00:00.000ZYam Marcovitzhttps://www.linkedin.com/in/yam-marcovic/<![CDATA[Parlant 3.0 — Reliable AI Agents]]>https://parlant.io/blog/parlant-3-0-release2025-08-15T00:00:00.000ZYam Marcovitzhttps://www.linkedin.com/in/yam-marcovic/<![CDATA[Agentic Backends: What I Wish Someone Had Told Me About API Design for LLMs]]>https://parlant.io/blog/what-no-one-tells-you-about-agentic-api-design2025-07-15T00:00:00.000ZYam Marcovitzhttps://www.linkedin.com/in/yam-marcovic/<![CDATA[Increasing the Accuracy of Embedding-Based Retrieval]]>https://parlant.io/blog/increasing-accuracy-of-embedding-based-retrieval2025-07-08T00:00:00.000ZDor Zoharhttps://www.linkedin.com/in/dor-zohar-6b803895/<![CDATA[Why We Built Parlant: From Mission-Critical Systems to Conversational AI]]>https://parlant.io/blog/why-we-built-parlant2025-06-29T00:00:00.000ZYam Marcovitzhttps://www.linkedin.com/in/yam-marcovic/<![CDATA[Building Customer-Facing AI Agents in 2025: From the "How" to the "What" and Back Again]]>https://parlant.io/blog/ai-agents-from-how-to-what-and-back-again2025-06-25T00:00:00.000ZYam Marcovitzhttps://www.linkedin.com/in/yam-marcovic/<![CDATA[Solving LLM Hallucinations in Conversational, Customer-Facing Use Cases]]>https://parlant.io/blog/solving-llm-hallucinations-in-conversational-customer-facing-use-cases2025-06-18T00:00:00.000ZYam Marcovitzhttps://www.linkedin.com/in/yam-marcovic/<![CDATA[From ELIZA to Parlant: The Evolution of Conversational AI Systems and Paradigms]]>https://parlant.io/blog/evolution-of-conversational-ai2025-05-01T00:00:00.000ZYam Marcovitzhttps://www.linkedin.com/in/yam-marcovic/<![CDATA[Why Generic RAG Frameworks Can't Catch On]]>https://parlant.io/blog/generic-rag-will-never-catch-on2025-04-24T00:00:00.000ZYam Marcovitzhttps://www.linkedin.com/in/yam-marcovic/<![CDATA[Are Autoregressive LLMs Really Doomed? (A Commentary Upon Yann LeCun's Recent Key Note)]]>https://parlant.io/blog/are-autoregressive-llms-really-doomed2025-02-09T00:00:00.000ZYam Marcovitzhttps://www.linkedin.com/in/yam-marcovic/<![CDATA[What Is Autoregression in LLMs?]]>https://parlant.io/blog/what-is-autoregression2025-02-09T00:00:00.000ZYam Marcovitzhttps://www.linkedin.com/in/yam-marcovic/<![CDATA[Rethinking How We Build Customer-Facing AI Agents]]>https://parlant.io/blog/rethinking-how-we-build-customer-facing-ai-agents2024-12-09T00:00:00.000ZYam Marcovitzhttps://www.linkedin.com/in/yam-marcovic/