<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>The Product Bet</title><description>Notes on AI product management, voice AI, RAG, and agentic workflows.</description><link>https://blog.tabassumkhanum.in/</link><language>en-us</language><item><title>Strict JSON schemas cut function-calling errors more than prompt tweaks</title><link>https://blog.tabassumkhanum.in/til/2026-08-02-function-calling-schema/</link><guid isPermaLink="true">https://blog.tabassumkhanum.in/til/2026-08-02-function-calling-schema/</guid><description>Tightening a tool&apos;s JSON schema (enums, required fields, no free-form strings) reduced malformed function calls more than any prompt change did.</description><pubDate>Sun, 02 Aug 2026 00:00:00 GMT</pubDate><category>agentic-workflows</category></item><item><title>Cache embeddings by content hash, not document ID</title><link>https://blog.tabassumkhanum.in/til/2026-07-30-embedding-cache/</link><guid isPermaLink="true">https://blog.tabassumkhanum.in/til/2026-07-30-embedding-cache/</guid><description>Keying an embedding cache by document ID instead of content hash silently serves stale vectors after edits.</description><pubDate>Thu, 30 Jul 2026 00:00:00 GMT</pubDate><category>rag</category></item><item><title>Designing Agentic Workflows: From Chatbot to Autonomous Assistant</title><link>https://blog.tabassumkhanum.in/articles/agentic-workflows-explained/</link><guid isPermaLink="true">https://blog.tabassumkhanum.in/articles/agentic-workflows-explained/</guid><description>A practical framework for deciding how much autonomy to hand an AI agent, and where humans still need to stay in the loop.</description><pubDate>Wed, 29 Jul 2026 00:00:00 GMT</pubDate><category>agentic-workflows</category><category>ai-product-management</category></item><item><title>Streaming TTS hides latency if you flush audio early</title><link>https://blog.tabassumkhanum.in/til/2026-07-28-streaming-tts-latency/</link><guid isPermaLink="true">https://blog.tabassumkhanum.in/til/2026-07-28-streaming-tts-latency/</guid><description>Perceived latency in voice agents drops a lot when you start playback on the first audio chunk instead of waiting for the full synthesis.</description><pubDate>Tue, 28 Jul 2026 00:00:00 GMT</pubDate><category>voice-ai</category></item><item><title>RAG Pitfalls Every PM Should Know Before Shipping</title><link>https://blog.tabassumkhanum.in/articles/rag-pitfalls-for-pms/</link><guid isPermaLink="true">https://blog.tabassumkhanum.in/articles/rag-pitfalls-for-pms/</guid><description>Retrieval-augmented generation looks simple in a demo and falls apart in production. Here&apos;s what product managers consistently get wrong before launch.</description><pubDate>Wed, 15 Jul 2026 00:00:00 GMT</pubDate><category>rag</category><category>ai-product-management</category></item></channel></rss>