http://tango.taileb6975.ts.net/blog Product notes, engineering lessons, and updates from Radish. en-us Thu, 30 Apr 2026 18:56:15 GMT http://tango.taileb6975.ts.net/blog/how-to-automate-lead-research-with-ai http://tango.taileb6975.ts.net/blog/how-to-automate-lead-research-with-ai Why public web Deep Research falls short for sales and investor research - and how Radish closes the gap with grounded, multi-source person and company enrichment. Mon, 27 Apr 2026 00:00:00 GMT http://tango.taileb6975.ts.net/blog/ai-assistant-permissions-how-to-keep-ai-from-going-rogue http://tango.taileb6975.ts.net/blog/ai-assistant-permissions-how-to-keep-ai-from-going-rogue How Radish keeps AI assistants from going rogue — OAuth scopes you control, tool-level Ask/Auto permissions, and a permission layer the agent can't bypass. Thu, 23 Apr 2026 00:00:00 GMT http://tango.taileb6975.ts.net/blog/why-we-built-a-package-manager-for-our-skills http://tango.taileb6975.ts.net/blog/why-we-built-a-package-manager-for-our-skills Radish Skills aren’t static prompts; they’re versioned packages with dependencies, constraints, and install/upgrade flows. Thu, 23 Apr 2026 00:00:00 GMT http://tango.taileb6975.ts.net/blog/the-ai-desktop-trap-will-swing-to-cloud http://tango.taileb6975.ts.net/blog/the-ai-desktop-trap-will-swing-to-cloud Why the trend of running AI agents on local servers is a hurdle for true AI democratization and how cloud-native orchestration wins. Tue, 21 Apr 2026 00:00:00 GMT http://tango.taileb6975.ts.net/blog/benchmarking-radish-vs-claude-cowork-for-lead-gen http://tango.taileb6975.ts.net/blog/benchmarking-radish-vs-claude-cowork-for-lead-gen A head-to-head benchmark on a real lead-gen task: finding verified LinkedIn profiles for regional US airline leadership teams—measuring valid links and cost. Mon, 20 Apr 2026 00:00:00 GMT http://tango.taileb6975.ts.net/blog/chatgpt-vs-radish-language-learning http://tango.taileb6975.ts.net/blog/chatgpt-vs-radish-language-learning ChatGPT can explain a language. Radish can help you actually learn one — with structure, audio, progress tracking, and workflows that continue across the tools you already use. Mon, 13 Apr 2026 00:00:00 GMT http://tango.taileb6975.ts.net/blog/your-ai-assistant-is-only-as-good-as-its-skills http://tango.taileb6975.ts.net/blog/your-ai-assistant-is-only-as-good-as-its-skills Most AI tools stop at answering questions. Radish goes further — with Skills that give your agent the ability to do things across the tools you already use. Mon, 13 Apr 2026 00:00:00 GMT http://tango.taileb6975.ts.net/blog/last-knowledge-system-second-brain-zero-organization http://tango.taileb6975.ts.net/blog/last-knowledge-system-second-brain-zero-organization Stop organizing your notes. Connect your messy files to a Radish agent and let AI handle search and recall — via Telegram, instantly. Thu, 09 Apr 2026 00:00:00 GMT http://tango.taileb6975.ts.net/blog/ai-skills-gap-47000-tools-most-professions-cant-use http://tango.taileb6975.ts.net/blog/ai-skills-gap-47000-tools-most-professions-cant-use AI tooling is booming but only for developers. We measured the democratization gap across 25M workers and found most professions locked out of the composable AI ecosystem. Thu, 02 Apr 2026 00:00:00 GMT http://tango.taileb6975.ts.net/blog/gemini-undocumented-schema-limits http://tango.taileb6975.ts.net/blog/gemini-undocumented-schema-limits Gemini silently fails when your tool schemas get too complex. We found the undocumented limits and how to work around them Wed, 11 Mar 2026 00:00:00 GMT http://tango.taileb6975.ts.net/blog/persistent-malformed-function-call-fix http://tango.taileb6975.ts.net/blog/persistent-malformed-function-call-fix How three layered fixes brought our Gemini MALFORMED_FUNCTION_CALL production error rate down to near zero. Sun, 30 Nov 2025 00:00:00 GMT