Generate brand-aligned content using the Senso content engine. Orchestrates brand kit verification, content type selection, prompt management, and generation runs. Use when the user wants to generate content like blog posts, FAQs, comparison pages, or any templated output from their knowledge base.

Build AI-powered room styling apps with Gemini vision + image generation, Unkey rate limiting, Assistant UI chat components, and Next.js App Router

Take a brand new Senso org from empty to fully populated self-improving knowledge system in 10 minutes. Researches the user's company from their website plus external sources, builds out the knowledge base with brand kit, content types, and tracking prompts, generates the first drafts, publishes sample citeables, kicks off GEO monitoring, and files a self-heal report with gap analysis. The first-run experience for any new Senso user. Use when the user runs Senso for the first time or says "set up Senso", "run onboarding", or "populate my knowledge base".

The guided first run for a Senso organization — from a blank organization to LLMs giving a trusted, cited answer about the brand: the website pulled in or the brand written up, the industry set, a first industry question the context layer answers, a checked draft, and a live page. Use when the user says "get me started with senso" (the phrase they are given to paste), "set up Senso", "run onboarding", "build my context layer", or asks for help with Senso without naming any material of their own. Also use when someone part-way through wants to know what to do next, or has finished a round and wants to go round again ("fill another gap"). Not for a user who named material — "save revenue.pdf to Senso" is an ordinary save, handled by the senso-context-layer skill.

Connect a Senso knowledge base to the questions its industry actually gets asked, and close what it cannot answer. Use for setting the organization's industry ("what industry are we", "match me to an industry"), bringing in an industry's questions ("what should I be tracking", "import prompts"), for the gap report — "what can't we answer", "what are my gaps", "what's missing from our knowledge base", or acting on a gap someone already found — and for finding the next one to close ("fill another gap", "what else should we be able to answer"). Also for where the brand stands in its industry — "how do I rank", "am I being cited", "who's beating us", "what do the models say about us" — and for checking whether what they say is accurate. Also the first two stages of the senso-quickstart flow, and every round after it. Not for writing or publishing content — that is generate-and-verify.

Put an approved Senso draft live where AI models can cite it, and follow what happens to it. Use for publishing generated content ("publish this", "make it live", "push it to citeables"), checking or retrying where it went ("did it publish", "retry the failed one"), pulling it back ("unpublish", "take it down"), and for what happened after — citations, which prompts a page is winning, and the provenance audit of a live URL. Also destinations and the call-to-action card. The fourth stage of the senso-quickstart flow. Not for writing or checking content — that is senso-generate-verify.

Search a Senso knowledge base for verified answers, context chunks, or content IDs. Use when the user asks a question that should be grounded in organizational knowledge, says "check Senso", or needs factual answers backed by verified documents.

Upload files or raw text into a Senso knowledge base. Handles file upload via presigned URLs, raw text/markdown creation, folder targeting, and processing status polling. Use when the user wants to add documents, files, or text content to their Senso KB.

Configure a Senso organization's brand kit (voice, tone, persona, writing rules) and content type templates. Use when the user wants to set up or update their brand identity, create content output formats, or prepare for content generation.

Browse, organize, and manage the Senso knowledge base folder tree. Create folders, move and rename nodes, view content details, download files, and check sync status. Use when the user wants to structure, reorganize, or explore their KB.

Manage the Senso content verification and publishing workflow. List items awaiting review, approve or reject content versions, publish to external destinations, save drafts, manage content ownership, and unpublish content. Use when the user wants to review, approve, reject, or publish generated content.

Guide the Senso v2 onboarding experiment: understand the brand, bring in relevant knowledge, compare a recorded external AI answer with approved facts, stage a checked draft with evidence, then publish when requested. Use for Senso quickstart v2, testing the new verification loop, or continuing a v2 onboarding session. Ordinary file saves belong to senso-context-layer.

Hackathon MVP for an entity intelligence cache — query → Redis semantic cache → Ghost (Postgres) entities → Tinyfish Search + mock retrieval → distillation → deltas → synthesis; optional Senso KB publish for cited.md pipeline.

Add, configure, and integrate assistant-ui components in React apps. Use when developers ask to add a chat thread, set up a runtime, integrate with AI SDK, configure tools, or build AI chat interfaces with assistant-ui.

AI-powered bedroom stylist that analyzes room photos, generates designer makeover plans with real shoppable products from Amazon, Target & IKEA — all within a user-specified budget.

Voice-first AI senior care companion. Calls seniors daily to check mood, medications, and needs. Detects falls, loneliness, and service requests (food, medicine, bathing, transportation). Alerts family with recommended local services. Use when building senior care, voice AI, or healthcare check-in applications.

Search your Senso.ai knowledge base hands-free through Edith smart glasses. Triggers on knowledge/document queries.

Ingest documents into your Senso.ai knowledge base through Edith smart glasses. Triggers when user wants to add content to their knowledge base.