A project-scoped assistant grounded in your own data

Assistant & RAG

Flicker's assistant answers from your content, not the model's guesswork. Connect a data source, Flicker ingests and embeds it into a private knowledge base, and every answer is retrieved from what you actually gave it.

Connect a source

A source is a set of files the assistant can read. Three kinds ship today: a bucket (a storage bucket your org already owns), a repo (a connected git repository), and tickets (a Flicker project's tickets and their documents). More kinds plug in behind the same interface. Turn on auto_embed and new content is chunked and embedded as it lands — no manual re-index.

Hybrid retrieval

The assistant is agentic: it decomposes a question into sub-questions, runs a hybrid search for each — pgvector semantic similarity and Postgres full-text — and merges the results with Reciprocal Rank Fusion. Hybrid beats either alone: vectors catch meaning, full-text catches exact terms and rare tokens. A failed sub-query degrades to fewer results rather than dropping the answer.

Ask

Open Assistant under your project and ask in plain language; the answer is grounded in the passages it retrieved, and the model behind it is pluggable. A retrieval playground lets you inspect exactly what was retrieved for a query and tune the pipeline before you ship it.