Skip to main content

Overview

The Raily Agentic Layer controls how the intent analyzer navigates and retrieves content from your data sources. Raily’s search isn’t a plain keyword match - it’s an agentic search. Before each query runs, the intent analyzer reads it, figures out what’s actually being asked, and adapts the search to fit. For end users, that means fewer irrelevant results and answers that match the question they actually asked. Every feature is fully configurable per workspace (your dedicated Raily environment for one set of content and users).

Search Behavior

Controls how Raily searches your indexed content when an AI agent issues a query.

Intent understanding

The intent analyzer classifies what you’re trying to do: looking up a known piece, asking a factual question, exploring a topic, comparing things, or following a step-by-step guide. The search adapts to that intent.

Freshness awareness

Recognizes time-sensitive queries (“latest”, “this week”, “yesterday’s update”) and prioritizes recent material. For fast-moving topics, it tightens the time window even when unspecified.

Multi-angle retrieval

For comparisons or multi-faceted questions (“compare A and B”), the intent analyzer runs several searches in parallel, one per angle, and merges the results, giving balanced evidence from each side.

Vocabulary bridging

The intent analyzer knows the vocabulary of your content and quietly rewrites queries into the terms the source actually uses, so casual phrasing still finds the right passages.

Filters

Filters narrow the retrieval scope before search runs. Raily handles them two ways: automatically inferred from the query, or explicitly configured per request.

Inferred from natural language

Phrases like “articles from last week” or “only in the opinion section” are recognized and turned into precise filters automatically. The search is schema-aware, applying the right filter for the right value, including:
  • Dates and time ranges - “this week”, “in 2024”, “before the election”
  • Authors and contributors - by name, with fuzzy matching
  • Sections, categories, or topics - opinion, sports, business
  • Content type - articles, reviews, interviews, recipes
  • Tags, entities, and other metadata your content provides
Available filters adapt to whatever fields exist in your collection.

Explicit configuration

Filters can be set explicitly by the calling application on any metadata field, useful when the UI already knows the scope (a section page, a saved view, or a permission boundary).

Retrieval Granularity

What it is

Each document can be split into smaller, focused passages (chunks), and the search returns the chunks that best match your query.

Why we do it

  • More precise answers. Returning the exact passage that answers your question beats returning the whole piece.
  • Better ranking. Short, focused passages let the search score relevance more accurately.
  • Faster reading. You see the relevant part first, with a link back to the full document.

What a chunk looks like

A chunk is a short, self-contained section of a document (typically a few paragraphs) and carries the source’s metadata (title, author, date, link). Multiple chunks from the same document can appear when more than one passage is relevant.

Chunks or full document?

The intent analyzer decides automatically:
  • Chunks - focused passages, used for factual lookups, topic exploration, and comparisons.
  • Full document - the complete piece, used when order or context matters (known articles, in-depth analysis, recipes and guides).
The intent analyzer can override the default when the query clearly calls for the other format. The defaults are part of each workspace’s configuration.

When nothing closely matches

Some queries have no strong match in your content. Raily uses two bars to decide what to return:
  • a retrieval bar, the minimum match quality for a passage to be considered at all, and
  • a confidence bar, the higher quality a passage needs to count as a strong match.
Passages that clear the retrieval bar but fall short of the confidence bar are weaker, related results. You choose what happens to them per workspace:
  • Show them as suggestions (default). Strong matches come first. Weaker ones follow under a header you set, such as “We didn’t find an exact match, but you might find these useful.” The reader gets something related instead of an empty page.
  • Hide them. Return only strong matches. If nothing clears the confidence bar, the search returns no results. Use this when a plausible-but-wrong answer is worse than none.
  • Show everything together. Return every result above the retrieval bar in score order, with no suggestion header and no split between strong and weak.
You also set the wording of the suggestion header and the per-result label, so the message fits your product’s voice and language.

Rules

Rules shape ranking on top of search results so the order matches what matters to your business.

Field boost

Field boost lets you promote specific topics or genres so they surface higher in results. Typical uses:
  • Promote a topic (e.g. push climate coverage above general news for environmental queries).
  • Promote a genre or content type (e.g. surface investigative pieces for analysis-style queries).
  • De-prioritize categories that are noisy for your audience.
Boosts are configured per workspace.

Tuning

The agentic layer is configuration-driven. Each workspace’s behavior lives in a single reviewable file uploaded into Raily. No code changes, no redeploy. Main things you can tune per workspace:
  • Domain rules - intent categories, chunks vs. full documents, freshness handling, result limits.
  • Filterable fields - which fields users can filter on and how each is interpreted.
  • Chunking - on/off, plus size and shape of chunks.
  • Result grouping - whether chunks are grouped under their parent document.
  • Relevance threshold - the minimum match quality for a result to be returned.
  • No-match behavior - whether weaker results show as suggestions, are hidden, or appear inline with everything else.
  • Reranker - an optional second pass that reorders top results.
  • Time decay - down-weights older results so fresher content ranks higher.

Next Steps

AI Servers

Expose your data to AI agents via authenticated endpoints