> ## Documentation Index
> Fetch the complete documentation index at: https://open-index.io/llms.txt
> Use this file to discover all available pages before exploring further.

# How to improve context search accuracy

> Why agentic search with navigation beats pre-injected RAG, and how field boosts, hybrid ranking, and schemas make retrieval precise.

An agent is only as good as the context it retrieves. If search returns
plausible-but-wrong records, the agent reasons confidently over the wrong facts — and
no amount of prompting fixes bad retrieval. This page is about making the agent's own
search accurate enough to trust.

## Stop pre-injecting. Let the agent search.

The common pattern is: your system runs RAG or prompt expansion, picks some chunks,
and injects them into the prompt. This has three problems:

* **You guess wrong.** Your retrieval heuristic decides what's relevant *before* the
  agent knows what it needs for this specific step.
* **It poisons.** Injected chunks the agent didn't ask for are exactly the surface for
  [context poisoning](/guide/context-poisoning).
* **It's opaque.** Neither you nor the user can tell what actually drove the answer.

The better model: **give the agent a search tool plus navigational meta-information**,
and make discovery its responsibility. It searches, reads what it got, decides whether
to search again or drill into a relationship — the same way a good analyst works.

<Info>
  This is agentic search over *all* your structured content, not a bolt-on RAG index.
  In [Open Index](/agents/mcp) the agent gets `navigation_guidelines()` (what doc\_types,
  fields, and relationships exist), `search_brain()`, and `get_entity()` — enough to
  navigate a domain it's never seen.
</Info>

## Give the agent a map before the first query

Retrieval accuracy jumps when the agent knows the *shape* of what it's searching.
Before its first query, hand it navigational context:

* Which **doc\_types** exist (`service`, `runbook`, `incident`…) and what each means.
* Which **fields** each carries, and which are searchable.
* Which **relationships** connect them, so it can traverse on purpose.

With that map, the agent scopes searches (`search only incidents`), follows edges
deliberately, and stops guessing. Without it, every query is a blind shot.

## Tune ranking so the right record wins

Precision is also a ranking problem. Two levers matter most:

<AccordionGroup>
  <Accordion title="Per-field boosts" icon="sliders">
    Weight a match in `name` far above a match in a long `description`. A genuine
    multiplier — a hit in a `boost: 6` title outranks a `boost: 1` body hit
    6-to-1 — so the record whose *identity* matches the query surfaces first. →
    [Search configuration](/guides/search-configuration)
  </Accordion>

  <Accordion title="Hybrid keyword + semantic" icon="layer-group">
    Keyword search nails exact names and identifiers; semantic search rescues queries
    that describe a thing in different words than the record uses ("checkout is slow"
    → "latency spike at payment"). Blend them — keyword-dominant by default, with a
    semantic weight you raise when users describe rather than name.
  </Accordion>
</AccordionGroup>

## Design schemas for retrieval

Search accuracy starts at the schema, not the query:

* Mark identity fields (`name`, `owner`, `status`) **syntactic** — exact/prefix
  matching, high boost.
* Mark prose fields (`description`, `summary`) **semantic** — matched by meaning.
* Mark opaque blobs and internal ids **`none`** — stored but never searched, so they
  can't add noise to results.

A field that shouldn't influence ranking simply isn't indexed. That's the cheapest
precision win there is.

## Checklist

* [ ] The agent searches; you don't pre-inject a guessed context blob.
* [ ] It gets navigational meta-info (doc\_types, fields, relationships) up front.
* [ ] Identity fields are boosted; noise fields are `search: none`.
* [ ] Ranking blends keyword + semantic to match both names and descriptions.

<Card title="Next: Conflicts & staleness" icon="code-merge" href="/guide/conflicts-and-staleness">
  Keeping retrieved context correct as it grows.
</Card>