---
title: "Semantic and agentic search | SparkFabrik"
url: "https://www.sparkfabrik.com/en/solutions/semantic-agentic-search/"
lang: "en"
type: "solution"
date: "2026-10-03"
lastmod: "2026-10-30"
description: "People type a question, not a keyword. Search answers with the right content and with the part of the page that holds the answer."
image: "https://www.sparkfabrik.com/images/og/soluzioni-ricerca-semantica-agentica-en.webp"
translations:
  it: "https://www.sparkfabrik.com/it/soluzioni/ricerca-semantica-agentica/index.md"
schema: {"@context":"https://schema.org","@id":"https://www.sparkfabrik.com/en/solutions/semantic-agentic-search/#service","@type":"Service","areaServed":[{"@type":"Country","name":"Italy"},{"@type":"Place","name":"Europe"}],"description":"People type a question, not a keyword. Search answers with the right content and with the part of the page that holds the answer.","name":"Semantic and agentic search","provider":{"@id":"https://www.sparkfabrik.com/#organization"},"serviceType":"Ricerca semantica e agentica","url":"https://www.sparkfabrik.com/en/solutions/semantic-agentic-search/"}
---

# Semantic and agentic search that answers questions.

People type a question and find **the passage of the page that holds the answer**, even when their words differ from the site's.

[Tell us about your project](https://www.sparkfabrik.com/en/contact-us/)

- Anchored to the official content
- Questions in natural language
- Open source

## People no longer search by keyword.

Semantic and agentic search is a search engine for websites and portals that understands the meaning of a question and answers with the official content, citing the page. SparkFabrik is an AI Native Engineering company that designs and runs the conversational search of the Luiss website.

Users are used to asking an AI and getting an immediate answer. On a site with thousands of pages, classic search returns a list of results, often wrong when the words do not match.

People who cannot find what they need call, write or leave. And a generic assistant, plugged into the site with no rules, risks answering with what is not there.

**A conversational search that answers on the page, precise because it is anchored to your content.**

Finds by meaning

## The right question, even with the wrong words.

Search understands what the question means: “duplicate card” finds the page about a new badge. **The result is the passage that answers**, with a link to the page.

_Try the search: pick a question and compare the keyword results with the answer by meaning, which brings the passage of the page even when the words differ._

Words and meaning

## Results that say why they are there.

Hybrid search: lexical and semantic, with filters and sorting. **Every result explains why it is there**, across product sheets, documentation and editorial content.

_Try the filters: a search in a technical catalogue; each result explains why it is there, for a matching word or for the meaning of the question, and the filters by content type narrow the list._

You see what is missing

## Unanswered questions tell you what to write.

A dashboard shows the people who manage the content the questions, the results and the unanswered questions, and **shows which content is missing or badly written**.

_Try the dashboard: change the period and assign an unanswered question to the editors; the dashboard keeps track of what is in progress._

## The situations people start from.

Where it helps most: universities, public administrations, technical catalogs, large editorial archives.

### We have thousands of pages and nobody finds anything

Search understands the meaning of the question and finds the right content even when the words used differ from the ones on the page.

### Our users type questions, not keywords

How do I request a duplicate card? Search answers with the passage of the page that holds the answer, and the link to the page.

### The product catalog is huge and technical

Search by meaning across data sheets, documentation and editorial content, with filters and results that explain why they are there.

### We want an assistant on the site, but a safe one

Agents and chatbots use search as a tool: they answer only with the indexed content, with guardrails on.

[The AI Knowledge Platform](https://www.sparkfabrik.com/en/solutions/ai-knowledge-platform/)

## How it works.

A pipeline indexes the content, the search combines words and meaning, and agents know when to use it.

1. **Indexing** (Content): CMS pages and documents turned into structured text and embeddings, updated when they change.
2. **Words and meaning** (Search): A hybrid search on Typesense: lexical and semantic, with filters and sorting.
3. **When to search** (Agents): An agent decides whether and how to use search. Other tools connect through the MCP client we maintain, enabled one by one.
4. **Guardrails and perimeter** (Control): Answers only from the indexed content, moderated conversation, unanswered questions logged.

- Drupal, Search API Typesense, Typesense, LiteLLM, Cohere, MCP, AI Guardrails, Kubernetes

## Perimeter, guardrails, metrics.

A search with AI inside is governed like a production system.

- **It searches only where it should** (Perimeter): It indexes only the content you choose, with the permissions of the person searching.
- **Answers under control** (AI Guardrails): The conversation is moderated and the answers stay inside the indexed content.
- **Visible quality** (Metrics): The dashboard shows which questions go unanswered.

Success Stories

## In production.

The numbers come from the Luiss platform, built with open source modules we maintain.

- [Luiss](https://www.sparkfabrik.com/en/success-stories/luiss/), University · In production: Conversational search over the university's content, with Search API Typesense and RAG.
- [Modules](https://www.sparkfabrik.com/en/services/drupal/drupal-certified-partner/), Open source: Search API Typesense and the Typesense RAG recipe for Drupal are maintained by us on drupal.org.
- [Talk](https://www.sparkfabrik.com/en/events/tomm-drupal-2024/), Event · Replay: AI and Typesense: how to integrate semantic search in Drupal, at Talks On My Machine.

## What is always included.

- **The indexing** (Your content, ready to be searched): CMS pages and documents, updated automatically when they change.
- **The search** (Words and meaning): Configuration of hybrid search, filters, sorting and languages.
- **The interface** (Where people search): The search component on the site or the portal, accessible and consistent with the design system.
- **The metrics** (What works and what does not): The question log and the dashboard for the editorial team.

## Three steps, in this order.

1. **Discovery**: We look at the content, the most frequent questions and the perimeter of the search. You leave with: The list of questions the search must answer and of the content to index.
2. **Build**: Indexing, search and interface, tested on real questions. You leave with: The new search live, with metrics in place.
3. **Evolution**: Agents, a conversational assistant, new sources and new languages. You leave with: A search that grows with the content.

**See it on your own pages.** Bring us the questions you get most often. We show you what the search would find, and where from. [Book a demo](https://www.sparkfabrik.com/en/contact-us/)

## The services inside this solution.

A solution is made of our services, put together for one precise problem.

- **AI Development**: Semantic search, RAG, agents. ([more](https://www.sparkfabrik.com/en/services/ai-development/))
- **MCP servers**: The agents that search, connected to other tools with permissions and tracing. ([more](https://www.sparkfabrik.com/en/services/ai-development/))
- **Drupal**: Search API and the modules we maintain. ([more](https://www.sparkfabrik.com/en/services/drupal/))
- **Strategy & Design**: The search experience and the content architecture. ([more](https://www.sparkfabrik.com/en/services/consultancy-design/design-unit/))
- **Managed Services**: Running it after the release. ([more](https://www.sparkfabrik.com/en/services/cloud-native-services/managed-services/))

**No lock-in to a vendor or a model.** Search runs on open source modules we maintain on drupal.org, such as **Search API Typesense**: no license and no lock-in to a vendor. (Open source: [Search API Typesense on drupal.org](https://www.drupal.org/project/search_api_typesense)) [The method: AI Native Engineering](https://www.sparkfabrik.com/en/ai-native-engineering/)

## Frequently asked questions.

The questions you are already asking.

### How is it different from the search I already have?

Classic search looks for words. This one looks for meaning: it finds the right content even when people use words different from the ones on the page, and answers with the passage that holds the answer.

### Do you use AI on our projects? With what guarantees?

Yes. We build the search with the same method as all our projects: specification before code, tests and review, and a person who approves every release. It runs on open source modules we maintain, such as Search API Typesense, and indexes only the content you choose, with guardrails active on the answers.

### Does it only work with Drupal?

Drupal is the most frequent case, with the modules we maintain. Indexing can also include documents and other sources.

### Can it make answers up?

Search returns existing content. When there is a conversational layer, it answers only with the indexed content and with guardrails on.

### Which languages does it support?

The ones on your site. Semantic search also works across different languages.

### What does it cost?

It depends on the amount of content, sources and languages. The Discovery gives you the order of magnitude.

## The other solutions.

- Solution: [AI Knowledge Platform](https://www.sparkfabrik.com/en/solutions/ai-knowledge-platform/): Company knowledge you can query in natural language, with governance per business unit, an open source stack and costs under control.
- Solution: [Multisite, multilingual CMS](https://www.sparkfabrik.com/en/solutions/content-management-system/): One Drupal for every site, brand and language, with independent editors and AI that helps the people who write.

## Talk to the CEO or the CTO.

Tell us what you publish and what you are asked most often. We will tell you where we would start.

[Tell us about your project](https://www.sparkfabrik.com/en/contact-us/)

- CEO: Stefano Mainardi, [Book 30 minutes](https://calendar.app.google/5N7BejeB8h1HpkYs7)
- CTO: Paolo Mainardi, [Book 30 minutes](https://calendar.app.google/gwe2fWtNU1aL31JCA)

Updated October 30, 2026.

---

*This is the Markdown version of the page, to facilitate reading by AI and crawlers. Visit [https://www.sparkfabrik.com/en/solutions/semantic-agentic-search/](https://www.sparkfabrik.com/en/solutions/semantic-agentic-search/) for the full version with images and interactions.*