Question 1

What is Claix?

Accepted Answer

Claix is the controlled data retrieval layer for AI agents: it connects to your relational database and lets each agent retrieve only the tables and columns you allow, guided by your own rules and returned as validated results or typed answers, without moving your data. Available via REST API, MCP, and A2A.

Question 2

How do I get started?

Accepted Answer

In three steps: connect your Postgres database with a read-only role (Claix drafts a Data Map for you to review), define routes and agents with your rules (no YAML or code), then call one endpoint so your agent gets live typed answers inside the perimeter you set.

Question 3

Does Claix copy my data into a vector store?

Accepted Answer

No. Claix does not copy your data or build a vector index over it. Agents query your database where it lives, within the tables and columns you allow. Every query is validated before it runs and traced afterward.

Question 4

Does Claix write to my database?

Accepted Answer

No. Claix connects with a read-only role. Loading documents into structured fields is a separate product, Claix Ingest, which you choose to use.

Question 5

Which databases does Claix support?

Accepted Answer

Postgres today (including Postgres-compatible setups such as Supabase). You connect with a read-only role so agents never get write access through Claix.

Question 6

What are routes and agents?

Accepted Answer

A route is a retrieval capability: the tables and columns allowed plus a short guide with your rules and vocabulary. An agent is the identity that uses them—its own endpoint, business prompt, attached routes, and response mode (raw results or reasoned typed answers). Create a route once and attach it to as many agents as you need.

Question 7

How do I call a Retrieve agent?

Accepted Answer

POST to /retrieve/{agent_name} with a JSON body of questions (each with an optional format such as string, int, boolean, json, or array:string). You get typed answers in order plus a log_id. The same agent is also reachable over MCP (claix.retrieve.ask) and A2A.

Question 8

What answer formats can I request?

Accepted Answer

In reasoned mode you can ask for string, int, boolean, timestamp, timestamptz, date, json, array:string, or array:int. Typed values mean your workflow can branch on booleans, use numbers and lists directly, and skip parsing free text.

Question 9

How does pricing work?

Accepted Answer

With Claix Managed AI the fee is €0.10 per question. With your own LLM key (BYOK) from OpenAI, Google, Anthropic, or xAI, the Claix fee drops to €0.02 per question and you pay your provider’s tokens directly. Results with your own key depend on the model you choose—test in the Sandbox before going live.

Question 10

Is agentic RAG the same as vector RAG?

Accepted Answer

No. They sit on different axes. “Agentic” is about who triggers retrieval (a fixed pipeline vs an agent calling a tool). “Vector” is about how results are matched (embeddings). An agent can call SQL, BM25, or embeddings; a fixed pipeline can use hybrid search. For relational business data, embeddings are often the wrong default.

Question 11

Is SQL retrieval RAG?

Accepted Answer

Yes. RAG means retrieved information feeds the model. It does not require embeddings, and the retrieved information does not have to be text chunks. A SQL query that returns live records for the model is still retrieval.

Question 12

When should I still use a vector database?

Accepted Answer

When you need semantic discovery over a large permanent text collection, heavy repeated search traffic, or a product where search is the product. For exact values, counts, dates, and live rows already in Postgres, query the database where it lives with scoped access instead of copying it into an index.

Question 13

Can I use Claix from LangChain, Cursor, or n8n?

Accepted Answer

Yes. Claix is not an agent framework—it is a retrieval layer you call from the stack you already use. Call REST from any HTTP client (including n8n), expose the agent as an MCP tool for Cursor and compatible clients, or connect over A2A so other agents can delegate data questions.

Question 14

What happens when the answer is not in the allowed tables?

Accepted Answer

The field comes back empty instead of a guess. Queries only run inside the routes you attached to the agent; everything outside that perimeter does not exist for them. Traces show what was asked, which route answered, and what came back.

Question 15

How is Claix different from giving an agent a database MCP server?

Accepted Answer

A generic database MCP connection is quick to wire up, but the access model depends on the server and the role you attach. Claix adds routes, per-agent allowlists, validation before queries run, typed multi-question answers, and a reviewable trace—so you define the boundary once and enforce it on every call.

Claix Retrieve Blog

Keep AI agents on current data: live database retrieval instead of stale copies

Agentic RAG vs vector RAG: two separate choices for database agents