The Agentic Search pattern

In one line. Conversational, cited answers over your enterprise documents and data — a Knowledge collection plus an agent that reads it. You’ll be able to. Recognize when Search is the right shape, build one in four steps, and tune it from demo to dependable.

What it is

Agentic Search is level 1 of the solution ladder: the fastest way to turn a pile of documents into an expert your whole team can ask. Users type questions in plain language; the agent answers from — and only from — the content you attached, with citations that click through to the exact source passage.

Choose this shape when the sentence in your head is “let people ask questions over our content.” If the sentence is “automate this process,” you want a Workflow.

The pattern, in four steps

1. KNOWLEDGE collection  →  2. ADD documents  →  3. AGENT  →  4. ATTACH collection
   (no lifecycle;            (upload or            (persona +     (Knowledge tab —
    readable on landing)      connector)            model)         the load-bearing wire)

Create a Knowledge collection — Studio ▸ Data Model ▸ Collections ▸ + Collection, set Category = Knowledge. That category choice is the fork in the road: Knowledge means no lifecycle — documents become readable knowledge the moment they land.
Add documents — upload directly or wire a connector so the collection stays current on its own.
Build the agent — Studio ▸ Agent Builder ▸ Agents ▸ + Agent. The persona sets the contract: answer from the attached documents, cite always, refuse when the answer isn’t there.
Attach the collection on the agent’s Knowledge tab. This attachment is both the power (grounded, cited answers) and the boundary (the agent cannot see anything you didn’t attach).

Step-by-step with every screen: B1 · Policy assistant.

The Knowledge-collection category is a shipped release feature (knowledgeCollections, default on). If an environment has it switched off as a kill-switch you won’t see the Knowledge toggle.

Tuning it from demo to dependable

You want	Do this	Where
Trustworthy answers	Keep citations on; make the persona refuse out-of-scope questions	Agent Persona
No leakage	Attach only the collections this audience may see; build separate agents for separate audiences	Agent Knowledge tab
Structured questions (“how many policies mention X?”)	Add a Knowledge schema so facts also land in a Datasheet; the agent answers those with a SQL tool	Collection schema + Tools
A guided start for users	Configure suggested questions in the chat experience	Chat & search

The distinction worth remembering: reading questions (“what does the policy say?”) are answered from passages; counting questions (“how many contracts expire in Q3?”) are answered by SQL over a Datasheet. A great assistant does both.

Worked builds

Build	What it adds
B1 · Policy assistant	The whole pattern, smallest form — the build from your first 30 minutes, production-grade
B2 · Enterprise data Q&A	Multiple collections, Knowledge schema, structured + narrative answers together

Where to go next

Ready for a process, not just questions: the Workflow pattern.
The controls behind step 3: A3 · Your first agent.
What “Knowledge” does under the hood: D2 · Collection types.