Prostir
Sign in
Sign up

Practical guide

Knowledge graph AI agent for product docs and support

A knowledge graph AI agent for product docs helps people find relevant answers across approved documentation. Start with the questions buyers and colleagues ask, organize supported sources and check the citations before relying on the result.

Connect your product docs

Before you read

What gets published

A published agent that answers GraphRAG-style questions across selected sources, uses controlled tools for live checks, names uncertainty when sources are missing, and keeps customer access tied to the same endpoint.

Best for

Product, support, success, and developer-relations companies with scattered docs, release notes, pricing rules, integrations, and customer-facing support questions that need more than raw chunk search.

Where the work happens

Knowledge graph AI agent · GraphRAG · Markdown-LD · knowledge_search

01

When a knowledge graph is worth it

  • A knowledge graph AI agent is useful when the answer depends on relationships across docs: product area, feature, plan rule, integration, owner, exception, and latest release.
  • GraphRAG is the search language people use for that pain, but the product job is simpler: selected sources become searchable graph artifacts the agent can query before it answers.
  • The agent still needs boundaries. If the source material is missing or stale, it should say so instead of guessing.
02

Build the graph-backed support agent

The useful path is source setup, graph build, search tool, safe live checks, access, and testing.

  1. 01
    Select the source set.

    Choose product docs, changelogs, pricing rules, integration guides, examples, and policies the agent is allowed to use.

  2. 02
    Build the knowledge graph.

    Prostir uses ManagedCode.MarkdownLd.Kb to produce Markdown-LD and JSON-LD graph artifacts from supported source documents.

  3. 03
    Enable `knowledge_search`.

    The published agent can search graph nodes, source names, headings, and relationships instead of pasting raw chunks into every prompt.

  4. 04
    Add controlled tools.

    Expose only narrow live checks such as status lookup, plan lookup, integration availability, or support handoff.

  5. 05
    Set access and publish.

    Publish one hosted agent with public, protected, or paid access rules and test real customer questions before sharing it.

03

What goes into the graph

The graph should start with approved sources, not the whole company drive.

  • docdocs/product/*.mdCanonical feature pages, setup steps, limits, and known caveats.
  • docrelease-notes/*.mdWhat changed, when it shipped, and which plans or regions it affects.
  • datagraph.jsonldThe latest JSON-LD graph artifact the creator can inspect or download.
  • codeknowledge_searchThe built-in search tool exposed only when the published agent has searchable knowledge.
  • codesafe live toolsPlan lookup, status lookup, entitlement check, or support handoff with narrow schemas.
04

What the customer asks

A support question spans docs, release notes, plan rules, and a live check.

A support question spans docs, release notes, plan rules, and a live check.

ChatGPT

Can our EU workspace use the new audit export, and does it work with the Salesforce integration?

knowledge_search

Matches: audit-export.md, release-notes/2026-06.md, integrations/salesforce.md, pricing/enterprise-plan.md.

plan_lookup

Workspace is Enterprise, EU region, audit export enabled, Salesforce integration connected.

Yes. Audit export is available on Enterprise workspaces, and the June release notes say EU workspaces are included. Your Salesforce integration is connected, so the next step is to enable export delivery in the audit settings. I do not see a source that covers custom field mapping, so I would hand that part to support.

05

Answer for search and AI overviews

  • A knowledge graph AI agent is not just a chatbot over a folder. It is a hosted agent with selected sources, Markdown-LD/JSON-LD graph artifacts, `knowledge_search`, controlled tools, and access rules.
  • Knowledge graph RAG is useful when questions cross document boundaries, but simple questions should stay simple and source-backed.
  • Prostir keeps the graph build, endpoint, source refresh, tool boundaries, auth, quotas, and paid access attached to the same published agent.

Solutions

Knowledge base chatbot for the questions you answer again

A focused agent that searches approved knowledge, cites supported sources and admits when the answer is missing.

Connect your product docsSee the solution

Related cases

Explore related options

Practical guide

AI agent builder for ChatGPT and Claude

Practical guide

Remote MCP server for ChatGPT, Claude, and Cursor

Practical guide

What is an AI-native agency?

Practical guide

Reusable AI skills: build a method for your agents

Practical guide

Knowledge base AI agent with paid access

Practical guide

MCP vs CLI: what is the difference?

Practical guide

How to make your product available in ChatGPT and Claude

Solutions

Give your knowledge a useful answer.

Would it be a bad idea to try the next recurring question against your own sources? Build a knowledge agent, check its citations and refine what it should answer. Start your 7-day Creator trial, no card needed.

Connect your product docsSee the solution

Image preview