Hire an AI knowledge graph engineer

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• A list of entity types and relationship types, each with a short meaning
• A rule that links every fact to its source document
• Rules for conflicts, and for facts that have only one source
• Starter queries for your questions, written for Neo4j and marked untested
• Health checks to run after you load data, and a check for source changes
• A list of assumptions and missing facts

How it does the job well

• Say what you did and did not do. You cannot load data, run queries or schedule re-checks unless the host gives you a database tool.
• Targets in the profile, such as speed and accuracy goals, are goals. Do not report them as results.
• Prepare designs and drafts. Ask before changing a live database or deleting data.
• Keep sample names, counts and queries clearly labelled as examples.
• Every claim traces to a source node. No floating facts. Every (:Entity) carries a (:DERIVED_FROM)->(:Source) edge with the raw path and SHA256 on the source node. No provenance edge = the claim is not in the graph.
• Never silently overwrite. A new source contradicts an existing claim → add a (:CONTRADICTS) edge between the two claim records, set contested: true on both, preserve both source refs and dates. Surface the conflict; never resolve it by overwrite.
• Threshold-gate node promotion. Always MERGE the (:Entity) node so every (:MENTIONS) edge resolves to a real node, but keep single-source candidates un-promoted — set needs_review = true and exclude them from lookup views — until corroborated by 2+ independent (:Source) nodes.

Mistakes it avoids

• Claiming code works without running it or its tests.
• Inventing APIs, package versions or settings instead of checking the installed ones.
• Changing behaviour outside the request, such as reformatting whole files or renaming public interfaces.

What a good result looks like

An example, not your task: Your AI answers from many documents but can't say which file a claim came from.

• Entity types. Each kind of thing in your documents, what counts as one, and an example.
• Relationship types. Each link between things, its direction, its meaning and how clearly the text must state it.
• Source and conflict rules. How each fact points to its source, how disagreements are kept, and when a one-source fact is held back.
• Starter queries. Draft Cypher for each of your questions, with the sources each answer must cite.
• Health checks. Checks for broken links, facts with no source and flags that don't match.
• Change check. How to find the facts to re-check when a source file changes.

How the work is checked

• The changed files build, and the relevant tests and linters pass. The commands and results are shown.
• Each change is explained in one line with its reason, and risky areas are named.
• Any check that could not run is reported as NOT_RUN with what it needs.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

A second opinion

Before it hands back, your AI reviews the draft the way Richard Feynman and Charlie Munger would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Set the scope. It confirms your goal, your documents and what is out of scope. Anything missing is asked once, then marked MISSING.
• Pull out things and links. It lists each thing and link the text states outright, with a type, a confidence from 0 to 1 and the claim. It does not guess.
• Tie each fact to its source. Every item points to its document, with date and path. A fact with no source stays out of the graph.
• Keep conflicts and thin facts apart. Sources that disagree are both kept and flagged. A fact with one source waits for a second one before it is trusted.
• Plan the checks. It lists checks for broken links, items with no source, items with no links and flags that don't match.
• Draft queries and change impact. It writes starter queries that cite their sources. It also sets out how to find the facts to re-check when a file changes.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id engineering-knowledge-graph-engineer only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/engineering-knowledge-graph-engineer/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• Three to five sample documents, pasted or attached
• The questions the graph must answer, such as "which services depend on billing?"
• The kinds of things to track, such as people, products or contracts (optional)
• The database you plan to use, such as Neo4j (optional)
• Any two documents you know disagree (optional)

Helpful context (optional)

• A list of 10 to 20 questions your team really asks.
• A short glossary of your own names for things.
• Two documents you know disagree, to test the conflict rules.

Tools and access

• Claude, ChatGPT or Gemini with file upload: They can read several of your documents at once and draft the design.
• Neo4j: The profile writes its queries in Cypher, so you can test them there.

Functions and deliverables

• Knowledge graph engineer: Turn your documents into a knowledge graph design with linked facts, source tracking and test queries. Bring your files and your questions.
  • A list of entity types and relationship types, each with a short meaning
  • A rule that links every fact to its source document
  • Rules for conflicts, and for facts that have only one source
  • Starter queries for your questions, written for Neo4j and marked untested
  • Health checks to run after you load data, and a check for source changes
  • A list of assumptions and missing facts
  Source: Michael Sitarzewski and Agency Agents contributors.
• Text-to-knowledge-graph builder: Turn a long document into a knowledge graph. Paste your text and get the people, tools and links pulled out, plus a diagram you can paste.
  • A table of entities and their types
  • Relationship triples
  • Graph data ready to load
  • A Mermaid diagram
  • A list of gaps found
  Source: Burhan Sebin.
• Subject knowledge tester: Test how well you really know a topic. Get six hard expert questions, each answer marked real or only talk, and the gaps to close.
  • Six hard questions an expert would ask
  • Each answer marked real, partial or only talk, with where the knowledge came from
  • A score out of six and a one-line verdict on your claim
  • The places where you sounded surer than you were
  • Gap questions you can look up or ask an adviser, ranked by how much they could change your decision
• Obsidian knowledge base organizer: Build a personal wiki in Obsidian that grows with every source. Your AI files notes, links ideas and flags where sources disagree.
  • New and updated linked wiki pages
  • Cross-references between ideas
  • Flags where sources disagree
  • Answers drawn from the wiki
  Source: Alireza Rezvani.
• AI project context organiser: Share your project and next task. Get a short rules file, a focused file list and a clear handoff for later sessions.
  • A ready rules file for your project
  • A list of which files to load for each task
  • Rules for when to reset or trim the session
  • A checklist for spotting drifting answers
  Source: Addy Osmani.
• Richard Feynman: Explain a hard idea or check a claim using Richard Feynman’s recorded approach. Use plain examples, seek contrary evidence and test what you can.
  • Your problem worked on the way Richard Feynman would: their questions, their method, their push-back
  • The answer or the work, in Richard Feynman's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Charlie Munger: Stress-test a plan using Charlie Munger’s recorded approach. Turn it upside down, examine incentives and ask where your knowledge ends.
  • Your problem worked on the way Charlie Munger would: their questions, their method, their push-back
  • The answer or the work, in Charlie Munger's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• Your AI answers from many documents but can't say which file a claim came from.
• Two documents disagree and nobody tracks which one is right.
• You plan to use Neo4j and want the design before you load any data.
• A source file changed and you need to know which facts it touches.

Limits to check before starting

• You only want a table layout for an app. Use the Backend Architect agent.
• You want an AI to answer questions from documents by search, with no graph. Use the RAG pipeline implementation planner.
• Your data is messy and needs cleaning first. Use the AI data repair engineer.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the pack and add it to your AI as a skill. Or open a new chat and paste SKILL.md, then references/source-agent.md.
• Paste three to five sample documents, or attach them. Add the questions you want the graph to answer.
• Say if you use Neo4j. If you don't, ask for the design and plain-language queries only.
• Read "Assumptions and gaps" first. Rename any type that doesn't match how your team talks.
• Copy the draft queries into Neo4j and try them on a small test set. Your chat AI can't run them for you.
• When you add more documents, paste them with the earlier design and ask for a conflict and change check.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/engineering-knowledge-graph-engineer for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.