Knowledge Graph Overview
A persistent memory layer that stores entities, relationships, and insights across all workflow executions. Your workflows get smarter with every run.
What is the Knowledge Graph?
The Knowledge Graph (KG) is AgentLed's long-term memory system. Unlike traditional automation tools that start from zero every run, AgentLed stores entities (companies, people, deals), their relationships, and AI-generated insights in a graph database.
Every workflow execution can read from and write to the graph. This means a lead scoring workflow can reference outcomes from previous runs, an investor matching workflow can factor in historical prediction accuracy, and a content workflow can learn from engagement patterns.
Architecture
The Knowledge Graph has three layers:
Entity Nodes
Companies, investors, leads, contacts, deals — any business object. Each node has a type, properties, and a unique identity. Nodes are created automatically during workflow execution or imported from Knowledge Lists.
Relationship Edges
Typed connections between entities: SCORED, INVESTED_IN, CONTACTED, MATCHED, FOLLOWED_BY. Edges carry metadata — a SCORED edge includes the score value, timestamp, and the execution that created it. Query edges to traverse the graph.
AI Insights
Insights generated by AI steps: scoring rationale, pattern recognition, calibration data. Insights are linked to the entities and executions that produced them, creating an audit trail of AI reasoning over time.
Built-in KG Tools
Every AI step in a workflow automatically has access to four Knowledge Graph tools. No configuration needed.
| Tool | Description |
|---|---|
| kg_search | Natural language semantic search across all entities and insights |
| kg_traverse | Follow typed relationship edges from a starting entity |
| kg_nodes | List all entities of a given type (e.g., all investors, all leads) |
| kg_write | Persist AI-generated insights and scores back to the graph |
Example: Investor Matching
A VC firm uses AgentLed to match startups against their 2,000+ investor database. Here's how the Knowledge Graph participates:
Run 1Cold start. AI scores 200 investors against a startup profile. Writes SCORED edges with score, rationale, and sector tags. Accuracy: 62%.
Run 5Before scoring, AI reads previous SCORED edges and IC feedback (PROCEED_TO_IC, HOLD edges created by the investment team). Adjusts weighting. Accuracy: 78%.
Run 12AI has 12 rounds of outcomes data. Reads scoring history, calibration benchmarks, and pattern insights. Accuracy: 89%. Zero manual tuning.
Data Sources
Data enters the Knowledge Graph through three paths:
- 1.Knowledge Lists — Upload CSVs or create structured lists in the dashboard. Rows sync to the graph as entities.
- 2.Workflow execution — AI steps write insights, scores, and relationships as they process data.
- 3.API ingestion — Push historical data or external enrichment results via the ingestion endpoints.
Next Steps
- KG API — Query and write to the graph programmatically
- Scoring & Feedback — Self-improving scoring loops
- Business Memory — Workspace-level shared context
- Knowledge Lists — Structured data import and storage