Rowboat – AI coworker that turns your work into a knowledge graph

Automatically captures work activities (emails, messages, documents, code commits) and transforms them into a structured knowledge graph representation using LLM-based entity and relationship extraction. The system parses unstructured work data, identifies key entities (people, projects, tasks, decisions), and maps relationships between them, building a queryable graph structure that persists across sessions and grows with continuous work activity.

Enables semantic search and retrieval over the constructed knowledge graph to surface relevant past work, decisions, and context based on natural language queries or current task context. Uses graph traversal and embedding-based similarity to find related entities, past decisions, and similar problems solved previously, returning ranked results with relationship paths that explain why results are relevant.

Generates concise summaries of relevant work context when switching between tasks or projects, using the knowledge graph to identify key entities, recent decisions, and involved stakeholders. The system traverses the graph to find all connected work items, extracts key facts and decisions, and synthesizes them into a brief summary that restores context without requiring manual review of past communications.

Integrates work data from multiple sources (email, Slack, GitHub, Jira, calendar, etc.) into a unified representation for knowledge graph construction. The system normalizes data from different schemas and formats, deduplicates entities across sources (e.g., recognizing the same person in email and Slack), and maps cross-source relationships (e.g., linking a GitHub commit to a Slack discussion).

Uses the knowledge graph and work history to suggest task decomposition, identify dependencies, and propose next steps based on similar past work and current project state. The system analyzes the graph to find related tasks, past decisions that constrain current work, and stakeholders who should be involved, then uses an LLM to synthesize a plan with estimated effort and risk factors.

Continuously monitors incoming work data and detects anomalies or significant changes in work patterns using the knowledge graph as a baseline. The system identifies unusual activity (e.g., new stakeholders appearing in a project, sudden change in communication patterns, decisions that contradict past precedent) and alerts relevant parties, helping catch miscommunication or missed context early.

Provides interactive visualization of the work knowledge graph, allowing users to explore entities, relationships, and work patterns visually. The system renders the graph with customizable filtering (by project, person, time range, entity type) and supports multiple visualization modes (network graph, timeline, hierarchical tree) to help users understand work structure and find connections they might miss in text-based search.