Resources for production agents.
Guides, notes, and technical primers from our work building source graphs, agent runtimes, MCP tools, eval systems, and closed-loop intelligence.
Learn
The concept library: source graphs, agent runtimes, MCP tools, workflow evals, governance, and closed-loop knowledge.
Use cases
Practical workflow patterns for data foundations, governed agents, approvals, eval dashboards, and knowledge loops.
Index
An A-Z map of AI terms, capabilities, workflow patterns, and infrastructure language used across the stack.
before
launch.
Workflow Evals
Evaluation suites that mutate prompts, models, retrieval policies, generated code, and node structure before promotion.
Read guideLatest articles
What we are publishing around agent infrastructure, evals, source graphs, and closed-loop operations.
Agent Runtime
The execution layer for event-driven agents: routing, tool calls, approvals, memory, retries, traces, and deployment controls.
Conversation Intelligence
Turning support, Slack, sales, and product conversations into structured signal, knowledge updates, and eval cases.
Source Graph
The owned map of systems, schemas, documents, permissions, events, and business meaning that agents use to act safely.
Highlights
Protocols, control planes, and operating practices behind the systems we launch.
Browse the library
A structured index for deeper concepts from the capability map.
Data substrate
Source Graph
The owned map of systems, schemas, documents, permissions, events, and business meaning that agents use to act safely.
Vector Search
Retrieval pipelines that combine chunking, embeddings, metadata, reranking, permissions, and evaluation.
Data Quality
Contracts, validation, lineage, freshness, and ownership for data that agents can safely use.
Agent runtime
Agent Runtime
The execution layer for event-driven agents: routing, tool calls, approvals, memory, retries, traces, and deployment controls.
MCP Tool Registry
A governed catalog of tools, schemas, permissions, and usage policies that agents can discover and invoke.
Human Approval
Approval gates for workflows where correctness, risk, or accountability require human judgment.
Evaluation
Operations
Model Routing
A gateway strategy for choosing the right model per task based on privacy, cost, latency, quality, and failure mode.
Agent Observability
Trace-level visibility into model calls, retrieval, tools, decisions, approvals, costs, and failures.
Governance
The policy layer for data access, tool permissions, human approvals, audit trails, and deployment boundaries.