Skip to main content

​
The Pipeline

Dino processes your API in four stages. Each stage is isolated, testable, and deterministic.
1

Discovery

Dino connects to your GraphQL endpoint and runs introspection. It captures the full schema — types, queries, mutations, subscriptions — and enumerates every operation.
  • GraphQL introspection query against your endpoint
  • Schema capture: all types, fields, arguments, directives
  • Operation enumeration: every query and mutation extracted
  • Schema snapshot saved for future diffing
2

Agent Execution

Six autonomous agents run in parallel against every operation. Each agent tests one quality dimension — input handling, response correctness, access control, rate limiting, error formatting, and deprecation tracking.No agent depends on another agent’s output. They run concurrently and produce independent findings. A failure in one agent never blocks or corrupts another.See The 12 Agents for details.
3

Catalog

Findings from all agents are merged into a unified operation catalog. Each operation gets:
  • A health score (0-100) based on findings across all dimensions
  • Metadata: argument types, return types, deprecation status
  • AI-generated descriptions (additive — the catalog exists with or without them)
4

Report

The catalog is rendered into JSON or Markdown. Every report includes the schema snapshot it was generated from, so you can diff between runs and see exactly what changed.

​
Package Architecture

Dino is a monorepo with strict dependency direction. Dependencies flow one way only.

@dino/core

Schema types, shared interfaces, deterministic primitives (Clock, Timer, RandomSource). Zero dependencies on anything above it.

@dino/plugins

The six agent implementations. Each plugin tests one quality dimension. Depends only on core types.

@dino/agents

Agent orchestration — parallel execution, finding aggregation, health score computation.

@dino/cli

The dino command. Config loading, agent wiring, output rendering. Top of the dependency chain.

@dino/reasoning

AI-powered descriptions and explanations. Additive — everything works without it.

@dino/analytics

Event tracking, historical comparisons, regression detection across scan runs.
The strict dependency direction (cli → agents → plugins → core) is enforced at build time. A plugin cannot import from an agent. An agent cannot import from the CLI.

​
What This Means for You

The pipeline is deterministic. Same API state in, same findings out. See Deterministic Engine.
Agents run in parallel. A six-agent scan is one pass with six concurrent workers, not six sequential passes.
JSON output, exit codes, schema snapshots for diffing. Built for pipelines, not dashboards.
Every output is a file you own. JSON reports, Markdown docs, schema snapshots — stored in your repo. If you stop using Dino, your data stays.