Big picture
A layered map from model access up to tools, agents, workflows, interfaces, and safety controls.
Example first
A terminal agent sits near the top because it is the thing you interact with. But it also reaches downward: it calls tools, connects to protocol adapters, manages context, and relies on a model access path. Goose is one example of this shape.
The stack is less like a set of boxes and more like a cutaway view. It shows what a product is built out of.
Bottom to top
Plain English: The safety rails and dashboard.
Technical view: Approvals, audit logs, traces, evals, policy, rate limits, cost controls, secret scanning, reproducibility, and deployment gates.
Examples: promptfoo, Braintrust, LangSmith, Helicone, OpenTelemetry, CI checks.
Plain English: The project manager that splits and schedules work.
Technical view: Workflow engines, graph execution, background jobs, subagent delegation, retries, queues, routing, and long-running task state.
Examples: LangGraph, AutoGen, CrewAI, Temporal, Airflow, GitHub Actions, n8n.
Plain English: The place where you talk to the AI and approve its work.
Technical view: Hosts own the conversation, context window policy, permission prompts, tool result display, and user interaction model.
Examples: Copilot CLI, Claude Code, Cursor, VS Code, Cline, Continue, chat apps, web dashboards.
Plain English: The loop that keeps asking, "what should I do next?"
Technical view: Planning, tool selection, state management, memory retrieval, error handling, reflection, retry logic, and stop conditions.
Examples: ReAct loops, LangChain, OpenAI Agents SDK, Semantic Kernel, Pydantic AI, custom coding agents.
Framework note: LangChain mainly fits here; LangGraph pushes higher into orchestration.
Plain English: Reusable recipes and add-ons.
Technical view: Skills, plugins, prompt packs, hooks, slash commands, project instruction files, templates, and reusable workflows.
Examples: skills, project instruction files, pre-tool hooks, code review prompt packs.
Plain English: Standard plugs that connect the AI to tools and information.
Technical view: Schemas and transports for discovering context, invoking tools, streaming results, authenticating, and adapting existing systems.
Examples: MCP, function calling, OpenAPI, LSP, DAP, browser automation protocols.
Plain English: The actual tools that do work.
Technical view: CLIs, APIs, shell commands, scripts, test runners, package managers, databases, browsers, and cloud services.
Examples: git, rg, jq, curl, gh, npm, pytest, SQL clients, REST APIs.
Plain English: The engine, the fuel, and the workshop floor.
Technical view: Hosted subscriptions, provider APIs, aggregate routers, local endpoints, model artifacts, embedding models, filesystems, databases, vector stores, containers, sandboxes, and credentials.
Examples: provider APIs, local hosting runtimes, quantized model files, Docker, E2B, local files.
Start here: model access paths.
Walkthrough
It has a CLI. A command such as bd is an executable capability, so it touches layer 02.
It stores durable state. The task graph acts like memory for agents and humans, so it also belongs near the foundation.
It shapes workflow. Ready-task detection, claiming, and dependencies push it upward into coordination.