AEL Docs
Follow updates
Menu
Follow updates
Browse the documentation

Preview documentation for AEL Beta 0.0.1 — launching soon

Agents

In AEL, the Agent Engineering Language, an agent will be ordinary typed code: a workflow of nodes and edges, each in its own named file, with its system prompt, model binding, tools, limits and checks written beside it. This guide describes the agents that Beta 0.0.1 will let you build, one subject per page.

Status

Planned for AEL Beta 0.0.1. AEL is not available yet.

Every example in the guide is preview syntax. The language is planned, and its spelling may change before launch.

The pages

  • Agents, nodes and edges

    The three building blocks, definitions and instances, runs, and model-driven or deterministic decisions.

  • System prompts

    Prompt sources, ordered fallback, running on input alone and the prompt each run keeps.

  • Models and providers

    Model bindings, the built-in client for OpenAI-compatible APIs, local and cloud models, and model policies.

  • Tools and MCP

    Typed tools and their permissions, the tool loop, MCP tools, services and your own connectors.

  • Typed inputs and outputs

    Inputs, input builders, output checks, raw or typed results, several inputs, media and streams.

  • Workflows

    Starting points and completion, edge modes, delivery, callbacks, fan-out, feedback and triggers.

  • Budgets, retries and validation

    The shared budget, attempts and repairs, which failures are retried, output checks and resource limits.

  • Teams of agents

    Supervisors, pipelines, routers, peers, quorum, handoff, typed delegation and remote agents over A2A.

  • Durable runs and approval

    The life of a run, pausing and resuming, human approval, restarts and side effects.

  • Memory and state

    Run state and long-term memory, scopes, retention and deletion, shared memory and retrieval (RAG).

  • Evaluations and prompt releases

    Evaluation suites, recorded-model regression tests, drift checks, promotion and rollback.

  • Reporting, logs and replay

    Time and token reports, structured logs, and recording and replaying runs.

What agents will give you

  • Agents as code. Agents, nodes (business steps) and edges (typed connections) will each be a building block in its own named file, so a workflow's structure will read at a glance.
  • Prompts as business policy. You will write an agent's business policy as a system prompt, inline, from a file, from the environment or from configuration, or run it on its input alone.
  • Models where you choose. A built-in client for OpenAI-compatible APIs will come with the language, for local model servers, major cloud providers and inference endpoints you run yourself.
  • Model policies. One call, a bounded loop, routing, ordered fallback, parallel fan-out or an independent verifier model.
  • Mixed decisions. One workflow will mix model-driven and deterministic decisions, and route sensor readings or events without paying for a model call.
  • Typed inputs and outputs. Your own input builders and output checks, a choice of raw or typed results, and text, structured data, images, audio, files and video frames.
  • Tools and MCP. A built-in MCP client will discover and call MCP tools, and an optional package will expose your agents as MCP tools.
  • One shared budget. Retries, output repair, timeouts and cancellation will draw on one budget, and token, time, CPU, memory and concurrency budgets will apply across every child agent.
  • Teams of agents. Supervisor, pipeline, fan-out and join, router, peers, quorum, handoff and typed delegation, and delegation to remote agents over A2A.
  • Durable runs. Runs will pause, resume, wait for human approval, survive restarts and reconcile side effects safely.
  • Scoped memory. State and long-term memory will be scoped per tenant, agent, session or subject, with retention and deletion rules.
  • Releasable prompts. Evaluations, recorded-model regression tests, drift checks, and promotion with one-step rollback, while active runs stay pinned to their version.
  • Reports and logs. Time and token usage will be reported by default, structured logs will go where you choose, and you will be able to record runs and replay them.
  • A first agent: a console agent from start to finish.
  • Language guide: files and roles, configuration, hooks, concurrency and capabilities.
  • Packages: the HTTP and MCP server packages, and model provider packages.
  • Agent inputs and outputs: the JSON Schemas of agent components, prompts, model requests and runs.