liveBook · Manning

Agent harness

As explained in Designing AI Agents

A software layer around an agent that manages execution, resources, tools, delegation, context, and verification.

An agent harness is the software layer that bounds a language model’s decisions while it directs an agent’s next action. The model chooses a tool, response, or reasoning step; the harness supplies context, memory, permissions, budgets, and stopping conditions. A feedback loop turns results into observations until the task finishes or a stopping rule fires. section 1.1

Unlike a fixed pipeline, an agent loop leaves action selection to the model at runtime. The harness constrains that decision space: it determines what the agent can read or change, where durable state lives, and what evidence counts as completion. Loading a document or spawning a subagent spends context, compute, or action opportunities, so these choices need budgets as well as capabilities. section 1.2

A harness can support planning, delegation, and filesystem-backed context, but it does not choose the collaboration pattern. The application still decides how responsibilities are split and whether work runs as a chain, an independent batch, a review loop, or a hierarchy. A long-running system may also need a runtime with checkpoints and recovery. section 8.8

Delegation with Deep Agents

Deep Agents gives a lead agent a task tool and lets the application define subagents with distinct instructions, descriptions, and tools. The lead model decides when to delegate; each subagent works in a separate context and returns its result. The application remains responsible for the overall collaboration topology. section 8.8

Table 8.7 Implementation layers and where collaboration control lives
Implementation layer (examples)
Where control lives
What it supplies
Topologies
Orchestration runtime (LangGraph)
State graph or phase controller
Durable state, recovery, routing
All four
Agent framework (LangChain, OpenAI Agents SDK)
Current agent or agent loop
Model-tool loop, handoffs, routing
Depends on the application
Agent harness (Deep Agents)
Lead agent, middleware, and subagent tool
Planning, filesystem context, delegation
Hierarchy with embedded chain, parallel, or review
Team or process framework (CrewAI, MetaGPT)
Crew, manager, or process
Defined roles and process
Chain, parallel, hierarchy
Conversational framework (AutoGen/AG2, CAMEL)
Agents and message flow
Interactive exchange
Chain and review
Protocol layer (MCP, A2A)
Outside the task topology
Tool/data access or task/result exchange
None by itself

Compare where control lives in a harness, an orchestration runtime, an agent framework, and other collaboration layers. section 8.8

How Designing AI Agents covers it

How deep it goes
Explains architectural responsibilities and contrasts implementation layers, without a step-by-step harness implementation.
Examples
Uses Deep Agents to illustrate a lead agent delegating to separately configured subagents.
What it assumes
Assumes experience calling an LLM API and trying a simple tool-calling or agent workflow, but not production-agent or framework experience.
What you can do after
Evaluate harness responsibilities and distinguish them from runtime and application-level collaboration choices.
How it connects
Connects model-directed control flow with feedback loops, context windows, delegation, and governance.

Also explained in

Compare how 4 books explain agent harness →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Designing AI Agents. The section links point to the parts of the book it draws on.