> ## Documentation Index
> Fetch the complete documentation index at: https://agentheya.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Agent Harness

> What your agent does at runtime — how a turn behaves, the limits you can set, and the reliability, memory, orchestration, observability, safety, and evaluation features you get on every channel.

Everything you build in the dashboard runs the same way on every channel — web,
widget, instant messaging, email, A2A, the OpenAI-compatible API, schedules,
and webhooks. This group documents the runtime **behavior** you can rely on and
the **controls** you can set, so you know what to expect when you put real
traffic on your agent.

The builder pages tell you *what to configure*. This group describes *how your
agent behaves* once it's running.

## What you get

| Concern          | What it means for you                                                                                     | Details                                                      |
| ---------------- | --------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------ |
| Execution        | Every reply is a bounded turn with limits you can set on time, tool use, and spend                        | [How a turn executes](/runtime/turn-execution)               |
| Durability       | Conversations, schedules, and queued work survive restarts and updates                                    | [Durability and recovery](/runtime/durability)               |
| State            | Each channel keeps its own conversation; workflow progress and configuration history are tracked          | [State and sessions](/runtime/state-and-sessions)            |
| Tool reliability | Approved actions aren't repeated on a retry, calls are time-bounded, and destructive actions need consent | [Tool execution and reliability](/runtime/tool-execution)    |
| Memory & context | Long-term memory, knowledge retrieval, and automatic handling of long conversations                       | [Memory and context management](/runtime/memory-and-context) |
| Multi-agent      | Connect, delegate to, and hand off to other agents and to humans                                          | [Multi-agent orchestration](/runtime/multi-agent)            |
| Observability    | A cost row per interaction, a health snapshot, and a full record you can drill into                       | [Observability and debugging](/runtime/observability)        |
| Safety           | Your policy controls, sandboxed code, spend limits, and isolation between agents and users                | [Safety and isolation](/runtime/safety)                      |
| Evaluation       | Score answers with a judge, verify goals, run test scenarios, and compare models                          | [Evaluation and quality](/runtime/evaluation)                |

## Consistent across every channel

A WhatsApp message, a scheduled run, and an API request all behave the same
way: your agent assembles its context, uses its tools, produces an answer, and
records the cost. The controls you set — response limits, effort, memory,
safety policy — apply everywhere, so you configure your agent once and it
behaves consistently no matter how a user reaches it.

## Where to start

* Deciding whether to put production traffic on your agent? Read
  [Durability and recovery](/runtime/durability) and
  [Tool execution and reliability](/runtime/tool-execution).
* Debugging a live agent? Start at
  [Observability and debugging](/runtime/observability).
* Building multi-agent systems? Start at
  [Multi-agent orchestration](/runtime/multi-agent) and the
  [peer patterns guide](/peer-patterns).