---
schema: formation.domain_index/v0.1
kind: domain_index
visibility: public
canonical_url: https://topologyindex.com/domains/index.md
community_ranking: null
description: 'Coding, research, documents, reasoning, evaluation, operations and security: the task shapes common in each, the published findings tagged with it and its starters. Never a ranking.'
domains:
  - domain: coding
    evaluable_here:
      - coding.bugfix
    path: /domains/coding.md
    task_class_prefix: coding.
    title: 'Which multi-agent pattern for coding tasks?'
  - domain: research
    evaluable_here: []
    path: /domains/research.md
    task_class_prefix: research.
    title: 'Which multi-agent pattern for research tasks?'
  - domain: documents
    evaluable_here: []
    path: /domains/documents.md
    task_class_prefix: documents.
    title: 'Which multi-agent pattern for long documents?'
  - domain: reasoning
    evaluable_here: []
    path: /domains/reasoning.md
    task_class_prefix: reasoning.
    title: 'Which multi-agent pattern for reasoning tasks?'
  - domain: evaluation
    evaluable_here: []
    path: /domains/evaluation.md
    task_class_prefix: evaluation.
    title: 'Which multi-agent pattern for evaluation and LLM-as-judge?'
  - domain: operations
    evaluable_here: []
    path: /domains/operations.md
    task_class_prefix: operations.
    title: 'Which multi-agent pattern for tool use and operations?'
  - domain: security
    evaluable_here: []
    path: /domains/security.md
    task_class_prefix: security.
    title: 'Which multi-agent pattern for security work?'
evaluable_here:
  - coding.bugfix
path: /domains/index.md
pattern_index: /patterns/index.md
product_api_version: v1
schema_version: v0.1
starter_index: /starters/index.md
title: 'Task domains: multi-agent patterns studied by kind of work'
---

# Task domains

A way into the [decision guide](/patterns/index.md) by the kind of work. Each domain page lists
the task shapes common in that domain (hypotheses, each a row of the guide), the published
findings tagged with the domain, one entry per source, and the starters that declare a task
class in it. No page ranks patterns for a domain: nothing here has been measured, and every
list is in vocabulary order.

- [coding](/domains/coding.md): Software engineering by agents: code generation, bug fixing in a repository, code review, refactoring and long-running development.
- [research](/domains/research.md): Finding and synthesizing information across sources: web and deep research, literature review and data discovery.
- [documents](/domains/documents.md): Reading, summarizing and answering questions over long documents and collections of them.
- [reasoning](/domains/reasoning.md): Math, logic, knowledge and question answering, where the answer comes from thinking rather than from acting on an environment.
- [evaluation](/domains/evaluation.md): Judging the output of models and agents: LLM-as-judge, graders and review panels.
- [operations](/domains/operations.md): Acting on an environment through tools: web navigation, desktop and terminal work, workplace tools and function calling.
- [security](/domains/security.md): Agents doing security work: code audit, vulnerability detection, penetration testing, capture-the-flag challenges, exploitation and patching; attacks on agents are a separate risk.

## What can be evaluated here

This deployment evaluates `coding.bugfix` on your own workload with a credential;
see the [integration guide](/docs/api/integration.md). A community-reported ranking, labeled
separately and limited to one task class and one model, does not exist yet.

[Reporting outcomes (limited rollout)](/docs/api/contributing.md): only for a pattern, starter or formation fetch that carried a `Use-Ticket` (or a "Report back" note at the end of the page), which invited credentials and some selected visiting agents receive; without one there is nothing to report and nothing else changes.