Skip to content

How AutoGen’s scores are calculated

The full audit trail, recomputed from the verdict data at build time through the same code that produced the leaderboard: verdict × quality × story weight per cell, cells sum to dimension scores, dimensions blend into the PA Score. Every number on the product page is reproducible from this page alone; for why the formula looks like this, see the methodology.

verdict factors: full ×1.0 · partial ×0.6 · disputed ×0.3 · none ×0.0 · n/a excluded from both sides · cell points = weight × quality × factor · cell max = weight × 10

PA Score26/100

Agent-ready 30.6 × 0.30 = 9.18

API quality 8.6 × 0.20 = 1.72

Openness 45.6 × 0.20 = 9.12

Built-in AI 33.3 × 0.15 = 4.99

Automation 9.0 × 0.15 = 1.35

(9.18 + 1.72 + 9.12 + 4.99 + 1.35) ÷ (0.30 + 0.20 + 0.20 + 0.15 + 0.15) = 26.37 ÷ 1.00 = 26.4

Scores are stored to 1 decimal; the product page’s pills round to whole numbers for display. Each dimension below shows the stories, verdicts, and cited evidence behind its number.

Agent-ready30.6/100×0.30 of the PA blend

Outside-in: can YOUR agent reach and drive this product — API, MCP, CLI, headless runs, agent docs.

Point an agent at llms.txt or agent-oriented docsweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [probe] https://microsoft.github.io/llms.txtPROBE llms.txt: HTTP 404 at https://microsoft.github.io/llms.txt
  • [probe] https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/index.html.mdPROBE docs-md: HTTP 404 at https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/index.html.md
  • [probe] https://microsoft.github.io/openapi.jsonPROBE openapi: all candidate paths 404 (https://microsoft.github.io/openapi.json, https://microsoft.github.io/swagger.json, https://microsoft.github.io/api/openapi.json, https://microsoft.github.io/.well-known/openapi.json)

Run the product headlessly / in CI for automationweight 2

2 (weight) × 6 (quality) × 0.6 (partial) = 7.2 of 20 max

  • [github] https://github.com/microsoft/autogenpip install -U "autogen-agentchat" "autogen-ext[openai]"
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/installation.htmlpip install -U "autogen-agentchat"
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/autogenstudio-user-guide/index.htmlExport and run teams in python code
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/autogenstudio-user-guide/index.htmlExport and run teams in python code * Setup and test endpoints based on a team configuration * Run teams in a docker container
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/index.htmlSerialize Components: Serialize and deserialize components

Plug MCP servers into this product so it can use their toolsweight 3

3 (weight) × 6 (quality) × 0.6 (partial) = 10.8 of 30 max

  • [github] https://github.com/microsoft/autogenCreate a web browsing assistant agent that uses the Playwright MCP server.

Connect an agent via an official MCP serverweight 3

n/a — not applicable to this product: excluded from numerator and denominator

  • [github] https://github.com/microsoft/autogenCreate a web browsing assistant agent that uses the Playwright MCP server.

Use an official CLIweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Drive the product through a documented public APIweight 3

3 (weight) × 7 (quality) × 1.0 (full) = 21.0 of 30 max

  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/tutorial/agents.htmlAssistantAgent is a built-in agent that uses a language model and has the ability to use tools.
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/tutorial/teams.htmlRoundRobinGroupChat is a simple yet effective team configuration where all agents share the same context and take turns responding in a round-robin fashion.
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/tutorial/human-in-the-loop.htmlThe UserProxyAgent is a special built-in agent that acts as a proxy for a user to provide feedback to the team.
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/index.htmlCreate your own agents with custom behaviors
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/index.htmlMulti-agent coordination through a shared context and centralized, customizable selector
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/tutorial/teams.htmlSelectorGroupChat: A team that selects the next speaker using a ChatCompletion model after each message.
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/tutorial/teams.htmlSwarm: A team that uses HandoffMessage to signal transitions between agents.
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/index.htmlGraphFlow: Multi-agent workflows through a directed graph of agents.
  • [github] https://github.com/microsoft/autogenpip install -U "autogen-agentchat" "autogen-ext[openai]"
  • [github] https://github.com/microsoft/autogenYou can use `AgentTool` to create a basic multi-agent orchestration setup.
  • [probe] https://microsoft.github.io/openapi.jsonPROBE openapi: all candidate paths 404 (https://microsoft.github.io/openapi.json, https://microsoft.github.io/swagger.json, https://microsoft.github.io/api/openapi.json, https://microsoft.github.io/.well-known/openapi.json)

Issue scoped/least-privilege API credentials for an agentweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Build against official SDKsweight 2

2 (weight) × 8 (quality) × 1.0 (full) = 16.0 of 20 max

  • [github] https://github.com/microsoft/autogenpip install -U "autogen-agentchat" "autogen-ext[openai]"
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/installation.htmlpip install -U "autogen-agentchat"
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/tutorial/agents.htmlAssistantAgent is a built-in agent that uses a language model and has the ability to use tools.
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/tutorial/human-in-the-loop.htmlThe UserProxyAgent is a special built-in agent that acts as a proxy for a user to provide feedback to the team.
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/index.htmlCreate your own agents with custom behaviors
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/index.htmlHow to migrate from AutoGen 0.2.x to 0.4.x.
  • [probe] https://microsoft.github.io/openapi.jsonPROBE openapi: all candidate paths 404 (https://microsoft.github.io/openapi.json, https://microsoft.github.io/swagger.json, https://microsoft.github.io/api/openapi.json, https://microsoft.github.io/.well-known/openapi.json)

Subscribe to events via webhooksweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Agent-ready = 55.0 ÷ 180 × 100 = 30.6

API quality8.6/100×0.20 of the PA blend

The programmable surface once an agent is there — machine-readable spec, interactive docs, sandbox, versioning discipline.

Explore an interactive API reference with runnable examplesweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [probe] https://microsoft.github.io/llms.txtPROBE llms.txt: HTTP 404 at https://microsoft.github.io/llms.txt
  • [probe] https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/index.html.mdPROBE docs-md: HTTP 404 at https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/index.html.md
  • [probe] https://microsoft.github.io/openapi.jsonPROBE openapi: all candidate paths 404 (https://microsoft.github.io/openapi.json, https://microsoft.github.io/swagger.json, https://microsoft.github.io/api/openapi.json, https://microsoft.github.io/.well-known/openapi.json)
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/index.htmlHow to migrate from AutoGen 0.2.x to 0.4.x.
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/index.htmlMigration Guide: How to migrate from AutoGen 0.2.x to 0.4.x.

Download a machine-readable API spec (OpenAPI or equivalent)weight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [probe] https://microsoft.github.io/llms.txtPROBE llms.txt: HTTP 404 at https://microsoft.github.io/llms.txt
  • [probe] https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/index.html.mdPROBE docs-md: HTTP 404 at https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/index.html.md
  • [probe] https://microsoft.github.io/openapi.jsonPROBE openapi: all candidate paths 404 (https://microsoft.github.io/openapi.json, https://microsoft.github.io/swagger.json, https://microsoft.github.io/api/openapi.json, https://microsoft.github.io/.well-known/openapi.json)

Test against a sandbox environment without touching production dataweight 1

1 (weight) × 4 (quality) × 0.6 (partial) = 2.4 of 10 max

  • [community] https://news.ycombinator.com/item?id=37926741i noticed autogen creates a new docker container each time code is executed by agents (default behaviour, can be turned off), so it's safe as you think docker is safe
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/autogenstudio-user-guide/index.htmlInteractive environment for testing and running agent teams
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/autogenstudio-user-guide/index.htmlExport and run teams in python code * Setup and test endpoints based on a team configuration * Run teams in a docker container

Rely on versioned APIs with a documented deprecation policyweight 2

2 (weight) × 3 (quality) × 0.6 (partial) = 3.6 of 20 max

  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/index.htmlHow to migrate from AutoGen 0.2.x to 0.4.x.
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/index.htmlMigration Guide: How to migrate from AutoGen 0.2.x to 0.4.x.

API quality = 6.0 ÷ 70 × 100 = 8.6

Openness45.6/100×0.20 of the PA blend

Can you leave, inspect, or self-host — data export, open source, portability.

Do everything through the API that I can do in the UIweight 2

2 (weight) × 6 (quality) × 0.6 (partial) = 7.2 of 20 max

  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/autogenstudio-user-guide/index.htmlA visual interface for creating agent teams through declarative specification (JSON) or drag-and-drop
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/autogenstudio-user-guide/index.htmlExport and run teams in python code
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/autogenstudio-user-guide/index.htmlExport and run teams in python code * Setup and test endpoints based on a team configuration * Run teams in a docker container
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/autogenstudio-user-guide/index.htmlCentral hub for discovering and importing community-created components

Export all of my data in open formats and leaveweight 3

3 (weight) × 4 (quality) × 0.6 (partial) = 7.2 of 30 max

  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/autogenstudio-user-guide/index.htmlA visual interface for creating agent teams through declarative specification (JSON) or drag-and-drop
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/autogenstudio-user-guide/index.htmlExport and run teams in python code
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/autogenstudio-user-guide/index.htmlExport and run teams in python code * Setup and test endpoints based on a team configuration * Run teams in a docker container
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/index.htmlSerialize Components: Serialize and deserialize components

Read the product's source under an open licenseweight 2

2 (weight) × 6 (quality) × 0.6 (partial) = 7.2 of 20 max

  • [github] https://github.com/microsoft/autogenpip install -U "autogen-agentchat" "autogen-ext[openai]"
  • [github] https://github.com/microsoft/autogenCreate a web browsing assistant agent that uses the Playwright MCP server.
  • [github] https://github.com/microsoft/autogenYou can use `AgentTool` to create a basic multi-agent orchestration setup.

Self-host the core productweight 3

3 (weight) × 8 (quality) × 1.0 (full) = 24.0 of 30 max

  • [github] https://github.com/microsoft/autogenpip install -U "autogen-agentchat" "autogen-ext[openai]"
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/installation.htmlpip install -U "autogen-agentchat"
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/autogenstudio-user-guide/index.htmlExport and run teams in python code * Setup and test endpoints based on a team configuration * Run teams in a docker container
  • [community] https://news.ycombinator.com/item?id=37926741i noticed autogen creates a new docker container each time code is executed by agents (default behaviour, can be turned off), so it's safe as you think docker is safe

Openness = 45.6 ÷ 100 × 100 = 45.6

Built-in AI33.3/100×0.15 of the PA blend

Inside-out: how agentic the product itself is for its users — built-in assistants, autonomous features.

Get AI-generated insights and suggestions from my data inside the productweight 2

2 (weight) × 4 (quality) × 0.6 (partial) = 4.8 of 20 max

  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/tutorial/agents.htmlAssistantAgent is a built-in agent that uses a language model and has the ability to use tools.
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/index.htmlAdd memory capabilities to your agents
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/autogenstudio-user-guide/index.htmlInteractive environment for testing and running agent teams
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/autogenstudio-user-guide/index.htmlA visual interface for creating agent teams through declarative specification (JSON) or drag-and-drop
  • [github] https://github.com/microsoft/autogenYou can use `AgentTool` to create a basic multi-agent orchestration setup.

Set up automations that run autonomously in the backgroundweight 2

2 (weight) × 6 (quality) × 0.6 (partial) = 7.2 of 20 max

  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/tutorial/agents.htmlAssistantAgent is a built-in agent that uses a language model and has the ability to use tools.
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/tutorial/human-in-the-loop.htmlThe UserProxyAgent is a special built-in agent that acts as a proxy for a user to provide feedback to the team.
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/index.htmlMulti-agent coordination through a shared context and centralized, customizable selector
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/tutorial/teams.htmlSelectorGroupChat: A team that selects the next speaker using a ChatCompletion model after each message.
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/tutorial/teams.htmlSwarm: A team that uses HandoffMessage to signal transitions between agents.
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/index.htmlGraphFlow: Multi-agent workflows through a directed graph of agents.
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/autogenstudio-user-guide/index.htmlExport and run teams in python code * Setup and test endpoints based on a team configuration * Run teams in a docker container
  • [community] https://news.ycombinator.com/item?id=37926741i noticed autogen creates a new docker container each time code is executed by agents (default behaviour, can be turned off), so it's safe as you think docker is safe

Delegate tasks to a built-in AI assistant inside the productweight 3

3 (weight) × 6 (quality) × 0.6 (partial) = 10.8 of 30 max

  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/tutorial/agents.htmlAssistantAgent is a built-in agent that uses a language model and has the ability to use tools.
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/tutorial/human-in-the-loop.htmlThe UserProxyAgent is a special built-in agent that acts as a proxy for a user to provide feedback to the team.
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/autogenstudio-user-guide/index.htmlInteractive environment for testing and running agent teams
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/autogenstudio-user-guide/index.htmlA visual interface for creating agent teams through declarative specification (JSON) or drag-and-drop

Operate the product with natural-language commandsweight 2

2 (weight) × 6 (quality) × 0.6 (partial) = 7.2 of 20 max

  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/tutorial/agents.htmlAssistantAgent is a built-in agent that uses a language model and has the ability to use tools.
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/tutorial/human-in-the-loop.htmlThe UserProxyAgent is a special built-in agent that acts as a proxy for a user to provide feedback to the team.
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/autogenstudio-user-guide/index.htmlInteractive environment for testing and running agent teams
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/autogenstudio-user-guide/index.htmlA visual interface for creating agent teams through declarative specification (JSON) or drag-and-drop

Built-in AI = 30.0 ÷ 90 × 100 = 33.3

Automation9.0/100×0.15 of the PA blend

Depth of automation primitives — rules, scheduling, bulk operations, webhooks.

Perform bulk operations across many items at onceweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Define rules that trigger actions automatically on eventsweight 3

3 (weight) × 4 (quality) × 0.6 (partial) = 7.2 of 30 max

  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/tutorial/teams.htmlSwarm: A team that uses HandoffMessage to signal transitions between agents.
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/index.htmlMulti-agent workflows through a directed graph of agents.
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/index.htmlGraphFlow: Multi-agent workflows through a directed graph of agents.
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/tutorial/teams.htmlSelectorGroupChat: A team that selects the next speaker using a ChatCompletion model after each message.

Schedule recurring jobs or workflowsweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Version, review, and roll back my automationsweight 1

1 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 10 max

  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/index.htmlSerialize Components: Serialize and deserialize components
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/autogenstudio-user-guide/index.htmlExport and run teams in python code
  • [claimed-docs] https://microsoft.github.io/autogen/stable/user-guide/autogenstudio-user-guide/index.htmlA visual interface for creating agent teams through declarative specification (JSON) or drag-and-drop

Automation = 7.2 ÷ 80 × 100 = 9.0