Agent Readiness Compare

Microsoft Scope

Audit or test tool operated by Microsoft.

In short

An open-source research-preview platform that evaluates how AI agents use a product on tasks you define, with reusable success criteria and the evidence behind every result. It ranks 9 of 10 on the ten-criterion rubric with 27 of 100, earning most on real agents 12 of 15 and dev fit 7 of 10.

What it is

An open-source research-preview platform that evaluates how AI agents use a product on tasks you define, with reusable success criteria and the evidence behind every result.

Operator: Microsoft. Type: Audit or test tool. Home page: microsoft.github.io/scope.

Ten-criterion rubric

Microsoft Scope: every scored part of the ten-criterion rubric, read 5 November 2026
CriterionPointsWhat the source says
Journey: find0 of 4none
Journey: read0 of 4none
Journey: use4 of 4agents attempt tasks against the product 1
Journey: pay0 of 3none
Checks2 of 15not a check scanner 1
Real agents12 of 15runs coding agents on repeatable tasks; access is requested 1
Open method: catalog0 of 3no site checks
Open method: weights0 of 3none
Open method: scale0 of 2none
Open method: changes0 of 2the repository has no releases and no change log 2
Standards: cites0 of 3no fixed check catalog: criteria are the user's own, and its docs map none to a spec (0 percent) 3
Standards: maintains0 of 2none
Dev fit: api3 of 3generated API reference 1
Dev fit: mcp0 of 3the documentation covers importing MCP servers for the agents under test; Scope does not expose one 3
Dev fit: cli2 of 2its README says the evidence behind every result can be inspected through the Portal or the CLI 1
Dev fit: ci2 of 2benchmarks run inside a development workflow 1
Peers: ranking0 of 6no score or leaderboard 1
Peers: size0 of 4none
Fixes: guidance0 of 4none
Fixes: brief0 of 3none
Fixes: applies0 of 3none
Repeat scans1 of 5versioned agent profiles so a later run starts from a known setup; no data 1
Free: free0 of 3access is requested 1
Free: limits1 of 2MIT-licensed code on GitHub 1

Total 27 of 100, rank 9 of 10. The ranking is on the pick page; the same cells are on the evidence page.

What the sources say

  • Microsoft describes Scope as an open-source agentic experience evaluation platform; the repository description adds that it is a research preview.1
  • It evaluates how AI agents use a product, approach real tasks and respond to feedback; success is defined with reusable criteria, each run can be followed live, and the evidence behind every result is inspected through a Portal or a CLI.1
  • The repository is MIT licensed, was created on 2026-07-28, was last pushed on 2026-11-04 and had 75 stars on 2026-11-05.4 dated 2026-11-05

Pricing and access

Open source under the MIT licence; no price is published (read 2026-11-05). 1

What it does not do

  • Its README describes no public score for sites and no leaderboard.
  • Evaluates what agents do on tasks you define; the README mentions no static checks of files such as llms.txt or robots.txt.

Sources

  1. github.com/microsoft/scope. https://github.com/microsoft/scope, read 2026-11-05.
  2. github.com/microsoft/scope/releases. https://github.com/microsoft/scope/releases, read 2026-11-05.
  3. microsoft.github.io/scope. https://microsoft.github.io/scope/, read 2026-11-05.
  4. api.github.com. https://api.github.com/repos/microsoft/scope, read 2026-11-05.

Last reviewed 2026-11-05