Skip to content

How Amplitude’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 Score32/100

Agent-ready 45.3 × 0.30 = 13.59

API quality 25.7 × 0.20 = 5.14

Openness 16.2 × 0.20 = 3.24

Built-in AI 52.9 × 0.15 = 7.93

Automation 10.5 × 0.15 = 1.57

(13.59 + 5.14 + 3.24 + 7.93 + 1.57) ÷ (0.30 + 0.20 + 0.20 + 0.15 + 0.15) = 31.48 ÷ 1.00 = 31.5

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-ready45.3/100×0.30 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) × 9 (quality) × 1.0 (full) = 18.0 of 20 max

  • [probe] https://amplitude.com/llms.txtPROBE llms.txt: HTTP 200 at https://amplitude.com/llms.txt # Amplitude Amplitude is the AI-native digital analytics platform built for AI builders, engineers, data teams, product
  • [probe] https://amplitude.com/docs.mdPROBE docs-md: HTTP 200 at https://amplitude.com/docs.md # Amplitude Documentation Official documentation for Amplitude analytics, SDKs, and APIs Source: https://amplitude.com
  • [probe] https://amplitude.com/openapi.jsonPROBE openapi: HTTP 200 at https://amplitude.com/openapi.json — contains "openapi" key

Run the product headlessly / in CI for automationweight 2

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

  • [claimed-docs] https://amplitude.com/docs/apisSend data directly from your server to the HTTP V2 endpoint.
  • [claimed-docs] https://amplitude.com/docs/feature-experimentManage flags, experiments, and deployments from CI, scripts, or your own tools with the Experiment APIs.
  • [claimed-docs] https://amplitude.com/docs/get-startedRun the Wizard CLI to instrument your codebase and get a first dashboard from one terminal command.
  • [claimed-docs] https://amplitude.com/docs/apisGet data that's displayed on the dashboard graphs in JSON format through the Dashboard REST API.
  • [probe] https://amplitude.com/openapi.jsonPROBE openapi: HTTP 200 at https://amplitude.com/openapi.json — contains "openapi" key

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

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

  • [claimed-docs] https://amplitude.com/mcp-serverBring Amplitude’s behavioral context directly into your AI tools—Claude, Cursor, OpenAI, Lovable, Figma, and more—to get answers where you work.
  • [claimed-docs] https://amplitude.com/mcp-serverBring Amplitude's behavioral context directly into your AI tools—Claude, Cursor, OpenAI, Lovable, Figma, and more—to get answers where you work.
  • [claimed-docs] https://amplitude.com/mcp-serverStart a conversation about your users or product and get expert-level answers in seconds that you can share with your whole org. No SQL, configuring dashboards, or waiting on the data team.
  • [probe] https://amplitude.com/mcp-serverofficial MCP server documented at https://amplitude.com/mcp-server

Connect an agent via an official MCP serverweight 3

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

  • [claimed-docs] https://amplitude.com/mcp-serverBring Amplitude’s behavioral context directly into your AI tools—Claude, Cursor, OpenAI, Lovable, Figma, and more—to get answers where you work.
  • [claimed-docs] https://amplitude.com/mcp-serverBring Amplitude's behavioral context directly into your AI tools—Claude, Cursor, OpenAI, Lovable, Figma, and more—to get answers where you work.
  • [claimed-docs] https://amplitude.com/mcp-serverStart a conversation about your users or product and get expert-level answers in seconds that you can share with your whole org. No SQL, configuring dashboards, or waiting on the data team.
  • [probe] https://amplitude.com/mcp-serverofficial MCP server documented at https://amplitude.com/mcp-server

Use an official CLIweight 2

2 (weight) × 5 (quality) × 0.6 (partial) = 6.0 of 20 max

  • [claimed-docs] https://amplitude.com/docs/get-startedRun the Wizard CLI to instrument your codebase and get a first dashboard from one terminal command.
  • [claimed-docs] https://amplitude.com/docsThe wizard detects your framework, installs the right SDK, adds your API key, and fires a test event.

Drive the product through a documented public APIweight 3

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

  • [claimed-docs] https://amplitude.com/docs/apisSend data directly from your server to the HTTP V2 endpoint.
  • [claimed-docs] https://amplitude.com/docs/apisExport your project's event data.
  • [claimed-docs] https://amplitude.com/docs/feature-experimentManage flags, experiments, and deployments from CI, scripts, or your own tools with the Experiment APIs.
  • [claimed-docs] https://amplitude.com/docs/apis/analytics/behavioral-cohortsList all your cohorts in Amplitude, export a cohort in Amplitude, or upload a cohort.
  • [claimed-docs] https://amplitude.com/docs/apisGet data that's displayed on the dashboard graphs in JSON format through the Dashboard REST API.
  • [claimed-docs] https://amplitude.com/docs/apisCreate, get, update, and delete categories, event types, event properties, and user properties.
  • [probe] https://amplitude.com/openapi.jsonPROBE openapi: HTTP 200 at https://amplitude.com/openapi.json — contains "openapi" key
  • [probe] https://amplitude.com/llms.txtPROBE llms.txt: HTTP 200 at https://amplitude.com/llms.txt # Amplitude Amplitude is the AI-native digital analytics platform built for AI builders, engineers, data teams, product
  • [probe] https://amplitude.com/docs.mdPROBE docs-md: HTTP 200 at https://amplitude.com/docs.md # Amplitude Documentation Official documentation for Amplitude analytics, SDKs, and APIs Source: https://amplitude.com

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

  • [claimed-docs] https://amplitude.com/docs/sdksEvaluate flags locally for low-latency rollout decisions.
  • [claimed-docs] https://amplitude.com/docs/sdksAuto-instrument page views, clicks, and sessions out of the box.
  • [claimed-docs] https://amplitude.com/docs/sdksEvery SDK shares the same identity, event, and consent model, so a user instrumented once is understood everywhere.
  • [claimed-docs] https://amplitude.com/docs/get-startedRun the Wizard CLI to instrument your codebase and get a first dashboard from one terminal command.
  • [claimed-docs] https://amplitude.com/docs/feature-experimentUse Experiment SDKs to flag and test features across web, mobile, and backend.
  • [claimed-docs] https://amplitude.com/docs/sdksUse the same API surface across web, mobile, server, and game engines.
  • [claimed-docs] https://amplitude.com/docs/sdksUnified SDKs provide one integration point for multiple Amplitude products.
  • [claimed-docs] https://amplitude.com/docs/apisSend data directly from your server to the HTTP V2 endpoint.
  • [probe] https://amplitude.com/llms.txtPROBE llms.txt: HTTP 200 at https://amplitude.com/llms.txt # Amplitude Amplitude is the AI-native digital analytics platform built for AI builders, engineers, data teams, product
  • [probe] https://amplitude.com/docs.mdPROBE docs-md: HTTP 200 at https://amplitude.com/docs.md # Amplitude Documentation Official documentation for Amplitude analytics, SDKs, and APIs Source: https://amplitude.com
  • [probe] https://amplitude.com/openapi.jsonPROBE openapi: HTTP 200 at https://amplitude.com/openapi.json — contains "openapi" key

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 = 95.2 ÷ 210 × 100 = 45.3

API quality25.7/100×0.20 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

  • [claimed-docs] https://amplitude.com/docs/apisSend data directly from your server to the HTTP V2 endpoint.
  • [claimed-docs] https://amplitude.com/docs/apisGet data that's displayed on the dashboard graphs in JSON format through the Dashboard REST API.
  • [claimed-docs] https://amplitude.com/docs/apisCreate, get, update, and delete categories, event types, event properties, and user properties.
  • [probe] https://amplitude.com/openapi.jsonPROBE openapi: HTTP 200 at https://amplitude.com/openapi.json — contains "openapi" key

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

2 (weight) × 9 (quality) × 1.0 (full) = 18.0 of 20 max

  • [probe] https://amplitude.com/openapi.jsonPROBE openapi: HTTP 200 at https://amplitude.com/openapi.json — contains "openapi" key
  • [probe] https://amplitude.com/llms.txtPROBE llms.txt: HTTP 200 at https://amplitude.com/llms.txt # Amplitude Amplitude is the AI-native digital analytics platform built for AI builders, engineers, data teams, product
  • [probe] https://amplitude.com/docs.mdPROBE docs-md: HTTP 200 at https://amplitude.com/docs.md # Amplitude Documentation Official documentation for Amplitude analytics, SDKs, and APIs Source: https://amplitude.com
  • [claimed-docs] https://amplitude.com/docs/apisSend data directly from your server to the HTTP V2 endpoint.

Test against a sandbox environment without touching production dataweight 1

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

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

Rely on versioned APIs with a documented deprecation policyweight 2

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

  • [claimed-docs] https://amplitude.com/docs/apisSend data directly from your server to the HTTP V2 endpoint.
  • [claimed-docs] https://amplitude.com/docs/apisGet data that's displayed on the dashboard graphs in JSON format through the Dashboard REST API.
  • [claimed-docs] https://amplitude.com/docs/feature-experimentManage flags, experiments, and deployments from CI, scripts, or your own tools with the Experiment APIs.
  • [probe] https://amplitude.com/openapi.jsonPROBE openapi: HTTP 200 at https://amplitude.com/openapi.json — contains "openapi" key

API quality = 18.0 ÷ 70 × 100 = 25.7

Openness16.2/100×0.20 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://amplitude.com/docs/apisSend data directly from your server to the HTTP V2 endpoint.
  • [claimed-docs] https://amplitude.com/docs/apisExport your project's event data.
  • [claimed-docs] https://amplitude.com/docs/feature-experimentManage flags, experiments, and deployments from CI, scripts, or your own tools with the Experiment APIs.
  • [claimed-docs] https://amplitude.com/docs/apis/analytics/behavioral-cohortsList all your cohorts in Amplitude, export a cohort in Amplitude, or upload a cohort.
  • [claimed-docs] https://amplitude.com/docs/apisGet data that's displayed on the dashboard graphs in JSON format through the Dashboard REST API.
  • [claimed-docs] https://amplitude.com/docs/apisCreate, get, update, and delete categories, event types, event properties, and user properties.
  • [claimed-docs] https://amplitude.com/docs/session-replayWatch real user sessions to understand the why behind your metrics.
  • [claimed-docs] https://amplitude.com/docs/feature-experimentEdit pages with a visual editor and ship the winning variant without a code deploy.
  • [claimed-docs] https://amplitude.com/docsCreate a dashboard
  • [probe] https://amplitude.com/openapi.jsonPROBE openapi: HTTP 200 at https://amplitude.com/openapi.json — contains "openapi" key
  • [probe] https://amplitude.com/mcp-serverofficial MCP server documented at https://amplitude.com/mcp-server

Export all of my data in open formats and leaveweight 3

3 (weight) × 5 (quality) × 0.6 (partial) = 9.0 of 30 max

  • [claimed-docs] https://amplitude.com/docs/apisExport your project's event data.
  • [claimed-docs] https://amplitude.com/docs/apis/analytics/behavioral-cohortsList all your cohorts in Amplitude, export a cohort in Amplitude, or upload a cohort.
  • [claimed-docs] https://amplitude.com/docs/apisGet data that's displayed on the dashboard graphs in JSON format through the Dashboard REST API.

Read the product's source under an open licenseweight 2

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

  • [claimed-docs] https://amplitude.com/integrationsThe Flutter SDK is an open-source UI for developing applications for Android, iOS, Windows, Mac, Linux, Google Fuchsia and the Web.

Self-host the core productweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

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

Openness = 16.2 ÷ 100 × 100 = 16.2

Built-in AI52.9/100×0.15 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) × 8 (quality) × 1.0 (full) = 16.0 of 20 max

  • [claimed-docs] https://amplitude.com/docsAsk questions in plain language — Amplitude AI surfaces answers across all your data.
  • [claimed-docs] https://amplitude.com/mcp-serverStart a conversation about your users or product and get expert-level answers in seconds that you can share with your whole org. No SQL, configuring dashboards, or waiting on the data team.
  • [claimed-docs] https://amplitude.com/mcp-serverBring Amplitude’s behavioral context directly into your AI tools—Claude, Cursor, OpenAI, Lovable, Figma, and more—to get answers where you work.
  • [claimed-docs] https://amplitude.com/mcp-serverBring Amplitude's behavioral context directly into your AI tools—Claude, Cursor, OpenAI, Lovable, Figma, and more—to get answers where you work.
  • [probe] https://amplitude.com/mcp-serverofficial MCP server documented at https://amplitude.com/mcp-server

Set up automations that run autonomously in the backgroundweight 2

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

  • [claimed-docs] https://amplitude.com/docs/feature-experimentRelease behind a flag, ramp to the audience you choose, and turn it off the moment something looks wrong.
  • [claimed-docs] https://amplitude.com/docs/get-startedLaunch in-product guides and surveys to onboard, announce, and learn from users.
  • [claimed-docs] https://amplitude.com/docs/feature-experimentManage flags, experiments, and deployments from CI, scripts, or your own tools with the Experiment APIs.
  • [claimed-docs] https://amplitude.com/docsEmbed an agent grounded in your help content and user behavior. Answer questions, guide flows, and complete tasks for users in the moments that matter.

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://amplitude.com/docsAsk questions in plain language — Amplitude AI surfaces answers across all your data.
  • [claimed-docs] https://amplitude.com/docsEmbed an agent grounded in your help content and user behavior. Answer questions, guide flows, and complete tasks for users in the moments that matter.
  • [claimed-docs] https://amplitude.com/mcp-serverStart a conversation about your users or product and get expert-level answers in seconds that you can share with your whole org. No SQL, configuring dashboards, or waiting on the data team.

Operate the product with natural-language commandsweight 2

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

  • [claimed-docs] https://amplitude.com/docsAsk questions in plain language — Amplitude AI surfaces answers across all your data.
  • [claimed-docs] https://amplitude.com/mcp-serverBring Amplitude’s behavioral context directly into your AI tools—Claude, Cursor, OpenAI, Lovable, Figma, and more—to get answers where you work.
  • [claimed-docs] https://amplitude.com/mcp-serverBring Amplitude's behavioral context directly into your AI tools—Claude, Cursor, OpenAI, Lovable, Figma, and more—to get answers where you work.
  • [claimed-docs] https://amplitude.com/mcp-serverStart a conversation about your users or product and get expert-level answers in seconds that you can share with your whole org. No SQL, configuring dashboards, or waiting on the data team.
  • [probe] https://amplitude.com/mcp-serverofficial MCP server documented at https://amplitude.com/mcp-server

Built-in AI = 47.6 ÷ 90 × 100 = 52.9

Automation10.5/100×0.15 of the PA blend

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

Perform bulk operations across many items at onceweight 2

2 (weight) × 5 (quality) × 0.6 (partial) = 6.0 of 20 max

  • [claimed-docs] https://amplitude.com/docs/apisSend data directly from your server to the HTTP V2 endpoint.
  • [claimed-docs] https://amplitude.com/docs/apisCreate, get, update, and delete categories, event types, event properties, and user properties.
  • [claimed-docs] https://amplitude.com/docs/apis/analytics/behavioral-cohortsList all your cohorts in Amplitude, export a cohort in Amplitude, or upload a cohort.
  • [claimed-docs] https://amplitude.com/docs/feature-experimentManage flags, experiments, and deployments from CI, scripts, or your own tools with the Experiment APIs.
  • [claimed-docs] https://amplitude.com/docs/apisExport your project's event data.

Define rules that trigger actions automatically on eventsweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

  • [claimed-docs] https://amplitude.com/docs/get-startedLaunch in-product guides and surveys to onboard, announce, and learn from users.
  • [claimed-docs] https://amplitude.com/docs/feature-experimentRelease behind a flag, ramp to the audience you choose, and turn it off the moment something looks wrong.
  • [claimed-docs] https://amplitude.com/docs/get-startedRoll out behind a flag and run A/B tests so the data, not a hunch, drives the release.

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

  • [claimed-docs] https://amplitude.com/docs/feature-experimentRelease behind a flag, ramp to the audience you choose, and turn it off the moment something looks wrong.
  • [claimed-docs] https://amplitude.com/docs/feature-experimentManage flags, experiments, and deployments from CI, scripts, or your own tools with the Experiment APIs.
  • [claimed-docs] https://amplitude.com/docs/get-startedRoll out behind a flag and run A/B tests so the data, not a hunch, drives the release.

Automation = 8.4 ÷ 80 × 100 = 10.5