How Cekura’s scores are calculated

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://docs.cekura.ai/llms.txt“PROBE llms.txt: HTTP 200 at https://docs.cekura.ai/llms.txt # Cekura > Cekura is the testing and observability platform for voice AI agents. Run simulated conversations, evaluate”
• [probe] https://docs.cekura.ai/documentation/introduction.md“PROBE docs-md: HTTP 200 at https://docs.cekura.ai/documentation/introduction.md > ## Documentation Index > Fetch the complete documentation index at: https://docs.cekura.ai/llms.txt > Use this file to”
• [claimed-docs] https://docs.cekura.ai/documentation/introduction“create a comprehensive plan to integrate cekura observability”

Run the product headlessly / in CI for automationweight 2

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

• [claimed-docs] https://docs.cekura.ai/cli-sdk/cli.md“Manage agents, scenarios, runs, and call data from your terminal”
• [claimed-docs] https://docs.cekura.ai/cli-sdk/sdk.md“Programmatic access to Cekura — sync and async clients for application code”
• [claimed-docs] https://docs.cekura.ai/documentation/guides/cronjob.md“Learn how to set up and manage automated cron jobs for your AI agent testing and evaluation workflows.”
• [claimed-docs] https://docs.cekura.ai/documentation/guides/github-actions-ci-cd.md“Learn how to set up GitHub Actions workflows to automatically test your agents with each change”
• [claimed-docs] https://docs.cekura.ai/api-reference/user/create-api-key.md“Create a new API key. When using API key authentication, only project-level API keys can be created.”
• [probe] https://docs.cekura.ai/openapi.json“PROBE openapi: HTTP 200 at https://docs.cekura.ai/openapi.json — contains "openapi" key”
• [probe] https://docs.cekura.ai/cli-sdk/cli“official CLI documented at https://docs.cekura.ai/cli-sdk/cli”

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://docs.cekura.ai/mcp/overview.md“Install Cekura Skills and MCP so your AI assistant can design, run, and improve voice-agent evaluations.”
• [probe] https://docs.cekura.ai/mcp/overview“official MCP server documented at https://docs.cekura.ai/mcp/overview”

Connect an agent via an official MCP serverweight 3

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

• [claimed-docs] https://docs.cekura.ai/mcp/overview.md“Install Cekura Skills and MCP so your AI assistant can design, run, and improve voice-agent evaluations.”
• [probe] https://docs.cekura.ai/mcp/overview“official MCP server documented at https://docs.cekura.ai/mcp/overview”

Use an official CLIweight 2

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

• [claimed-docs] https://docs.cekura.ai/cli-sdk/cli.md“Manage agents, scenarios, runs, and call data from your terminal”
• [probe] https://docs.cekura.ai/cli-sdk/cli“official CLI documented at https://docs.cekura.ai/cli-sdk/cli”

Drive the product through a documented public APIweight 3

3 (weight) × 9 (quality) × 1.0 (full) = 27.0 of 30 max

• [probe] https://docs.cekura.ai/openapi.json“PROBE openapi: HTTP 200 at https://docs.cekura.ai/openapi.json — contains "openapi" key”
• [claimed-docs] https://docs.cekura.ai/cli-sdk/sdk.md“Programmatic access to Cekura — sync and async clients for application code”
• [claimed-docs] https://docs.cekura.ai/api-reference/observability/send-calls.md“Your agent (or its provider's post-call webhook) POSTs here with the transcript, recording URL, and metadata; Cekura stores it as a `CallLog`, schedules metric evaluation”
• [claimed-docs] https://docs.cekura.ai/api-reference/user/create-api-key.md“Create a new API key. When using API key authentication, only project-level API keys can be created.”
• [claimed-docs] https://docs.cekura.ai/cli-sdk/cli.md“Manage agents, scenarios, runs, and call data from your terminal”
• [probe] https://docs.cekura.ai/cli-sdk/cli“official CLI documented at https://docs.cekura.ai/cli-sdk/cli”

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

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

• [claimed-docs] https://docs.cekura.ai/api-reference/user/create-api-key.md“Create a new API key. When using API key authentication, only project-level API keys can be created.”

Build against official SDKsweight 2

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

• [claimed-docs] https://docs.cekura.ai/cli-sdk/cli.md“Manage agents, scenarios, runs, and call data from your terminal”
• [claimed-docs] https://docs.cekura.ai/cli-sdk/sdk.md“Programmatic access to Cekura — sync and async clients for application code”
• [probe] https://docs.cekura.ai/openapi.json“PROBE openapi: HTTP 200 at https://docs.cekura.ai/openapi.json — contains "openapi" key”
• [probe] https://docs.cekura.ai/cli-sdk/cli“official CLI documented at https://docs.cekura.ai/cli-sdk/cli”
• [claimed-docs] https://docs.cekura.ai/api-reference/user/create-api-key.md“Create a new API key. When using API key authentication, only project-level API keys can be created.”

Subscribe to events via webhooksweight 2

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

• [claimed-docs] https://docs.cekura.ai/api-reference/observability/send-calls.md“Your agent (or its provider's post-call webhook) POSTs here with the transcript, recording URL, and metadata; Cekura stores it as a `CallLog`, schedules metric evaluation”

Explore an interactive API reference with runnable examplesweight 2

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

• [probe] https://docs.cekura.ai/openapi.json“PROBE openapi: HTTP 200 at https://docs.cekura.ai/openapi.json — contains "openapi" key”
• [claimed-docs] https://docs.cekura.ai/api-reference/observability/send-calls.md“Your agent (or its provider's post-call webhook) POSTs here with the transcript, recording URL, and metadata; Cekura stores it as a `CallLog`, schedules metric evaluation”
• [claimed-docs] https://docs.cekura.ai/api-reference/user/create-api-key.md“Create a new API key. When using API key authentication, only project-level API keys can be created.”

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://docs.cekura.ai/openapi.json“PROBE openapi: HTTP 200 at https://docs.cekura.ai/openapi.json — contains "openapi" key”
• [claimed-docs] https://docs.cekura.ai/api-reference/observability/send-calls.md“Your agent (or its provider's post-call webhook) POSTs here with the transcript, recording URL, and metadata; Cekura stores it as a `CallLog`, schedules metric evaluation”
• [claimed-docs] https://docs.cekura.ai/api-reference/user/create-api-key.md“Create a new API key. When using API key authentication, only project-level API keys can be created.”

Test against a sandbox environment without touching production dataweight 1

1 (weight) × 5 (quality) × 0.6 (partial) = 3.0 of 10 max

• [claimed-docs] https://docs.cekura.ai/documentation/guides/testing-agents/overview.md“Learn how to quickly create and test voice agents on Cekura without requiring any external API keys or integrations.”
• [claimed-docs] https://www.cekura.ai“Run thousands of synthetic conversations before go-live.”
• [claimed-docs] https://www.cekura.ai“Run the same scenarios across platforms and models. Pick the one that actually performs.”

Rely on versioned APIs with a documented deprecation policyweight 2

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

• [probe] https://docs.cekura.ai/openapi.json“PROBE openapi: HTTP 200 at https://docs.cekura.ai/openapi.json — contains "openapi" key”
• [claimed-docs] https://docs.cekura.ai/api-reference/user/create-api-key.md“Create a new API key. When using API key authentication, only project-level API keys can be created.”

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

2 (weight) × 7 (quality) × 0.6 (partial) = 8.4 of 20 max

• [claimed-docs] https://docs.cekura.ai/cli-sdk/cli.md“Manage agents, scenarios, runs, and call data from your terminal”
• [claimed-docs] https://docs.cekura.ai/cli-sdk/sdk.md“Programmatic access to Cekura — sync and async clients for application code”
• [claimed-docs] https://docs.cekura.ai/api-reference/observability/send-calls.md“Your agent (or its provider's post-call webhook) POSTs here with the transcript, recording URL, and metadata; Cekura stores it as a `CallLog`, schedules metric evaluation”
• [claimed-docs] https://docs.cekura.ai/api-reference/user/create-api-key.md“Create a new API key. When using API key authentication, only project-level API keys can be created.”
• [probe] https://docs.cekura.ai/openapi.json“PROBE openapi: HTTP 200 at https://docs.cekura.ai/openapi.json — contains "openapi" key”
• [probe] https://docs.cekura.ai/cli-sdk/cli“official CLI documented at https://docs.cekura.ai/cli-sdk/cli”
• [claimed-docs] https://docs.cekura.ai/documentation/guides/dashboards.md“Build custom dashboards with widgets to visualize and analyze your call data, metrics, and metadata.”

Export all of my data in open formats and leaveweight 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

Read the product's source under an open licenseweight 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

Self-host the core productweight 3

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

• [claimed-docs] https://docs.cekura.ai/api-reference/user/create-api-key.md“Create a new API key. When using API key authentication, only project-level API keys can be created.”
• [claimed-docs] https://docs.cekura.ai/documentation/introduction“create a comprehensive plan to integrate cekura observability”
• [probe] https://docs.cekura.ai/llms.txt“PROBE llms.txt: HTTP 200 at https://docs.cekura.ai/llms.txt # Cekura > Cekura is the testing and observability platform for voice AI agents. Run simulated conversations, evaluate”

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

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

• [claimed-docs] https://docs.cekura.ai/documentation/key-concepts/metrics/llm-judge-metric.md“Evaluate AI voice agent calls using natural language criteria with LLM-powered judging”
• [claimed-docs] https://www.cekura.ai“Live drift detection across every call.”
• [claimed-docs] https://www.cekura.ai“Cekura flags issues → reproduces in simulation → suggests fixes automatically.”
• [claimed-docs] https://docs.cekura.ai/documentation/guides/dashboards.md“Build custom dashboards with widgets to visualize and analyze your call data, metrics, and metadata.”

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://docs.cekura.ai/documentation/guides/cronjob.md“Learn how to set up and manage automated cron jobs for your AI agent testing and evaluation workflows.”
• [claimed-docs] https://docs.cekura.ai/documentation/guides/github-actions-ci-cd.md“Learn how to set up GitHub Actions workflows to automatically test your agents with each change”
• [claimed-docs] https://www.cekura.ai“Live drift detection across every call.”
• [claimed-docs] https://www.cekura.ai“Cekura flags issues → reproduces in simulation → suggests fixes automatically.”
• [claimed-docs] https://docs.cekura.ai/api-reference/observability/send-calls.md“Your agent (or its provider's post-call webhook) POSTs here with the transcript, recording URL, and metadata; Cekura stores it as a `CallLog`, schedules metric evaluation”

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

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

• [claimed-docs] https://www.cekura.ai“Cekura flags issues → reproduces in simulation → suggests fixes automatically.”
• [claimed-docs] https://docs.cekura.ai/mcp/overview.md“Install Cekura Skills and MCP so your AI assistant can design, run, and improve voice-agent evaluations.”
• [claimed-docs] https://docs.cekura.ai/documentation/introduction“npx skills add cekura-ai/cekura-skills --all”

Operate the product with natural-language commandsweight 2

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

• [claimed-docs] https://docs.cekura.ai/documentation/introduction“npx skills add cekura-ai/cekura-skills --all”
• [claimed-docs] https://docs.cekura.ai/mcp/overview.md“Install Cekura Skills and MCP so your AI assistant can design, run, and improve voice-agent evaluations.”
• [github] https://github.com/cekura-ai/cekura-skills“13 Skills, 14 Commands in one plugin”
• [claimed-docs] https://docs.cekura.ai/documentation/key-concepts/metrics/llm-judge-metric.md“Evaluate AI voice agent calls using natural language criteria with LLM-powered judging”
• [probe] https://docs.cekura.ai/mcp/overview“official MCP server documented at https://docs.cekura.ai/mcp/overview”

Perform bulk operations across many items at onceweight 2

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

• [claimed-docs] https://www.cekura.ai“Run thousands of synthetic conversations before go-live.”
• [claimed-docs] https://docs.cekura.ai/cli-sdk/cli.md“Manage agents, scenarios, runs, and call data from your terminal”
• [claimed-docs] https://docs.cekura.ai/cli-sdk/sdk.md“Programmatic access to Cekura — sync and async clients for application code”
• [claimed-docs] https://docs.cekura.ai/documentation/guides/cronjob.md“Learn how to set up and manage automated cron jobs for your AI agent testing and evaluation workflows.”
• [claimed-docs] https://docs.cekura.ai/documentation/guides/github-actions-ci-cd.md“Learn how to set up GitHub Actions workflows to automatically test your agents with each change”

Define rules that trigger actions automatically on eventsweight 3

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

• [claimed-docs] https://docs.cekura.ai/documentation/guides/cronjob.md“Learn how to set up and manage automated cron jobs for your AI agent testing and evaluation workflows.”
• [claimed-docs] https://docs.cekura.ai/documentation/guides/github-actions-ci-cd.md“Learn how to set up GitHub Actions workflows to automatically test your agents with each change”
• [claimed-docs] https://www.cekura.ai“Cekura flags issues → reproduces in simulation → suggests fixes automatically.”
• [claimed-docs] https://www.cekura.ai“Live drift detection across every call.”

Schedule recurring jobs or workflowsweight 2

2 (weight) × 7 (quality) × 1.0 (full) = 14.0 of 20 max

• [claimed-docs] https://docs.cekura.ai/documentation/guides/cronjob.md“Learn how to set up and manage automated cron jobs for your AI agent testing and evaluation workflows.”
• [claimed-docs] https://docs.cekura.ai/documentation/guides/github-actions-ci-cd.md“Learn how to set up GitHub Actions workflows to automatically test your agents with each change”
• [claimed-docs] https://docs.cekura.ai/cli-sdk/cli.md“Manage agents, scenarios, runs, and call data from your terminal”
• [claimed-docs] https://docs.cekura.ai/cli-sdk/sdk.md“Programmatic access to Cekura — sync and async clients for application code”

Version, review, and roll back my automationsweight 1

1 (weight) × 3 (quality) × 0.6 (partial) = 1.8 of 10 max

• [claimed-docs] https://docs.cekura.ai/documentation/guides/testing-agents/ab-testing.md“Compare two versions of your agent side-by-side to measure prompt, model, or configuration changes.”
• [claimed-docs] https://docs.cekura.ai/documentation/guides/dashboards.md“Build custom dashboards with widgets to visualize and analyze your call data, metrics, and metadata.”