StackResolve logoStackResolve

Methodology

How the AgentReady Score is computed. Four pillars, weighted signals, deterministic.

The AgentReady Score measures how ready a product is for AI agents to discover, understand, adopt, and operate. It is deterministic. The score is derived from stored facts, not from a model's opinion, so the same facts always produce the same number and every point is traceable to a signal.

#The framework: DISCOVER, UNDERSTAND, ADOPT, OPERATE

PillarScore keyThe agent question it answers
DISCOVERdiscoveryCan an agent find you and know you exist?
UNDERSTANDunderstandingCan an agent tell what you do, your pricing, and when to use you?
ADOPTadoptionCan an agent sign up, get a key, and install without a human?
OPERATEoperabilityCan an agent actually use you as a primitive?

#How the number is built

Each pillar holds a set of weighted signals. A signal is either present or not. A pillar score is the sum of the weights of the present signals, divided by the total possible weight for that pillar, times 100. The headline agentready score is the average of the four pillar scores. Every score is rounded to a whole number.

Text
pillar   = round( sum(weights of present signals) / sum(all weights) * 100 )
agentready = round( (discovery + understanding + adoption + operability) / 4 )

#DISCOVER signals

Signal (namespace.key)WeightPresent when
agent_capability.llms_txt3An /llms.txt file is served
agent_capability.openapi2An OpenAPI spec is served
agent_capability.api2A public API is detected
company.categories1Categories are populated
readability.robots_ai_allowed1robots.txt does not block AI crawlers
readability.sitemap1A sitemap.xml is served
readability.agents_md2An AGENTS.md, CLAUDE.md, or llms-full.txt file is served

#UNDERSTAND signals

Signal (namespace.key)WeightPresent when
company.description2A description is populated
pricing.pricing or pricing.free_tier2Pricing or a free-tier flag is known
company.products2Products are populated
company.categories1Categories are populated
agent_capability.authentication1An auth method is documented
readability.meta_description1The homepage has a meta description
readability.json_ld1The homepage has Schema.org JSON-LD
readability.canonical1The homepage has a canonical link
readability.markdown_mirror1A text/markdown mirror is served

#ADOPT signals

Signal (namespace.key)WeightPresent when
pricing.self_serve3An agent can sign up and pay without a human
agent_capability.sdks2Official SDKs are detected
agent_capability.cli1A CLI is detected
agent_capability.api1A public API is detected
agent_capability.openapi1An OpenAPI spec is served

#OPERATE signals

Signal (namespace.key)WeightPresent when
agent_capability.mcp_available3An MCP server exists
agent_capability.api2A public API is detected
agent_capability.sdks1Official SDKs are detected
agent_capability.claude_compatible1Documented Claude Code compatibility
agent_capability.codex_compatible1Documented Codex compatibility
agent_capability.cursor_compatible1Documented Cursor compatibility

#Where the signals come from

The audit does not trust marketing copy for capability claims. The homepage rarely states whether a vendor has SDKs, a CLI, or an MCP server, so the audit looks where the truth lives and writes deterministic, high-confidence facts:

  • GitHub org repositories: an *-mcp repo means an MCP server exists, a *-cli repo means a CLI exists, SDK and client repos reveal SDK languages.
  • npm and PyPI: a published package confirms an SDK and its language.
  • Direct probes: /llms.txt, /openapi.json, robots.txt, sitemap.xml, and AGENTS.md on the apex and the docs. subdomain.
  • Homepage HTML: canonical link, meta description, JSON-LD, and a markdown mirror link.

Hard evidence overrides the model. If the GitHub org has an MCP repo, mcp_available is set true regardless of what the copy says. Each fact carries a confidence and a timestamp. See Sources and Freshness.

#Reading a score

A score in the 90s means an agent can find, understand, adopt, and operate the product with almost no human help. A score in the 50s usually means the product is usable by a developer but leaves gaps for an agent: no llms.txt, no MCP server, no OpenAPI spec, or no self-serve signup. The audit issues array lists the specific fixes, ordered by how much they would raise the score.

  • Audit: score one product and get the fix list.
  • Registry: browse products already scored.
  • Schemas: the fact namespaces behind every signal.