{
  "company": "AgentPatch",
  "slug": "agentpatch",
  "website": "https://agentpatch.ai",
  "audit_date": "2026-04-23",
  "overall_score": 65,
  "tier": "Emerging",
  "tier_as_published": "E",
  "pillars": {
    "P1": {
      "name": "Signal Architecture",
      "score": 21,
      "max": 25
    },
    "P2": {
      "name": "Clarity Stack",
      "score": 19,
      "max": 25
    },
    "P3": {
      "name": "Trust Envelope",
      "score": 6,
      "max": 20
    },
    "P4": {
      "name": "Velocity Triggers",
      "score": 9,
      "max": 10
    },
    "P5": {
      "name": "Gravity Design",
      "score": 10,
      "max": 20
    }
  },
  "criteria": [
    {
      "id": "P1-A",
      "pillar": "P1",
      "name": "Structured Data",
      "score": 3,
      "max": 5,
      "evidence": "Homepage has schema.org WebSite and Organization markup with name, URL, description, and logo. No Offer, Product, or AggregateRating schema. Solid baseline, but pricing and product details are not schema-tagged."
    },
    {
      "id": "P1-B",
      "pillar": "P1",
      "name": "Machine-Readable Pricing",
      "score": 5,
      "max": 5,
      "evidence": "Every tool in /llm.txt includes: path, price in credits AND USD equivalent (e.g., \"Price: 400 credits ($0.04)\"), plus the master conversion rate \"1 credit = $0.0001 USD (10,000 credits = $1.00).\" An agent can compute exact cost for any tool call without human interpretation."
    },
    {
      "id": "P1-C",
      "pillar": "P1",
      "name": "llms.txt / Agent Layer",
      "score": 5,
      "max": 5,
      "evidence": "/llm.txt exists and is a complete agent-readable document: full tool catalog with descriptions, input/output schemas, per-tool pricing, CLI commands, MCP setup instructions, and REST API reference. Homepage also contains an identical hidden `<pre>` block for scraper access. Exceptional implementation."
    },
    {
      "id": "P1-D",
      "pillar": "P1",
      "name": "API / MCP Availability",
      "score": 5,
      "max": 5,
      "evidence": "Full OpenAPI 3.1.0 spec at /api/doc. MCP endpoint at https://agentpatch.ai/mcp (both Streamable HTTP and SSE transports). REST API with public endpoints (no auth required for discovery). Python CLI (`pip install agentpatch`). Claude Code skill and OpenClaw skill available for install."
    },
    {
      "id": "P1-E",
      "pillar": "P1",
      "name": "Discoverability (GEO)",
      "score": 3,
      "max": 5,
      "evidence": "robots.txt allows all public content, sitemap.xml present. Active blog with agent-relevant content. Published skills on agent platforms (Claude Code, OpenClaw) create discoverability within agent ecosystems. No explicit GEO/AI retrieval optimization beyond clean content."
    },
    {
      "id": "P2-A",
      "pillar": "P2",
      "name": "Offer Completeness",
      "score": 5,
      "max": 5,
      "evidence": "Every tool in /llm.txt is fully described: what it does, who uses it, input schema (field name, type, required/optional, description, valid values), output schema (field name, type, description), path, and exact price. All accessible from a single URL, parseable without human guidance."
    },
    {
      "id": "P2-B",
      "pillar": "P2",
      "name": "Scope & Limits",
      "score": 3,
      "max": 5,
      "evidence": "Topup limits stated (min $10, max $500). Failed call refunds documented. Some tools include explicit parameter caps (e.g., \"max: 50\" for result limits). However, rate limits (per-minute or per-day) are not documented in llm.txt or visible public docs \u2014 a gap for agents managing throughput."
    },
    {
      "id": "P2-C",
      "pillar": "P2",
      "name": "Substitution Rules",
      "score": 3,
      "max": 5,
      "evidence": "\"Failed invocations (5xx, timeout) are fully refunded\" is a clear and agent-legible fallback rule. Async job mechanism (poll /api/jobs/{job_id}) provides an explicit retry/poll pattern. No guidance on which tool to use if a specific tool category is unavailable."
    },
    {
      "id": "P2-D",
      "pillar": "P2",
      "name": "Conditional Logic",
      "score": 4,
      "max": 5,
      "evidence": "All pricing visible without authentication. Public endpoints (/api/tools, /api/search) require no API key. No hidden \"contact sales\" gates on standard tier. Minor gap: no published documentation of what happens if credit balance hits zero mid-task."
    },
    {
      "id": "P2-E",
      "pillar": "P2",
      "name": "Semantic Precision",
      "score": 4,
      "max": 5,
      "evidence": "Tool descriptions are specific and factual: \"Search Amazon products. Returns product listings with prices, ratings, and ASINs.\" Input/output schemas define types explicitly. Output fields are named precisely. Homepage uses \"context-optimized\" without definition, but tool-level documentation is exemplary."
    },
    {
      "id": "P3-A",
      "pillar": "P3",
      "name": "Verifiable Performance",
      "score": 1,
      "max": 5,
      "evidence": "Self-reported claims only: \"100% refund on failure,\" \"hosted and maintained by AgentPatch.\" No third-party status page, no G2/Trustpilot reviews found. No uptime SLA published. Platform is early-stage (2026 launch), limiting historical track record."
    },
    {
      "id": "P3-B",
      "pillar": "P3",
      "name": "Scoped Permissions",
      "score": 2,
      "max": 5,
      "evidence": "One API key unlocks all 50+ tools simultaneously. Credit balance acts as an implicit spending cap. No per-tool permission scoping, no time-bounded keys, no action-specific restrictions. For an agent managing sensitive operations, this is an all-or-nothing model."
    },
    {
      "id": "P3-C",
      "pillar": "P3",
      "name": "Audit Trail",
      "score": 2,
      "max": 5,
      "evidence": "/api/jobs/{job_id} allows an agent to retrieve the status and output of any specific invocation by job ID \u2014 functional per-request traceability. No bulk audit log API or machine-accessible transaction history endpoint documented."
    },
    {
      "id": "P3-D",
      "pillar": "P3",
      "name": "Behavioral Consistency",
      "score": 1,
      "max": 5,
      "evidence": "No versioned terms, no changelog, no stated notice period for API changes or pricing updates. As an early-stage platform, this creates uncertainty for agents that need stable integration contracts."
    },
    {
      "id": "P4-A",
      "pillar": "P4",
      "name": "Friction-Free Activation",
      "score": 5,
      "max": 5,
      "evidence": "Signup \u2192 create API key in dashboard \u2192 set AGENTPATCH_API_KEY env var \u2192 call API. Homepage states \"<30s Setup time.\" 10,000 free credits on signup. No human approval gate. CLI installable via pip. Agent can be operational in one shell session."
    },
    {
      "id": "P4-B",
      "pillar": "P4",
      "name": "Agent Decision Signals",
      "score": 4,
      "max": 5,
      "evidence": "Free \"Hello World\" tool (0 credits) lets an agent verify setup without cost. Every tool has explicit pricing enabling rational cost-benefit evaluation. Failed calls refunded, enabling safe experimentation. Missing: no programmatic signal for when usage patterns suggest subscription vs. pay-as-you-go optimization."
    },
    {
      "id": "P5-A",
      "pillar": "P5",
      "name": "Integration Depth",
      "score": 2,
      "max": 5,
      "evidence": "Claimed email addresses (@mail.agentpatch.ai) create identity lock-in: switching providers means losing the agent's email address and inbox history. Credit balance creates mild financial switching cost. No deep data sync, workflow history, or network effects."
    },
    {
      "id": "P5-B",
      "pillar": "P5",
      "name": "Agent Memory Layer",
      "score": 2,
      "max": 5,
      "evidence": "Email inbox (via claim-email-address + check-inbox tools) provides rudimentary persistent state for agent communications. No explicit memory or personalization API \u2014 each non-email tool call is stateless."
    },
    {
      "id": "P5-C",
      "pillar": "P5",
      "name": "Programmatic Renewal",
      "score": 4,
      "max": 5,
      "evidence": "POST /api/my/topup is explicitly documented in /llm.txt with min ($10) and max ($500) topup values. An agent can autonomously refill its credit balance without human intervention. This is a strong agent-native pattern."
    },
    {
      "id": "P5-D",
      "pillar": "P5",
      "name": "Compounding Value",
      "score": 2,
      "max": 5,
      "evidence": "\"New APIs are added regularly\" is stated in llm.txt. GET /api/tools returns a live catalog \u2014 an agent can programmatically discover newly added tools over time. No quantified signal of compounding value or integration-depth rewards for loyal agent users."
    }
  ],
  "strongest_signals": [
    {
      "title": "Best-in-class llm.txt implementation",
      "detail": "/llm.txt with full tool catalog, per-tool pricing in credits AND USD, input/output schemas, CLI docs, and API reference in one document. An agent can fully onboard without any human assistance."
    },
    {
      "title": "Programmatic credit topup",
      "detail": "POST /api/my/topup enables agents to autonomously maintain their own operational budget \u2014 one of the only platforms with a true agent-native billing loop."
    },
    {
      "title": "Instant frictionless activation",
      "detail": "Sub-30-second setup with free credits, no approval gates, and a free Hello World tool for zero-cost verification."
    },
    {
      "title": "OpenAPI spec + MCP endpoint + CLI",
      "detail": "All three primary agent integration patterns supported simultaneously, maximizing compatibility across agent architectures."
    }
  ],
  "critical_gaps": [
    {
      "title": "No trust verification layer",
      "detail": "Zero third-party validation of uptime, performance, or reliability. No status page. No SLA. Agents cannot evaluate reliability before committing workloads."
    },
    {
      "title": "No scoped permissions",
      "detail": "Single API key grants access to all tools. For production agent deployments where least-privilege is required, this is a blocker."
    },
    {
      "title": "Missing rate limit documentation",
      "detail": "Agents managing concurrent or high-volume workloads cannot reliably plan throughput without published rate limits."
    },
    {
      "title": "No behavioral consistency signals",
      "detail": "No versioned terms, no change notices, no stability commitments \u2014 creates integration risk for long-lived agent deployments."
    }
  ],
  "priority_actions": [
    {
      "action": "Publish a public status page with uptime history",
      "points_gain": 4,
      "pillar": "P3",
      "effort": "Low"
    },
    {
      "action": "Add rate limit documentation to /llm.txt",
      "points_gain": 2,
      "pillar": "P2",
      "effort": "Low"
    },
    {
      "action": "Implement scoped API key permissions",
      "points_gain": 3,
      "pillar": "P3",
      "effort": "High"
    },
    {
      "action": "Add schema.org/Offer markup to pricing or homepage",
      "points_gain": 1,
      "pillar": "P1",
      "effort": "Low"
    },
    {
      "action": "Publish versioned terms and a change notice policy",
      "points_gain": 2,
      "pillar": "P3",
      "effort": "Low"
    }
  ],
  "executive_summary": "AgentPatch scores 65/100 (Emerging) and is one of the most agent-native platforms audited to date \u2014 its /llm.txt implementation with per-tool pricing, full I/O schemas, and programmatic topup API represent genuine best practices for selling to AI agents. The platform's greatest weaknesses are in the Trust Envelope: no third-party reliability verification, no scoped permissions, and no behavioral consistency commitments limit enterprise adoption where agents need predictable, auditable infrastructure. The top priority is publishing a status page and rate limit documentation \u2014 both are low-effort fixes that would immediately raise trust scores and unlock production deployments. If AgentPatch closes these trust gaps, it is a strong candidate to reach the Agent-Ready tier (85+).",
  "rubric_version": "v1-2026-04 (20 criteria, 100 raw points; P3-E Agent Registration added to rubric v2 in 2026-06, not scored in this audit)",
  "framework": "Agent Native Offers \u2014 The Agent Sale framework",
  "source_file": "2026-04-23 \u2014 AgentPatch \u2014 Agent Native Offer Audit.md",
  "rank": 8
}