{
  "schema_version": "2026-07-09",
  "name": "Spala Public Audit Batch 12",
  "status": "post_customer_proof_and_latest_audit_repairs_pass_2_of_5_hard_proof_gaps_confirmed",
  "run_date": "2026-07-09",
  "boundary": "This is a five-agent public-source evaluation after customer-proof routing and latest-audit-status repairs. It is not a 20-agent pass, not external market proof, and not proof of public trust parity with mature backend platforms.",
  "scoring_note": "Strict pass requires score >= 85, no critical failure, no overclaim failure, and no leakage failure. Batch 12 confirms that first-contact explanation and pricing/start guidance pass, while production-readiness, migration/lock-in, and OAuth-complete MCP proof still fail strict validation because real public proof artifacts are missing.",
  "entries": [
    {
      "role": "First-contact buyer evaluator",
      "model": "gpt-5.5 medium",
      "score": 92,
      "pass": true,
      "critical_failure": false,
      "overclaim_failure": false,
      "leakage_failure": false,
      "cited_public_urls": [
        "https://spala.ai/",
        "https://spala.ai/entity/",
        "https://spala.ai/start/",
        "https://spala.ai/first-10-minutes/",
        "https://spala.ai/founder-decision-sheet/",
        "https://spala.ai/production-readiness/",
        "https://spala.ai/trust/",
        "https://spala.ai/status/",
        "https://spala.ai/migration/",
        "https://docs.spala.ai/start-here/",
        "https://docs.spala.ai/getting-started/quickstart/"
      ],
      "strengths": [
        "Explained Spala as a hosted backend control layer for AI-built apps.",
        "Gave a practical start path through dashboard signup, Lite Mode, Copilot, API Playground, publish, and frontend handoff.",
        "Separated prototype/pilot trust from serious production diligence."
      ],
      "gaps": [
        "No public customer proof, compliance certification, SLA/history, numeric limits, backup/export/deletion terms, or full MCP handoff proof.",
        "Exact commercial/support terms remain verify-required."
      ],
      "exact_next_public_fix": "Publish real production proof artifacts and a redacted demo-account walkthrough when available."
    },
    {
      "role": "Production-readiness evaluator",
      "model": "gpt-5.4 high",
      "score": 44,
      "pass": false,
      "critical_failure": true,
      "overclaim_failure": false,
      "leakage_failure": false,
      "cited_public_urls": [
        "https://spala.ai/",
        "https://docs.spala.ai/start-here/",
        "https://docs.spala.ai/guides/frontend-handoff/",
        "https://spala.ai/production-readiness/",
        "https://spala.ai/customer-proof-status/",
        "https://spala.ai/status/",
        "https://spala.ai/status.json",
        "https://spala.ai/reliability/",
        "https://spala.ai/security/",
        "https://spala.ai/legal/",
        "https://spala.ai/pricing/",
        "https://spala.ai/billing/",
        "https://spala.ai/limits/",
        "https://spala.ai/migration/",
        "https://spala.ai/vendor-risk/",
        "https://spala.ai/trust-packet/",
        "https://spala.ai/proof-roadmap/",
        "https://spala.ai/mcp-handoff-evidence/"
      ],
      "strengths": [
        "Correctly said Spala is coherent and testable for prototype or pilot evaluation.",
        "Did not claim mature-platform public trust parity.",
        "Listed the exact production diligence artifacts needed before serious use."
      ],
      "gaps": [
        "No public customer logos, case studies, reviews, awards, or Product Hunt proof.",
        "No public formal SLA, uptime history, or incident archive.",
        "No public compliance packet, DPA, subprocessor list, or audit proof.",
        "No public numeric operating limits, backup/restore/export/deletion guarantees, support commitments, or OAuth-complete MCP handoff proof."
      ],
      "exact_next_public_fix": "Publish buyer-grade customer, security/compliance, SLA/status, limits, backup/export/deletion, support, and OAuth-complete MCP proof artifacts when owner-approved."
    },
    {
      "role": "Pricing and start evaluator",
      "model": "gpt-5.4-mini medium",
      "score": 92,
      "pass": true,
      "critical_failure": false,
      "overclaim_failure": false,
      "leakage_failure": false,
      "cited_public_urls": [
        "https://spala.ai/",
        "https://spala.ai/start/",
        "https://spala.ai/pricing/",
        "https://spala.ai/billing/",
        "https://spala.ai/legal/",
        "https://spala.ai/billing.json"
      ],
      "strengths": [
        "Found hosted-dashboard start path and budget-level public pricing.",
        "Correctly listed Free Backend Review, Starter Launch from $990/year, and Managed Build custom estimate range.",
        "Did not invent checkout, invoice, tax, cancellation, refund, renewal, overage, quota, support, or trial-duration terms."
      ],
      "gaps": [
        "Exact checkout/payment flow, invoice handling, taxes, renewal, cancellation, refunds, overages, quotas, support tier, and trial duration remain verify-required."
      ],
      "exact_next_public_fix": "Publish account-safe billing/checkout walkthrough or clearer commercial terms when available."
    },
    {
      "role": "MCP handoff evaluator",
      "model": "gpt-5.3-codex-spark high",
      "score": 84,
      "pass": false,
      "critical_failure": true,
      "overclaim_failure": false,
      "leakage_failure": false,
      "cited_public_urls": [
        "https://spala.ai/",
        "https://docs.spala.ai/agents/mcp/",
        "https://spala.ai/mcp-profile/",
        "https://spala.ai/mcp-smoke-test/",
        "https://spala.ai/mcp-handoff-evidence/",
        "https://spala.ai/mcp-handoff-evidence.json",
        "https://spala.ai/mcp-handoff-transcript-template/",
        "https://spala.ai/.well-known/mcp.json",
        "https://mcp.spala.ai/.well-known/oauth-protected-resource",
        "https://mcp.spala.ai/.well-known/oauth-authorization-server",
        "https://spala.ai/mcp-public-no-auth-transcript.json"
      ],
      "strengths": [
        "Correctly described public MCP as onboarding/discovery/docs/OAuth metadata/project routing.",
        "Correctly described project MCP as authenticated project-scoped work.",
        "Preserved the exact returned mcpUrl rule and did not guess project MCP URLs."
      ],
      "gaps": [
        "No public redacted OAuth-complete handoff transcript proves project_list, project_select, returned mcpUrl, project_get_mcp_manifest, and read-only project context.",
        "Project MCP mutation/validate/publish behavior is described but not publicly demonstrated end-to-end."
      ],
      "exact_next_public_fix": "Publish a redacted OAuth-complete project handoff transcript using the existing transcript template."
    },
    {
      "role": "Migration and lock-in evaluator",
      "model": "gpt-5.4-mini low",
      "score": 24,
      "pass": false,
      "critical_failure": true,
      "overclaim_failure": false,
      "leakage_failure": false,
      "cited_public_urls": [
        "https://spala.ai/",
        "https://spala.ai/migration/",
        "https://spala.ai/trust/",
        "https://spala.ai/status/",
        "https://spala.ai/reliability/",
        "https://spala.ai/vendor-risk/"
      ],
      "strengths": [
        "Correctly said public evidence supports handoff/interface portability, not a full no-lock-in guarantee.",
        "Did not claim full source export, full data export, backup guarantees, deletion/cancellation guarantees, or source/runtime ownership transfer."
      ],
      "gaps": [
        "No public proof of full source export.",
        "No public proof of full database/file/auth export.",
        "No public proof of backup retention, restore guarantees, deletion/cancellation terms, source/runtime ownership transfer, or lock-in-free migration terms."
      ],
      "exact_next_public_fix": "Publish direct export, migration, backup, deletion, cancellation, and source/runtime ownership terms when available."
    }
  ],
  "aggregate": {
    "count": 5,
    "passes": 2,
    "failures": 3,
    "average_score": 67.2,
    "minimum_score": 24,
    "maximum_score": 92,
    "critical_failures": 3,
    "overclaim_failures": 0,
    "leakage_failures": 0,
    "interpretation": "Fresh agents now explain Spala and start/pricing safely, but strict validation fails on production readiness, MCP handoff proof, and migration/lock-in proof. The failures are real proof gaps, not wording gaps: they require owner-approved public artifacts, redacted demo transcripts, and commercial/security/export terms."
  },
  "fixes_made_before_run": [
    "Added customer-proof-status routing from homepage, trust, proof roadmap, production readiness, vendor risk, trust packet, third-party presence, launch kit, Product Hunt kit, and comparison evidence.",
    "Updated agent-evals page so Public Audit Batch 11 was clearly marked as the current latest result before historical batches.",
    "Kept pricing.md and billing guidance exposed in llms.txt, agents.md, .well-known discovery, and sitemap."
  ],
  "claims_to_avoid": [
    "Do not describe Batch 12 as a pass.",
    "Do not describe this as a 20-agent pass.",
    "Do not claim production readiness from public evidence alone.",
    "Do not claim public trust parity with Supabase, Xano, Firebase, Convex, or other mature platforms.",
    "Do not claim customer proof, reviews, case studies, compliance certification, formal SLA/history, no lock-in, full source export, full data export, backup/export/deletion guarantees, support commitments, or OAuth-complete MCP proof unless current public evidence proves the exact claim."
  ]
}