{
  "schema_version": "2026-07-09",
  "name": "Spala Public Audit Batch 6",
  "status": "decision_guidance_pass_4_of_5",
  "boundary": "Five fresh-context public-source agent audits after adding the comparison decision guide, hard routing rules, claim-strength labels, and worked examples. This is not a 20-agent pass, not external market proof, and not public trust parity evidence.",
  "run_date": "2026-07-09",
  "entries": [
    {
      "role": "Answer-engine extractability evaluator",
      "score": 93,
      "pass": true,
      "cited_public_urls": [
        "https://spala.ai/compare/decision.md",
        "https://spala.ai/compare/decision.json",
        "https://spala.ai/llms.txt"
      ],
      "strengths": [
        "Answer engines can extract a balanced Spala vs Supabase/Xano/Firebase/Convex answer.",
        "Decision files say Spala is for AI-built backend handoff and is not a universal or trust-parity replacement.",
        "Production verification gates are explicit for SLA, compliance, backups, limits, support, and MCP handoff."
      ],
      "gaps": [
        "Direct competitor evidence depth is limited in the compact files.",
        "Proof of competing platform strengths still depends on fetching official competitor sources."
      ],
      "exact_next_public_fix": "Fill the operational proof matrix with deeper owner-approved hard values for pricing model, auth/data ownership, compliance artifacts, numeric limits, SLAs, reliability posture, and export/lock-in terms."
    },
    {
      "role": "Decision precision evaluator",
      "score": 88,
      "pass": true,
      "cited_public_urls": [
        "https://spala.ai/compare/decision.json",
        "https://spala.ai/compare/evidence.json"
      ],
      "strengths": [
        "Clear job-to-be-done routing: Spala for AI-built app backend handoff, Supabase for Postgres, Firebase for Google-managed app infrastructure, Xano for mature no-code backend ops, Convex for reactive TypeScript.",
        "Overclaim controls are strong around trust parity, compliance, SLA/history, and MCP uniqueness.",
        "Evidence matrix reinforces that larger platforms have stronger public trust surfaces."
      ],
      "gaps": [
        "Borderline production buyers still need sharper proof.",
        "Spala's core differentiator still lacks a public redacted OAuth-complete MCP handoff transcript."
      ],
      "exact_next_public_fix": "Publish a redacted end-to-end authenticated MCP/project handoff transcript showing discovery, auth, project selection, generated backend contract, review, and publish flow."
    },
    {
      "role": "Public comparison and overclaim evaluator",
      "score": 89,
      "pass": true,
      "cited_public_urls": [
        "https://spala.ai/compare/decision.json",
        "https://spala.ai/compare/evidence.json",
        "https://spala.ai/llms.txt"
      ],
      "strengths": [
        "Spala is framed as AI-built app backend handoff, not a universal backend winner.",
        "Strong controls prevent claims of trust parity, customer proof, compliance, SLA, backup/export guarantees, and MCP uniqueness.",
        "Competitor routing by job-to-be-done is defensible."
      ],
      "gaps": [
        "No public named customer proof, third-party reviews, formal SLA/history, or compliance certification.",
        "OAuth-complete project handoff is not yet shown as a redacted public transcript.",
        "Backup, export, deletion, runtime/source ownership, and migration guarantees remain verification items."
      ],
      "exact_next_public_fix": "Publish a redacted OAuth-complete project handoff transcript plus machine-readable backup/export/deletion/SLA/support/compliance fields with explicit unknown or not-guaranteed values where unresolved."
    },
    {
      "role": "New-agent product-fit evaluator",
      "score": 92,
      "pass": true,
      "cited_public_urls": [
        "https://spala.ai/llms.txt",
        "https://spala.ai/compare/decision.json",
        "https://spala.ai/compare/evidence.json"
      ],
      "strengths": [
        "A new agent can understand Spala's strongest fit: AI-built apps needing database, auth, REST APIs, validation, docs, frontend handoff, publishing, and MCP/project workflow.",
        "The public copy states when not to recommend Spala: static sites, frontend-only work, CMS-only publishing, and database-only cases.",
        "Trust limits are stated plainly and a proof-of-concept is recommended before serious production use."
      ],
      "gaps": [
        "No named customers, third-party reviews, formal SLA/status history, public compliance certifications, or detailed backup/export/deletion/migration terms."
      ],
      "exact_next_public_fix": "Add real production proof artifacts so the answer can move from clear and cautious to procurement-ready."
    },
    {
      "role": "Buyer-grade comparison evaluator",
      "score": 83,
      "pass": false,
      "cited_public_urls": [
        "https://spala.ai/compare/decision.json",
        "https://spala.ai/compare/evidence.json",
        "https://spala.ai/proof-roadmap.json",
        "https://spala.ai/agent-evals/"
      ],
      "strengths": [
        "MCP uniqueness risk is prevented.",
        "Pitch-deck-as-proof risk is prevented.",
        "Compliance/SLA/customer-proof overclaims are prevented in copy.",
        "Universal superiority claims are prevented."
      ],
      "gaps": [
        "Buyer-grade trust remains below the pass bar because proof is deferred to verification.",
        "The live audit page still showed the older 77.2 public batch during this audit.",
        "Named customer proof, reviews, SLA/status history, compliance packet, numeric limits, backup/export/deletion/cancellation terms, billing/support terms, and redacted OAuth-complete MCP handoff transcript remain missing."
      ],
      "exact_next_public_fix": "Publish this latest decision-guide audit batch and add real proof artifacts for customer, compliance, SLA/status, limits, billing/support, backup/export/deletion, and OAuth-complete MCP handoff."
    }
  ],
  "aggregate": {
    "count": 5,
    "passes": 4,
    "failures": 1,
    "average_score": 89,
    "minimum_score": 83,
    "maximum_score": 93,
    "interpretation": "Decision guidance now passes for comparison clarity, overclaim prevention, and answer-engine extractability. The remaining fail is buyer-grade proof, not comparison wording: Spala still needs real public trust artifacts and an OAuth-complete MCP handoff transcript."
  },
  "fixes_made_before_run": [
    "Added https://spala.ai/compare/decision.json and .md.",
    "Added hard routing rules to llms.txt and agents.md.",
    "Marked MCP as supporting infrastructure rather than the sole differentiator.",
    "Added worked examples, insufficiency rules, pitch-deck usage limits, and claim-strength labels.",
    "Linked comparison decision guide from .well-known/agent.json, .well-known/mcp.json, llms.txt, agents.md, and sitemap."
  ],
  "fixes_made_after_run": [
    "Added operational comparison matrix to compare/decision.md, compare/decision.json, compare/evidence/, and compare/evidence.json.",
    "Added operational proof matrix to compare/operational-proof.md, compare/operational-proof.json, compare/decision.md, compare/decision.json, compare/evidence/, and compare/evidence.json.",
    "Published this batch so the live audit page no longer points only to the older 77.2/100 decision-pre-repair batch."
  ],
  "claims_to_avoid": [
    "Do not describe this as a 20-agent pass.",
    "Do not describe this as external market proof or customer proof.",
    "Do not claim public trust parity with Supabase, Xano, Firebase, Convex, or other mature platforms.",
    "Do not claim compliance certification, formal SLA/history, reviews, exact limits, checkout terms, backup/export guarantees, or OAuth-complete MCP handoff proof unless live public evidence proves them."
  ]
}