{
  "apiVersion": "v1",
  "organization": {
    "id": "coval",
    "name": "Coval",
    "sector": "ai-vendor",
    "aiVendor": true,
    "domain": "coval.ai",
    "passages": 5,
    "checked": 5,
    "url": "https://the-ai-record.com/organizations/coval",
    "json": "https://the-ai-record.com/api/v1/organizations/coval.json",
    "description": "A startup that sells evaluation and testing tools for voice AI agents.",
    "ownership": null,
    "ticker": null,
    "hq": null,
    "founded": null,
    "website": "https://www.coval.ai",
    "profileSource": "https://www.coval.ai/blog/how-we-built-our-code-reviewer/",
    "figures": [],
    "topics": [
      "ai-review-quality",
      "code-review",
      "ai-review-cost"
    ]
  },
  "people": [
    {
      "id": "dana-dzik",
      "name": "Dana Dzik",
      "role": "Engineer, Coval (author of the Coval blog post on its code reviewer)",
      "level": "practitioner",
      "levelMeaning": "Someone doing the work at the organization.",
      "organization": "Coval",
      "organizationId": "coval",
      "passages": 5,
      "reported": 0,
      "url": "https://the-ai-record.com/people/dana-dzik",
      "json": "https://the-ai-record.com/api/v1/people/dana-dzik.json"
    }
  ],
  "passages": [
    {
      "id": "coval-asked-name-sensitive-risk-domains-2026",
      "text": "Asked to name sensitive risk domains in prose, the model claimed authorization in 38% of reviews, while about 18% of the changes touched anything authorization-shaped; required to quote the specific changed line instead, it produced 570 claims, of which 98% resolved to real code—the same model over the same pull requests, with only the form of the question changed.",
      "context": null,
      "speaker": "Dana Dzik",
      "speakerId": "dana-dzik",
      "speakerUrl": "https://the-ai-record.com/people/dana-dzik",
      "speakerLevel": "practitioner",
      "role": "Engineer, Coval (author of the Coval blog post on its code reviewer)",
      "voice": "person",
      "organization": "Coval",
      "organizationId": "coval",
      "organizationUrl": "https://the-ai-record.com/organizations/coval",
      "aiVendor": true,
      "work": {
        "title": "Notes on Building a Code Reviewer",
        "type": "post",
        "date": "2026-09-10",
        "publisher": "Coval blog",
        "locator": "The rebuild",
        "url": "https://www.coval.ai/blog/how-we-built-our-code-reviewer/"
      },
      "grade": "B",
      "gradeMeaning": "The organization's own post, paper or talk.",
      "verification": {
        "status": "verified",
        "meaning": "An independent second reader re-fetched the source and confirmed the wording.",
        "reviewedOn": "2026-11-07"
      },
      "topics": [
        "ai-review-quality"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [
        {
          "metric": "claims-resolving-to-real-code",
          "value": 0.98,
          "unit": "share",
          "period": "570 claims when the reviewer must quote the changed line",
          "definition": "Share of 570 review claims that resolved to real code when each claim had to quote a changed line",
          "level": "human-approves"
        }
      ],
      "url": "https://the-ai-record.com/passages/coval-asked-name-sensitive-risk-domains-2026",
      "json": "https://the-ai-record.com/api/v1/passages/coval-asked-name-sensitive-risk-domains-2026.json"
    },
    {
      "id": "coval-august-people-opened-2-578-pull-2026",
      "text": "In August, people at Coval opened 2,578 pull requests and pushed roughly 3,400 further commits to them after they were first marked ready.",
      "context": null,
      "speaker": "Dana Dzik",
      "speakerId": "dana-dzik",
      "speakerUrl": "https://the-ai-record.com/people/dana-dzik",
      "speakerLevel": "practitioner",
      "role": "Engineer, Coval (author of the Coval blog post on its code reviewer)",
      "voice": "person",
      "organization": "Coval",
      "organizationId": "coval",
      "organizationUrl": "https://the-ai-record.com/organizations/coval",
      "aiVendor": true,
      "work": {
        "title": "Notes on Building a Code Reviewer",
        "type": "post",
        "date": "2026-09-10",
        "publisher": "Coval blog",
        "locator": "Introduction",
        "url": "https://www.coval.ai/blog/how-we-built-our-code-reviewer/"
      },
      "grade": "B",
      "gradeMeaning": "The organization's own post, paper or talk.",
      "verification": {
        "status": "verified",
        "meaning": "An independent second reader re-fetched the source and confirmed the wording.",
        "reviewedOn": "2026-11-07"
      },
      "topics": [
        "code-review"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [
        {
          "metric": "pull-requests-opened",
          "value": 2578,
          "unit": "count",
          "period": "August 2026",
          "definition": "Pull requests opened by people at Coval in August; about 3,400 further commits were pushed after they were marked ready",
          "level": "unclear"
        }
      ],
      "url": "https://the-ai-record.com/passages/coval-august-people-opened-2-578-pull-2026",
      "json": "https://the-ai-record.com/api/v1/passages/coval-august-people-opened-2-578-pull-2026.json"
    },
    {
      "id": "coval-reviews-capped-three-findings-silence-2026",
      "text": "Reviews are capped at three findings, a partly arbitrary number kept because it measurably changes whether people read the output; and silence is the usual outcome, 922 of the 1,732 recorded runs of this design having published nothing, a mean of 0.70 findings per review.",
      "context": null,
      "speaker": "Dana Dzik",
      "speakerId": "dana-dzik",
      "speakerUrl": "https://the-ai-record.com/people/dana-dzik",
      "speakerLevel": "practitioner",
      "role": "Engineer, Coval (author of the Coval blog post on its code reviewer)",
      "voice": "person",
      "organization": "Coval",
      "organizationId": "coval",
      "organizationUrl": "https://the-ai-record.com/organizations/coval",
      "aiVendor": true,
      "work": {
        "title": "Notes on Building a Code Reviewer",
        "type": "post",
        "date": "2026-09-10",
        "publisher": "Coval blog",
        "locator": "The rebuild",
        "url": "https://www.coval.ai/blog/how-we-built-our-code-reviewer/"
      },
      "grade": "B",
      "gradeMeaning": "The organization's own post, paper or talk.",
      "verification": {
        "status": "verified",
        "meaning": "An independent second reader re-fetched the source and confirmed the wording.",
        "reviewedOn": "2026-11-07"
      },
      "topics": [
        "ai-review-quality"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [
        {
          "metric": "review-runs-publishing-nothing",
          "value": 922,
          "unit": "count",
          "period": "1,732 recorded runs of the current design",
          "definition": "Review runs, of 1,732 recorded, that published no findings",
          "level": "human-approves"
        }
      ],
      "url": "https://the-ai-record.com/passages/coval-reviews-capped-three-findings-silence-2026",
      "json": "https://the-ai-record.com/api/v1/passages/coval-reviews-capped-three-findings-silence-2026.json"
    },
    {
      "id": "coval-roster-brought-median-cost-per-review-2026",
      "text": "In its first week in production the roster brought the median cost per review from about thirty cents to eleven while publishing at roughly the same rate.",
      "context": null,
      "speaker": "Dana Dzik",
      "speakerId": "dana-dzik",
      "speakerUrl": "https://the-ai-record.com/people/dana-dzik",
      "speakerLevel": "practitioner",
      "role": "Engineer, Coval (author of the Coval blog post on its code reviewer)",
      "voice": "person",
      "organization": "Coval",
      "organizationId": "coval",
      "organizationUrl": "https://the-ai-record.com/organizations/coval",
      "aiVendor": true,
      "work": {
        "title": "Notes on Building a Code Reviewer",
        "type": "post",
        "date": "2026-09-10",
        "publisher": "Coval blog",
        "locator": "The roster",
        "url": "https://www.coval.ai/blog/how-we-built-our-code-reviewer/"
      },
      "grade": "B",
      "gradeMeaning": "The organization's own post, paper or talk.",
      "verification": {
        "status": "verified",
        "meaning": "An independent second reader re-fetched the source and confirmed the wording.",
        "reviewedOn": "2026-11-07"
      },
      "topics": [
        "ai-review-cost",
        "code-review"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [
        {
          "metric": "median-review-cost",
          "value": 0.11,
          "unit": "usd",
          "period": "first week of the roster in production",
          "definition": "Median model cost per automated code review, down from about $0.30",
          "level": "human-approves"
        }
      ],
      "url": "https://the-ai-record.com/passages/coval-roster-brought-median-cost-per-review-2026",
      "json": "https://the-ai-record.com/api/v1/passages/coval-roster-brought-median-cost-per-review-2026.json"
    },
    {
      "id": "coval-configuration-catches-most-what-our-2026",
      "text": "The configuration that catches the most of what our human reviewers catch is also the cheapest one we have run, and most of its budget goes to models that would be dismissed on sight as too weak for code review—which, individually, they are.",
      "context": null,
      "speaker": "Dana Dzik",
      "speakerId": "dana-dzik",
      "speakerUrl": "https://the-ai-record.com/people/dana-dzik",
      "speakerLevel": "practitioner",
      "role": "Engineer, Coval (author of the Coval blog post on its code reviewer)",
      "voice": "person",
      "organization": "Coval",
      "organizationId": "coval",
      "organizationUrl": "https://the-ai-record.com/organizations/coval",
      "aiVendor": true,
      "work": {
        "title": "Notes on Building a Code Reviewer",
        "type": "post",
        "date": "2026-09-10",
        "publisher": "Coval blog",
        "locator": "Where it goes",
        "url": "https://www.coval.ai/blog/how-we-built-our-code-reviewer/"
      },
      "grade": "B",
      "gradeMeaning": "The organization's own post, paper or talk.",
      "verification": {
        "status": "verified",
        "meaning": "An independent second reader re-fetched the source and confirmed the wording.",
        "reviewedOn": "2026-11-07"
      },
      "topics": [
        "ai-review-cost",
        "ai-review-quality"
      ],
      "functions": [
        "engineering"
      ],
      "figures": [],
      "url": "https://the-ai-record.com/passages/coval-configuration-catches-most-what-our-2026",
      "json": "https://the-ai-record.com/api/v1/passages/coval-configuration-catches-most-what-our-2026.json"
    }
  ],
  "notice": [
    "Every passage is reproduced word for word from the cited source.",
    "Check the verification status: \"reported\" means not yet confirmed by an independent second reader.",
    "Organizations flagged aiVendor sell AI tools or services and have a reason to publish flattering numbers.",
    "An empty result means the archive holds nothing on it, not that nobody has said anything."
  ]
}