🐦 Twitter Post Details

Viewing enriched Twitter post

@PawelHuryn

I got permission to publish a new AI Evals FAQ (Sep, 2025). It’s massive. And it's a goldmine for engineers and AI PMs. @HamelHusain and @sh_reya run the world’s No. 1 AI Evals course. Together with top AI architects and ML researchers, they answer the most common questions from 1,500+ students. 51 pages of unique insights and resources. And 100% free. Some of the questions: Q: What are LLM Evals? Q: What’s a minimum viable evaluation setup? Q: Why is "error analysis" so important in LLM evals, and how is it performed? Q: What is the best approach for generating synthetic data? Q: Are there scenarios where synthetic data may not be reliable? Q: Why do you recommend binary (pass/fail) evaluations? Q: Should I use "ready-to-use" evaluation metrics? Q: How many people should annotate my LLM outputs? Q: Should PMs and engineers collaborate on error analysis? How? Q: What parts of evals can be automated with LLMs? Q: Should I stop writing prompts manually in favor of automated tools? Q: What makes a good custom interface for reviewing LLM outputs? Q: What gaps in eval tooling should I be prepared to fill myself? Q: How should I version and manage prompts? Q: How are evaluations used differently in CI/CD vs. monitoring production? Q: What’s the difference between guardrails & evaluators? Q: Is RAG dead? Q: How should I approach evaluating my RAG system? Q: How do I evaluate sessions with human handoffs? Q: How do I evaluate complex multi-step workflows? Q: How do I evaluate agentic workflows? Get a full PDF (Google Drive, 51 pages): https://t.co/4azaPGfIxr Hope that helps! Feel free to share it with your network. — P.S. The guys shared a crazy amount of knowledge for free. But if you want to dive even deeper, here's a 35% discount for the AI Evals Cohort: https://t.co/MtnOgX99i9 (The next cohort: Oct 6—Nov 1, 2025)

Media 1
Media 2
Media 3
Media 4
View on Twitter

📊 Media Metadata

{
  "media": [
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1968057373831897459/media_0.jpg?",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1968057373831897459/media_0.jpg?",
      "type": "photo",
      "filename": "media_0.jpg"
    },
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1968057373831897459/media_1.jpg?",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1968057373831897459/media_1.jpg?",
      "type": "photo",
      "filename": "media_1.jpg"
    },
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1968057373831897459/media_2.jpg?",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1968057373831897459/media_2.jpg?",
      "type": "photo",
      "filename": "media_2.jpg"
    },
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1968057373831897459/media_3.jpg?",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1968057373831897459/media_3.jpg?",
      "type": "photo",
      "filename": "media_3.jpg"
    }
  ],
  "processed_at": "2025-09-18T14:23:49.044764",
  "pipeline_version": "2.0"
}

🔧 Raw API Response

{
  "type": "tweet",
  "id": "1968057373831897459",
  "url": "https://x.com/PawelHuryn/status/1968057373831897459",
  "twitterUrl": "https://twitter.com/PawelHuryn/status/1968057373831897459",
  "text": "I got permission to publish a new AI Evals FAQ (Sep, 2025).\n\nIt’s massive. And it's a goldmine for engineers and AI PMs.\n\n@HamelHusain and @sh_reya run the world’s No. 1 AI Evals course.\n\nTogether with top AI architects and ML researchers, they answer the most common questions from 1,500+ students.\n\n51 pages of unique insights and resources. \nAnd 100% free.\n\nSome of the questions:\n\nQ: What are LLM Evals?\n\nQ: What’s a minimum viable evaluation setup?\n\nQ: Why is \"error analysis\" so important in LLM evals, and how is it performed?\n\nQ: What is the best approach for generating synthetic data?\n\nQ: Are there scenarios where synthetic data may not be reliable?\n\nQ: Why do you recommend binary (pass/fail) evaluations?\n\nQ: Should I use \"ready-to-use\" evaluation metrics?\n\nQ: How many people should annotate my LLM outputs?\n\nQ: Should PMs and engineers collaborate on error analysis? How?\n\nQ: What parts of evals can be automated with LLMs?\n\nQ: Should I stop writing prompts manually in favor of automated tools?\n\nQ: What makes a good custom interface for reviewing LLM outputs?\n\nQ: What gaps in eval tooling should I be prepared to fill myself?\n\nQ: How should I version and manage prompts?\n\nQ: How are evaluations used differently in CI/CD vs. monitoring production?\n\nQ: What’s the difference between guardrails & evaluators?\n\nQ: Is RAG dead?\n\nQ: How should I approach evaluating my RAG system?\n\nQ: How do I evaluate sessions with human handoffs?\n\nQ: How do I evaluate complex multi-step workflows?\n\nQ: How do I evaluate agentic workflows?\n\nGet a full PDF (Google Drive, 51 pages): https://t.co/4azaPGfIxr\n\nHope that helps!\n\nFeel free to share it with your network.\n\n—\n\nP.S. The guys shared a crazy amount of knowledge for free. But if you want to dive even deeper, here's a 35% discount for the AI Evals Cohort: https://t.co/MtnOgX99i9\n\n(The next cohort: Oct 6—Nov 1, 2025)",
  "source": "Twitter for iPhone",
  "retweetCount": 24,
  "replyCount": 3,
  "likeCount": 190,
  "quoteCount": 2,
  "viewCount": 16802,
  "createdAt": "Tue Sep 16 21:00:17 +0000 2025",
  "lang": "en",
  "bookmarkCount": 335,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "1968057373831897459",
  "displayTextRange": [
    0,
    278
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "PawelHuryn",
    "url": "https://x.com/PawelHuryn",
    "twitterUrl": "https://twitter.com/PawelHuryn",
    "id": "1459767830623178755",
    "name": "Paweł Huryn",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/1797200367500787712/zo1WQz0D_normal.jpg",
    "coverPicture": "https://pbs.twimg.com/profile_banners/1459767830623178755/1748026888",
    "description": "",
    "location": "Newsletter: Join 110K+ PMs →",
    "followers": 27809,
    "following": 310,
    "status": "",
    "canDm": true,
    "canMediaTag": true,
    "createdAt": "Sun Nov 14 06:19:25 +0000 2021",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 2984,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 1376,
    "statusesCount": 5706,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [],
    "profile_bio": {
      "description": "AI & Product Management | Founder, Author @ The Product Compass Newsletter | Join 115,000+ PMs: https://t.co/WYKbT0gY7S",
      "entities": {
        "description": {
          "urls": [
            {
              "display_url": "productcompass.pm",
              "expanded_url": "http://www.productcompass.pm",
              "indices": [
                96,
                119
              ],
              "url": "https://t.co/WYKbT0gY7S"
            }
          ]
        },
        "url": {
          "urls": [
            {
              "display_url": "productcompass.pm",
              "expanded_url": "https://www.productcompass.pm/",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/B9jpTdKDGa"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {
    "media": [
      {
        "allow_download_status": {
          "allow_download": true
        },
        "display_url": "pic.twitter.com/FRv9oE3dos",
        "expanded_url": "https://twitter.com/PawelHuryn/status/1968057373831897459/photo/1",
        "ext_media_availability": {
          "status": "Available"
        },
        "features": {
          "large": {
            "faces": [
              {
                "h": 34,
                "w": 34,
                "x": 115,
                "y": 208
              }
            ]
          },
          "orig": {
            "faces": [
              {
                "h": 34,
                "w": 34,
                "x": 115,
                "y": 208
              }
            ]
          }
        },
        "id_str": "1968056366943145984",
        "indices": [
          279,
          302
        ],
        "media_key": "3_1968056366943145984",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARtP8Napl5AACgACG0/xwRjWoXMAAA==",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAABCgABG0/w1qmXkAAKAAIbT/HBGNahcwAA",
            "media_key": "3_1968056366943145984"
          }
        },
        "media_url_https": "https://pbs.twimg.com/media/G0_w1qmXkAAZyhZ.jpg",
        "original_info": {
          "focus_rects": [
            {
              "h": 463,
              "w": 827,
              "x": 0,
              "y": 0
            },
            {
              "h": 827,
              "w": 827,
              "x": 0,
              "y": 0
            },
            {
              "h": 943,
              "w": 827,
              "x": 0,
              "y": 0
            },
            {
              "h": 1075,
              "w": 538,
              "x": 134,
              "y": 0
            },
            {
              "h": 1075,
              "w": 827,
              "x": 0,
              "y": 0
            }
          ],
          "height": 1075,
          "width": 827
        },
        "sizes": {
          "large": {
            "h": 1075,
            "w": 827
          }
        },
        "type": "photo",
        "url": "https://t.co/FRv9oE3dos"
      },
      {
        "allow_download_status": {
          "allow_download": true
        },
        "display_url": "pic.twitter.com/FRv9oE3dos",
        "expanded_url": "https://twitter.com/PawelHuryn/status/1968057373831897459/photo/1",
        "ext_media_availability": {
          "status": "Available"
        },
        "features": {
          "large": {},
          "orig": {}
        },
        "id_str": "1968056378246782976",
        "indices": [
          279,
          302
        ],
        "media_key": "3_1968056378246782976",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARtP8NlLV2AACgACG0/xwRjWoXMAAA==",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAABCgABG0/w2UtXYAAKAAIbT/HBGNahcwAA",
            "media_key": "3_1968056378246782976"
          }
        },
        "media_url_https": "https://pbs.twimg.com/media/G0_w2UtXYAAFWAG.png",
        "original_info": {
          "focus_rects": [
            {
              "h": 462,
              "w": 825,
              "x": 0,
              "y": 10
            },
            {
              "h": 825,
              "w": 825,
              "x": 0,
              "y": 0
            },
            {
              "h": 941,
              "w": 825,
              "x": 0,
              "y": 0
            },
            {
              "h": 1075,
              "w": 538,
              "x": 287,
              "y": 0
            },
            {
              "h": 1075,
              "w": 825,
              "x": 0,
              "y": 0
            }
          ],
          "height": 1075,
          "width": 825
        },
        "sizes": {
          "large": {
            "h": 1075,
            "w": 825
          }
        },
        "type": "photo",
        "url": "https://t.co/FRv9oE3dos"
      },
      {
        "allow_download_status": {
          "allow_download": true
        },
        "display_url": "pic.twitter.com/FRv9oE3dos",
        "expanded_url": "https://twitter.com/PawelHuryn/status/1968057373831897459/photo/1",
        "ext_media_availability": {
          "status": "Available"
        },
        "features": {
          "large": {},
          "orig": {}
        },
        "id_str": "1968056393832734720",
        "indices": [
          279,
          302
        ],
        "media_key": "3_1968056393832734720",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARtP8NzsViAACgACG0/xwRjWoXMAAA==",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAABCgABG0/w3OxWIAAKAAIbT/HBGNahcwAA",
            "media_key": "3_1968056393832734720"
          }
        },
        "media_url_https": "https://pbs.twimg.com/media/G0_w3OxWIAAmJV0.jpg",
        "original_info": {
          "focus_rects": [
            {
              "h": 463,
              "w": 827,
              "x": 0,
              "y": 333
            },
            {
              "h": 827,
              "w": 827,
              "x": 0,
              "y": 151
            },
            {
              "h": 943,
              "w": 827,
              "x": 0,
              "y": 93
            },
            {
              "h": 1075,
              "w": 538,
              "x": 0,
              "y": 0
            },
            {
              "h": 1075,
              "w": 827,
              "x": 0,
              "y": 0
            }
          ],
          "height": 1075,
          "width": 827
        },
        "sizes": {
          "large": {
            "h": 1075,
            "w": 827
          }
        },
        "type": "photo",
        "url": "https://t.co/FRv9oE3dos"
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {
    "urls": [
      {
        "display_url": "drive.google.com/file/d/1y447t7…",
        "expanded_url": "https://drive.google.com/file/d/1y447t7zN1m11ObIvNNo7mVdWCjAicoyQ/view?usp=sharing",
        "indices": [
          1581,
          1604
        ],
        "url": "https://t.co/4azaPGfIxr"
      },
      {
        "display_url": "bit.ly/aievals35",
        "expanded_url": "https://bit.ly/aievals35",
        "indices": [
          1812,
          1835
        ],
        "url": "https://t.co/MtnOgX99i9"
      }
    ],
    "user_mentions": [
      {
        "id_str": "825766640",
        "indices": [
          122,
          134
        ],
        "name": "Hamel Husain",
        "screen_name": "HamelHusain"
      },
      {
        "id_str": "2286218053",
        "indices": [
          139,
          147
        ],
        "name": "Shreya Shankar",
        "screen_name": "sh_reya"
      }
    ]
  },
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "article": null
}