Viewing enriched Twitter post
The evals book is here. Hamel is the evals 🐐 and I’m lucky he wanted to write this book with me!! We are grateful for our reviewers, editors, illustrators and readers. Order it on Amazon; or come to our book signing to get a copy (link in replies).
{
"score": 0.34,
"score_components": {
"author": 0.09,
"engagement": 0.0,
"quality": 0.04000000000000001,
"source": 0.135,
"nlp": 0.05,
"recency": 0.025
},
"scored_at": "2026-10-27T19:02:16.120182",
"import_source": "api_import",
"source_tagged_at": "2026-10-27T19:02:16.120191",
"enriched": true,
"enriched_at": "2026-10-27T19:02:16.120193"
}{
"type": "tweet",
"id": "2115148262772715682",
"url": "https://x.com/sh_reya/status/2115148262772715682",
"twitterUrl": "https://twitter.com/sh_reya/status/2115148262772715682",
"text": "The evals book is here. Hamel is the evals 🐐 and I’m lucky he wanted to write this book with me!! We are grateful for our reviewers, editors, illustrators and readers. Order it on Amazon; or come to our book signing to get a copy (link in replies).",
"source": "",
"retweetCount": 2,
"replyCount": 6,
"likeCount": 22,
"quoteCount": 0,
"viewCount": 996,
"createdAt": "Tue Oct 27 18:26:58 +0000 2026",
"lang": "en",
"bookmarkCount": 12,
"isReply": false,
"inReplyToId": null,
"conversationId": "2115148262772715682",
"displayTextRange": [
0,
248
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "sh_reya",
"url": "https://x.com/sh_reya",
"twitterUrl": "https://twitter.com/sh_reya",
"id": "2286218053",
"name": "Shreya Shankar",
"isVerified": false,
"isBlueVerified": true,
"verifiedType": null,
"profilePicture": "https://pbs.twimg.com/profile_images/1342529111839944705/hzr44mb5_normal.jpg",
"coverPicture": "",
"description": "",
"location": "SF & Pittsburgh",
"followers": 59144,
"following": 822,
"status": "",
"canDm": true,
"canMediaTag": true,
"createdAt": "Sat Jan 11 06:46:16 +0000 2014",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 16600,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 433,
"statusesCount": 6227,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [
"2103207153821688056"
],
"profile_bio": {
"description": "Incoming assistant professor @CSDatCMU @CMUDB. Putting LLMs in databases and BI tools. Created https://t.co/PmuOqAXVgS and https://t.co/8MQt4na2cj.",
"entities": {
"description": {
"urls": [
{
"display_url": "docetl.org",
"expanded_url": "http://docetl.org",
"indices": [
95,
118
],
"url": "https://t.co/PmuOqAXVgS"
},
{
"display_url": "evals.info",
"expanded_url": "http://evals.info",
"indices": [
123,
146
],
"url": "https://t.co/8MQt4na2cj"
}
],
"user_mentions": [
{
"id_str": "",
"indices": [
29,
38
],
"name": "",
"screen_name": "CSDatCMU"
},
{
"id_str": "",
"indices": [
39,
45
],
"name": "",
"screen_name": "CMUDB"
}
]
},
"url": {
"urls": [
{
"display_url": "sh-reya.com",
"expanded_url": "http://www.sh-reya.com",
"indices": [
0,
23
],
"url": "https://t.co/j0wChgdtjx"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null,
"protected": false
},
"extendedEntities": {},
"card": null,
"place": {},
"entities": {},
"quoted_tweet": {
"type": "tweet",
"id": "2115139454268539260",
"url": "https://x.com/Dandiggastech/status/2115139454268539260",
"twitterUrl": "https://twitter.com/Dandiggastech/status/2115139454268539260",
"text": "I read the error analysis chapter of Evals for AI Engineers by @HamelHusain and @sh_reya and realised I already had the dataset.\n\nSome backstory. I work with coding agents all day: Claude Code, Codex, Hermes, Antigravity. Every session is a trace. What I typed, every tool call, what came back, what it said. Hundreds of them, sitting on disk, never read.\n\nThe chapter says: don't start with metrics. Read traces end to end. Mark the first step where it went wrong and write one short note in your own words. Yes or no verdict per trace, no scores out of 5. Only after 20 marked traces do you group them into failure types. And don't let a model invent the categories, it will hand you \"hallucination\" and miss the ones specific to your system.\n\nSo I built it into the dashboard I use to watch my agents. Last 14 days, up to 200 sessions per app, 431 when I took the screenshot. Each step has one button: mark this as the failure. Every mark lands in a Failures list with the note and a CSV download.\n\nThe first failure it found was in the list itself. 193 of the 200 newest Claude rows were \"Untitled\". My own usage check had been running every 10 minutes and left 1,893 throwaway sessions that pushed the real ones out. Filtered, 117 real sessions named. If the sample is wrong, the reading is wrong before it starts.\n\nFirst real mark: an agent said a metronome app was done before it had looked at it. A stop hook had to force the screenshot. No category yet. Just the note.\n\nThe agent's answer is not the data. The trace is the data.",
"source": "",
"retweetCount": 0,
"replyCount": 4,
"likeCount": 5,
"quoteCount": 1,
"viewCount": 980,
"createdAt": "Tue Oct 27 17:51:57 +0000 2026",
"lang": "en",
"bookmarkCount": 5,
"isReply": false,
"inReplyToId": null,
"conversationId": "2115139454268539260",
"displayTextRange": [
0,
278
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "Dandiggastech",
"url": "https://x.com/Dandiggastech",
"twitterUrl": "https://twitter.com/Dandiggastech",
"id": "2070972618371448832",
"name": "Daniel Adekugbe",
"isVerified": false,
"isBlueVerified": true,
"verifiedType": null,
"profilePicture": "https://pbs.twimg.com/profile_images/2070996119618777088/x7oRGA0s_normal.jpg",
"coverPicture": "",
"description": "",
"location": "",
"followers": 13,
"following": 94,
"status": "",
"canDm": false,
"canMediaTag": true,
"createdAt": "Sat Jun 27 20:49:19 +0000 2026",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 8,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 13,
"statusesCount": 147,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [
"2078701431716970942"
],
"profile_bio": {
"description": "Backend/platform engineer. Agent reliability + evals. I make agents prove their work.",
"entities": {
"description": {},
"url": {
"urls": [
{
"display_url": "linkedin.com/in/daniel-adek…",
"expanded_url": "https://www.linkedin.com/in/daniel-adekugbe-11a71859",
"indices": [
0,
23
],
"url": "https://t.co/WpWLUQiTXG"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null,
"protected": false
},
"extendedEntities": {
"media": [
{
"display_url": "pic.x.com/dJMAi5FCzW",
"expanded_url": "https://x.com/Dandiggastech/status/2115139454268539260/photo/1",
"ext_master_playlist_only": [],
"ext_media_availability": {
"status": "Available"
},
"ext_playlists": [],
"features": {
"large": {
"faces": []
},
"orig": {
"faces": []
}
},
"id_str": "2115139443124314112",
"indices": [
279,
302
],
"media_key": "3_2115139443124314112",
"media_results": {
"id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAAR1afB3116AACgACHVp8II4XAXwAAA==",
"result": {
"__typename": "ApiMedia",
"id": "QXBpTWVkaWE6DAABCgABHVp8HfXXoAAKAAIdWnwgjhcBfAAA",
"media_key": "3_2115139443124314112"
}
},
"media_url_https": "https://pbs.twimg.com/media/HVp8HfXXoAAclsc.jpg",
"original_info": {
"focus_rects": [
{
"h": 1344,
"w": 2400,
"x": 0,
"y": 0
},
{
"h": 1500,
"w": 1500,
"x": 270,
"y": 0
},
{
"h": 1500,
"w": 1316,
"x": 362,
"y": 0
},
{
"h": 1500,
"w": 750,
"x": 645,
"y": 0
},
{
"h": 1500,
"w": 2400,
"x": 0,
"y": 0
}
],
"height": 1500,
"width": 2400
},
"sizes": {
"large": {
"h": 1280,
"w": 2048
}
},
"type": "photo",
"url": "https://t.co/dJMAi5FCzW"
},
{
"display_url": "pic.x.com/dJMAi5FCzW",
"expanded_url": "https://x.com/Dandiggastech/status/2115139454268539260/photo/1",
"ext_master_playlist_only": [],
"ext_media_availability": {
"status": "Available"
},
"ext_playlists": [],
"features": {
"large": {
"faces": []
},
"orig": {
"faces": []
}
},
"id_str": "2115139447838683137",
"indices": [
279,
302
],
"media_key": "3_2115139447838683137",
"media_results": {
"id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAAR1afB8O1zABCgACHVp8II4XAXwAAA==",
"result": {
"__typename": "ApiMedia",
"id": "QXBpTWVkaWE6DAABCgABHVp8Hw7XMAEKAAIdWnwgjhcBfAAA",
"media_key": "3_2115139447838683137"
}
},
"media_url_https": "https://pbs.twimg.com/media/HVp8Hw7XMAEK2Jj.jpg",
"original_info": {
"focus_rects": [
{
"h": 1024,
"w": 1828,
"x": 0,
"y": 27
},
{
"h": 1828,
"w": 1828,
"x": 0,
"y": 0
},
{
"h": 2084,
"w": 1828,
"x": 0,
"y": 0
},
{
"h": 2400,
"w": 1200,
"x": 179,
"y": 0
},
{
"h": 2400,
"w": 1828,
"x": 0,
"y": 0
}
],
"height": 2400,
"width": 1828
},
"sizes": {
"large": {
"h": 2048,
"w": 1560
}
},
"type": "photo",
"url": "https://t.co/dJMAi5FCzW"
}
]
},
"card": null,
"place": {},
"entities": {
"hashtags": [],
"symbols": [],
"urls": [],
"user_mentions": [
{
"id_str": "825766640",
"indices": [
63,
75
],
"name": "Hamel Husain",
"screen_name": "HamelHusain"
},
{
"id_str": "2286218053",
"indices": [
80,
88
],
"name": "Shreya Shankar",
"screen_name": "sh_reya"
}
]
},
"quoted_tweet": null,
"retweeted_tweet": null,
"isLimitedReply": false,
"communityInfo": null,
"article": null
},
"retweeted_tweet": null,
"isLimitedReply": false,
"communityInfo": null,
"article": null
}