@HamelHusain
RT @sh_reya: we've been iterating a lot on how DocWriter internally represents a user's writing style! the naive approach is to dump all a…
🐦 Twitter Post Details
Viewing enriched Twitter post
📊 Media Metadata
{
"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": "2026-08-23T16:02:07.363170",
"import_source": "api_import",
"source_tagged_at": "2026-08-23T16:02:07.363180",
"enriched": true,
"enriched_at": "2026-08-23T16:02:07.363181"
}🔧 Raw API Response
{
"type": "tweet",
"id": "2091536667073229221",
"url": "https://x.com/HamelHusain/status/2091536667073229221",
"twitterUrl": "https://twitter.com/HamelHusain/status/2091536667073229221",
"text": "RT @sh_reya: we've been iterating a lot on how DocWriter internally represents a user's writing style!\n\nthe naive approach is to dump all a…",
"source": "Twitter for iPhone",
"retweetCount": 7,
"replyCount": 27,
"likeCount": 167,
"quoteCount": 2,
"viewCount": 13486,
"createdAt": "Sun Aug 23 14:42:54 +0000 2026",
"lang": "en",
"bookmarkCount": 180,
"isReply": false,
"inReplyToId": null,
"conversationId": "2091536667073229221",
"displayTextRange": [
0,
140
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "HamelHusain",
"url": "https://x.com/HamelHusain",
"twitterUrl": "https://twitter.com/HamelHusain",
"id": "825766640",
"name": "Hamel Husain",
"isVerified": false,
"isBlueVerified": true,
"verifiedType": null,
"profilePicture": "https://pbs.twimg.com/profile_images/1287206199088173057/ixE4fKy1_normal.jpg",
"coverPicture": "https://pbs.twimg.com/profile_banners/825766640/1758993452",
"description": "",
"location": "Looking at the data",
"followers": 53542,
"following": 2639,
"status": "",
"canDm": true,
"canMediaTag": false,
"createdAt": "Sat Sep 15 18:45:02 +0000 2012",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 18823,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 1626,
"statusesCount": 17267,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [
"2087679097468334120"
],
"profile_bio": {
"description": "Evals Evals Evals - https://t.co/Zrmp6LRd9c\n\nAbout Me: https://t.co/P6WyeKkyTa",
"entities": {
"description": {
"urls": [
{
"display_url": "evals.info",
"expanded_url": "http://evals.info",
"indices": [
21,
44
],
"url": "https://t.co/Zrmp6LRd9c"
},
{
"display_url": "hamel.dev",
"expanded_url": "https://hamel.dev",
"indices": [
56,
79
],
"url": "https://t.co/P6WyeKkyTa"
}
]
},
"url": {
"urls": [
{
"display_url": "evals.info",
"expanded_url": "http://evals.info",
"indices": [
0,
23
],
"url": "https://t.co/Zrmp6LRd9c"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {},
"card": null,
"place": {},
"entities": {
"user_mentions": [
{
"id_str": "2286218053",
"indices": [
3,
11
],
"name": "Shreya Shankar",
"screen_name": "sh_reya"
}
]
},
"quoted_tweet": null,
"retweeted_tweet": {
"type": "tweet",
"id": "2091273234851549617",
"url": "https://x.com/sh_reya/status/2091273234851549617",
"twitterUrl": "https://twitter.com/sh_reya/status/2091273234851549617",
"text": "we've been iterating a lot on how DocWriter internally represents a user's writing style!\n\nthe naive approach is to dump all a user's prior writing in context and pray the AI figures out how to sound like them. this doesn't really work. and the user can't just manually specify their style either, because nobody knows what their meaningful writing preferences (for an AI agent) actually are.\n\nso we've built a multi-agent pipeline that runs lexical, grammatical, and discourse analyses on the user's writing, extracts specific patterns with evidence, and then surfaces them in a UI where the user can confirm or reject each pattern by comparing two passages side by side\n\nTBD on how well it performs in our next round of user studies 😆 it feels like we are really trying to do anything possible to avoid fine-tuning, but perhaps we need to bite the bullet eventually",
"source": "Twitter for iPhone",
"retweetCount": 7,
"replyCount": 27,
"likeCount": 167,
"quoteCount": 2,
"viewCount": 13486,
"createdAt": "Sat Aug 22 21:16:07 +0000 2026",
"lang": "en",
"bookmarkCount": 180,
"isReply": false,
"inReplyToId": null,
"conversationId": "2091273234851549617",
"displayTextRange": [
0,
277
],
"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": "Berkeley, CA",
"followers": 54844,
"following": 791,
"status": "",
"canDm": true,
"canMediaTag": true,
"createdAt": "Sat Jan 11 06:46:16 +0000 2014",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 16089,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 422,
"statusesCount": 5983,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [
"2054246871250653479"
],
"profile_bio": {
"description": "Incoming asst. prof @CSDatCMU @CMUDB. I build user-centered data & AI systems. Created https://t.co/PmuOqAYt6q and https://t.co/8MQt4naA1R. PhD @Berkeley_EECS; undergrad @Stanford CS.",
"entities": {
"description": {
"urls": [
{
"display_url": "docetl.org",
"expanded_url": "http://docetl.org",
"indices": [
87,
110
],
"url": "https://t.co/PmuOqAYt6q"
},
{
"display_url": "evals.info",
"expanded_url": "http://evals.info",
"indices": [
115,
138
],
"url": "https://t.co/8MQt4naA1R"
}
],
"user_mentions": [
{
"id_str": "",
"indices": [
20,
29
],
"name": "",
"screen_name": "CSDatCMU"
},
{
"id_str": "",
"indices": [
30,
36
],
"name": "",
"screen_name": "CMUDB"
},
{
"id_str": "",
"indices": [
144,
158
],
"name": "",
"screen_name": "Berkeley_EECS"
},
{
"id_str": "",
"indices": [
170,
179
],
"name": "",
"screen_name": "Stanford"
}
]
},
"url": {
"urls": [
{
"display_url": "sh-reya.com",
"expanded_url": "http://www.sh-reya.com",
"indices": [
0,
23
],
"url": "https://t.co/j0wChge195"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {
"media": [
{
"allow_download_status": {
"allow_download": true
},
"display_url": "pic.x.com/981aTeWSpH",
"expanded_url": "https://x.com/sh_reya/status/2091273234851549617/photo/1",
"ext_master_playlist_only": [],
"ext_media_availability": {
"status": "Available"
},
"ext_playlists": [],
"features": {
"large": {
"faces": []
},
"orig": {
"faces": []
}
},
"id_str": "2091269534036692992",
"indices": [
278,
301
],
"media_key": "3_2091269534036692992",
"media_results": {
"id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAAR0Fro+p2pAACgACHQWx7VOb0bEAAA==",
"result": {
"__typename": "ApiMedia",
"id": "QXBpTWVkaWE6DAABCgABHQWuj6nakAAKAAIdBbHtU5vRsQAA",
"media_key": "3_2091269534036692992"
}
},
"media_url_https": "https://pbs.twimg.com/media/HQWuj6nakAACJnY.jpg",
"original_info": {
"focus_rects": [
{
"h": 1915,
"w": 3420,
"x": 0,
"y": 0
},
{
"h": 1964,
"w": 1964,
"x": 728,
"y": 0
},
{
"h": 1964,
"w": 1723,
"x": 849,
"y": 0
},
{
"h": 1964,
"w": 982,
"x": 1219,
"y": 0
},
{
"h": 1964,
"w": 3420,
"x": 0,
"y": 0
}
],
"height": 1964,
"width": 3420
},
"sizes": {
"large": {
"h": 1176,
"w": 2048
}
},
"type": "photo",
"url": "https://t.co/981aTeWSpH"
}
]
},
"card": null,
"place": {},
"entities": {
"hashtags": [],
"symbols": [],
"urls": [],
"user_mentions": []
},
"quoted_tweet": null,
"retweeted_tweet": null,
"isLimitedReply": false,
"communityInfo": null,
"article": null
},
"isLimitedReply": false,
"communityInfo": null,
"article": null
}