Viewing enriched Twitter post
I’m excited to release a post which outlines a reference architecture for building agents over your documents 🤖📑 (we call it Agentic Document Workflows) A lot of knowledge work is dominated by PDFs, PowerPoints, Excel. “Basic RAG over your docs” doesn’t capture the full… https://t.co/azFKclHwRt
{
"media": [
{
"type": "image",
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1915109277498585569/media_0.jpg?",
"filename": "media_0.jpg"
}
],
"nlp": {
"sentiment": "positive",
"topics": [
"reference architecture",
"document workflows",
"knowledge work"
],
"entities": [],
"summary": "The tweet expresses excitement about releasing a post on a reference architecture for building agents over documents.",
"language": "en",
"processed_at": "2025-08-07T12:19:58.356123"
}
}{
"data": {
"threaded_conversation_with_injections_v2": {
"instructions": [
{
"type": "TimelineClearCache"
},
{
"type": "TimelineAddEntries",
"entries": [
{
"entryId": "tweet-1915109277498585569",
"sortIndex": "1953521498761199616",
"content": {
"entryType": "TimelineTimelineItem",
"__typename": "TimelineTimelineItem",
"itemContent": {
"itemType": "TimelineTweet",
"__typename": "TimelineTweet",
"tweet_results": {
"result": {
"__typename": "Tweet",
"rest_id": "1915109277498585569",
"has_birdwatch_notes": false,
"core": {
"user_results": {
"result": {
"__typename": "User",
"id": "VXNlcjozNjk3Nzc0MTY=",
"rest_id": "369777416",
"affiliates_highlighted_label": {},
"has_graduated_access": true,
"is_blue_verified": true,
"profile_image_shape": "Circle",
"legacy": {
"can_dm": true,
"can_media_tag": true,
"created_at": "Wed Sep 07 22:54:31 +0000 2011",
"default_profile": true,
"default_profile_image": false,
"description": "co-founder/CEO @llama_index\n\nCareers: https://t.co/EUnMNmbCtx\nEnterprise: https://t.co/Ht5jwxSrQB",
"entities": {
"description": {
"urls": [
{
"display_url": "llamaindex.ai/careers",
"expanded_url": "https://www.llamaindex.ai/careers",
"url": "https://t.co/EUnMNmbCtx",
"indices": [
38,
61
]
},
{
"display_url": "llamaindex.ai/contact",
"expanded_url": "https://www.llamaindex.ai/contact",
"url": "https://t.co/Ht5jwxSrQB",
"indices": [
74,
97
]
}
]
},
"url": {
"urls": [
{
"display_url": "llamaindex.ai",
"expanded_url": "https://www.llamaindex.ai/",
"url": "https://t.co/YiIfjVlzb6",
"indices": [
0,
23
]
}
]
}
},
"fast_followers_count": 0,
"favourites_count": 7776,
"followers_count": 64138,
"friends_count": 1378,
"has_custom_timelines": true,
"is_translator": false,
"listed_count": 1295,
"location": "",
"media_count": 1244,
"name": "Jerry Liu",
"normal_followers_count": 64138,
"pinned_tweet_ids_str": [
"1953108641558540720"
],
"possibly_sensitive": false,
"profile_image_url_https": "https://pbs.twimg.com/profile_images/1283610285031460864/1Q4zYhtb_normal.jpg",
"profile_interstitial_type": "",
"screen_name": "jerryjliu0",
"statuses_count": 6037,
"translator_type": "none",
"url": "https://t.co/YiIfjVlzb6",
"verified": false,
"want_retweets": false,
"withheld_in_countries": []
},
"tipjar_settings": {}
}
}
},
"unmention_data": {},
"edit_control": {
"edit_tweet_ids": [
"1915109277498585569"
],
"editable_until_msecs": "1745436207000",
"is_edit_eligible": true,
"edits_remaining": "5"
},
"is_translatable": false,
"views": {
"count": "15126",
"state": "EnabledWithCount"
},
"source": "<a href=\"https://mobile.twitter.com\" rel=\"nofollow\">Twitter Web App</a>",
"note_tweet": {
"is_expandable": true,
"note_tweet_results": {
"result": {
"id": "Tm90ZVR3ZWV0OjE5MTUxMDkyNzcyOTcyMDkzNDQ=",
"text": "I’m excited to release a post which outlines a reference architecture for building agents over your documents 🤖📑 (we call it Agentic Document Workflows)\n\nA lot of knowledge work is dominated by PDFs, PowerPoints, Excel. “Basic RAG over your docs” doesn’t capture the full potential of agents, which can handle e2e processes.\n\nThe reference architecture for ADW has four stages:\n1) parsing and extraction\n2) retrieval - matching against relevant additional context\n3) reasoning - multi-step logic over tools\n4) action-taking\n\nA LOT of use cases fall into this pattern, ranging from due diligence to contract analysis.\n\nTo implement this architecture, you need both a data layer and agent orchestration - this is well served by LlamaCloud and our open-source framework respectively.\n\nLlamaCloud: https://t.co/XYZmx5TFz8\nWe have a full repo of examples here: https://t.co/4RFrqz1RlH\nMore LlamaCloud examples: https://t.co/lXRAGhljFl",
"entity_set": {
"hashtags": [],
"symbols": [],
"urls": [
{
"display_url": "cloud.llamaindex.ai",
"expanded_url": "https://cloud.llamaindex.ai/",
"url": "https://t.co/XYZmx5TFz8",
"indices": [
794,
817
]
},
{
"display_url": "github.com/run-llama/llam…",
"expanded_url": "https://github.com/run-llama/llama_cloud_services",
"url": "https://t.co/4RFrqz1RlH",
"indices": [
856,
879
]
},
{
"display_url": "github.com/run-llama/llam…",
"expanded_url": "https://github.com/run-llama/llamacloud-demo",
"url": "https://t.co/lXRAGhljFl",
"indices": [
906,
929
]
}
],
"user_mentions": []
},
"richtext": {
"richtext_tags": []
},
"media": {
"inline_media": []
}
}
}
},
"quoted_status_result": {
"result": {
"__typename": "Tweet",
"rest_id": "1915098378880602555",
"has_birdwatch_notes": false,
"core": {
"user_results": {
"result": {
"__typename": "User",
"id": "VXNlcjoxNjA0Mjc4MzU4Mjk2MDU1ODA4",
"rest_id": "1604278358296055808",
"affiliates_highlighted_label": {},
"has_graduated_access": true,
"is_blue_verified": true,
"profile_image_shape": "Circle",
"legacy": {
"can_dm": false,
"can_media_tag": true,
"created_at": "Sun Dec 18 00:52:44 +0000 2022",
"default_profile": true,
"default_profile_image": false,
"description": "Build AI agents over your documents\n\nGithub: https://t.co/HC19j7vMwc\nDocs: https://t.co/QInqg2zksh\nLlamaCloud: https://t.co/yQGTiRSNvj",
"entities": {
"description": {
"urls": [
{
"display_url": "github.com/run-llama/llam…",
"expanded_url": "http://github.com/run-llama/llama_index",
"url": "https://t.co/HC19j7vMwc",
"indices": [
45,
68
]
},
{
"display_url": "docs.llamaindex.ai",
"expanded_url": "http://docs.llamaindex.ai",
"url": "https://t.co/QInqg2zksh",
"indices": [
75,
98
]
},
{
"display_url": "cloud.llamaindex.ai",
"expanded_url": "https://cloud.llamaindex.ai/",
"url": "https://t.co/yQGTiRSNvj",
"indices": [
111,
134
]
}
]
},
"url": {
"urls": [
{
"display_url": "llamaindex.ai",
"expanded_url": "https://www.llamaindex.ai/",
"url": "https://t.co/epzefqQqZx",
"indices": [
0,
23
]
}
]
}
},
"fast_followers_count": 0,
"favourites_count": 1425,
"followers_count": 99665,
"friends_count": 28,
"has_custom_timelines": false,
"is_translator": false,
"listed_count": 1571,
"location": "",
"media_count": 1676,
"name": "LlamaIndex 🦙",
"normal_followers_count": 99665,
"pinned_tweet_ids_str": [
"1950285220663742516"
],
"possibly_sensitive": false,
"profile_banner_url": "https://pbs.twimg.com/profile_banners/1604278358296055808/1752258343",
"profile_image_url_https": "https://pbs.twimg.com/profile_images/1623505166996742144/n-PNQGgd_normal.jpg",
"profile_interstitial_type": "",
"screen_name": "llama_index",
"statuses_count": 3500,
"translator_type": "none",
"url": "https://t.co/epzefqQqZx",
"verified": false,
"want_retweets": false,
"withheld_in_countries": []
},
"tipjar_settings": {}
}
}
},
"unmention_data": {},
"edit_control": {
"edit_tweet_ids": [
"1915098378880602555"
],
"editable_until_msecs": "1745433608000",
"is_edit_eligible": true,
"edits_remaining": "5"
},
"is_translatable": false,
"views": {
"count": "18708",
"state": "EnabledWithCount"
},
"source": "<a href=\"https://crossposter.llamaindex.ai\" rel=\"nofollow\">LlamaIndex CrossPoster</a>",
"note_tweet": {
"is_expandable": true,
"note_tweet_results": {
"result": {
"id": "Tm90ZVR3ZWV0OjE5MTUwOTgzNzg2NDk5NzI3Mzc=",
"text": "How do you build an Agentic Document Workflow (ADW), and when does it make sense to do so?\n\nADW is the logical next step beyond the RAG chatbot everybody builds as a prototype. ADW scales better, integrates with your existing software ecosystem, and provides better error handling and human oversight. But how do you actually build one?\n\nIn this post we go into:\n➡️ The 4 stages of an ADW workflow\n➡️ The essential elements of an ADW stack\n➡️ A real-world case study of an ADW implementation\n➡️ Reference implementations of several ADW use-cases\n\nNot every problem requires ADW, so we've also examined how to calculate the ROI of an ADW implementation.\n\nRead it all in our in-depth guide:\nhttps://t.co/wYn0z86goY",
"entity_set": {
"hashtags": [],
"symbols": [],
"urls": [
{
"display_url": "llamaindex.ai/blog/beyond-ch…",
"expanded_url": "https://www.llamaindex.ai/blog/beyond-chatbots-adopting-agentic-document-workflows-for-enterprises",
"url": "https://t.co/wYn0z86goY",
"indices": [
689,
712
]
}
],
"user_mentions": []
}
}
}
},
"legacy": {
"bookmark_count": 33,
"bookmarked": false,
"created_at": "Wed Apr 23 17:40:08 +0000 2025",
"conversation_id_str": "1915098378880602555",
"display_text_range": [
0,
281
],
"entities": {
"hashtags": [],
"media": [
{
"display_url": "pic.x.com/ZZzr7scHhF",
"expanded_url": "https://x.com/llama_index/status/1915098378880602555/photo/1",
"id_str": "1915098375852335104",
"indices": [
282,
305
],
"media_key": "3_1915098375852335104",
"media_url_https": "https://pbs.twimg.com/media/GpPL04KbIAAMVtg.jpg",
"type": "photo",
"url": "https://t.co/ZZzr7scHhF",
"ext_media_availability": {
"status": "Available"
},
"features": {
"large": {
"faces": []
},
"medium": {
"faces": []
},
"small": {
"faces": []
},
"orig": {
"faces": []
}
},
"sizes": {
"large": {
"h": 631,
"w": 1263,
"resize": "fit"
},
"medium": {
"h": 600,
"w": 1200,
"resize": "fit"
},
"small": {
"h": 340,
"w": 680,
"resize": "fit"
},
"thumb": {
"h": 150,
"w": 150,
"resize": "crop"
}
},
"original_info": {
"height": 631,
"width": 1263,
"focus_rects": [
{
"x": 0,
"y": 0,
"w": 1127,
"h": 631
},
{
"x": 0,
"y": 0,
"w": 631,
"h": 631
},
{
"x": 0,
"y": 0,
"w": 554,
"h": 631
},
{
"x": 0,
"y": 0,
"w": 316,
"h": 631
},
{
"x": 0,
"y": 0,
"w": 1263,
"h": 631
}
]
},
"media_results": {
"result": {
"media_key": "3_1915098375852335104"
}
}
}
],
"symbols": [],
"timestamps": [],
"urls": [],
"user_mentions": []
},
"extended_entities": {
"media": [
{
"display_url": "pic.x.com/ZZzr7scHhF",
"expanded_url": "https://x.com/llama_index/status/1915098378880602555/photo/1",
"id_str": "1915098375852335104",
"indices": [
282,
305
],
"media_key": "3_1915098375852335104",
"media_url_https": "https://pbs.twimg.com/media/GpPL04KbIAAMVtg.jpg",
"type": "photo",
"url": "https://t.co/ZZzr7scHhF",
"ext_media_availability": {
"status": "Available"
},
"features": {
"large": {
"faces": []
},
"medium": {
"faces": []
},
"small": {
"faces": []
},
"orig": {
"faces": []
}
},
"sizes": {
"large": {
"h": 631,
"w": 1263,
"resize": "fit"
},
"medium": {
"h": 600,
"w": 1200,
"resize": "fit"
},
"small": {
"h": 340,
"w": 680,
"resize": "fit"
},
"thumb": {
"h": 150,
"w": 150,
"resize": "crop"
}
},
"original_info": {
"height": 631,
"width": 1263,
"focus_rects": [
{
"x": 0,
"y": 0,
"w": 1127,
"h": 631
},
{
"x": 0,
"y": 0,
"w": 631,
"h": 631
},
{
"x": 0,
"y": 0,
"w": 554,
"h": 631
},
{
"x": 0,
"y": 0,
"w": 316,
"h": 631
},
{
"x": 0,
"y": 0,
"w": 1263,
"h": 631
}
]
},
"media_results": {
"result": {
"media_key": "3_1915098375852335104"
}
}
}
]
},
"favorite_count": 31,
"favorited": false,
"full_text": "How do you build an Agentic Document Workflow (ADW), and when does it make sense to do so?\n\nADW is the logical next step beyond the RAG chatbot everybody builds as a prototype. ADW scales better, integrates with your existing software ecosystem, and provides better error handling… https://t.co/ZZzr7scHhF",
"is_quote_status": false,
"lang": "en",
"possibly_sensitive": false,
"possibly_sensitive_editable": true,
"quote_count": 1,
"reply_count": 0,
"retweet_count": 6,
"retweeted": false,
"user_id_str": "1604278358296055808",
"id_str": "1915098378880602555"
}
}
},
"legacy": {
"bookmark_count": 198,
"bookmarked": false,
"created_at": "Wed Apr 23 18:23:27 +0000 2025",
"conversation_id_str": "1915109277498585569",
"display_text_range": [
0,
272
],
"entities": {
"hashtags": [],
"media": [
{
"display_url": "pic.x.com/azFKclHwRt",
"expanded_url": "https://x.com/jerryjliu0/status/1915109277498585569/photo/1",
"id_str": "1915109241712762880",
"indices": [
273,
296
],
"media_key": "3_1915109241712762880",
"media_url_https": "https://pbs.twimg.com/media/GpPVtWpbYAAijdD.jpg",
"type": "photo",
"url": "https://t.co/azFKclHwRt",
"ext_media_availability": {
"status": "Available"
},
"features": {
"large": {
"faces": []
},
"medium": {
"faces": []
},
"small": {
"faces": []
},
"orig": {
"faces": []
}
},
"sizes": {
"large": {
"h": 631,
"w": 1263,
"resize": "fit"
},
"medium": {
"h": 600,
"w": 1200,
"resize": "fit"
},
"small": {
"h": 340,
"w": 680,
"resize": "fit"
},
"thumb": {
"h": 150,
"w": 150,
"resize": "crop"
}
},
"original_info": {
"height": 631,
"width": 1263,
"focus_rects": [
{
"x": 0,
"y": 0,
"w": 1127,
"h": 631
},
{
"x": 0,
"y": 0,
"w": 631,
"h": 631
},
{
"x": 0,
"y": 0,
"w": 554,
"h": 631
},
{
"x": 0,
"y": 0,
"w": 316,
"h": 631
},
{
"x": 0,
"y": 0,
"w": 1263,
"h": 631
}
]
},
"media_results": {
"result": {
"media_key": "3_1915109241712762880"
}
}
}
],
"symbols": [],
"timestamps": [],
"urls": [],
"user_mentions": []
},
"extended_entities": {
"media": [
{
"display_url": "pic.x.com/azFKclHwRt",
"expanded_url": "https://x.com/jerryjliu0/status/1915109277498585569/photo/1",
"id_str": "1915109241712762880",
"indices": [
273,
296
],
"media_key": "3_1915109241712762880",
"media_url_https": "https://pbs.twimg.com/media/GpPVtWpbYAAijdD.jpg",
"type": "photo",
"url": "https://t.co/azFKclHwRt",
"ext_media_availability": {
"status": "Available"
},
"features": {
"large": {
"faces": []
},
"medium": {
"faces": []
},
"small": {
"faces": []
},
"orig": {
"faces": []
}
},
"sizes": {
"large": {
"h": 631,
"w": 1263,
"resize": "fit"
},
"medium": {
"h": 600,
"w": 1200,
"resize": "fit"
},
"small": {
"h": 340,
"w": 680,
"resize": "fit"
},
"thumb": {
"h": 150,
"w": 150,
"resize": "crop"
}
},
"original_info": {
"height": 631,
"width": 1263,
"focus_rects": [
{
"x": 0,
"y": 0,
"w": 1127,
"h": 631
},
{
"x": 0,
"y": 0,
"w": 631,
"h": 631
},
{
"x": 0,
"y": 0,
"w": 554,
"h": 631
},
{
"x": 0,
"y": 0,
"w": 316,
"h": 631
},
{
"x": 0,
"y": 0,
"w": 1263,
"h": 631
}
]
},
"media_results": {
"result": {
"media_key": "3_1915109241712762880"
}
}
}
]
},
"favorite_count": 139,
"favorited": false,
"full_text": "I’m excited to release a post which outlines a reference architecture for building agents over your documents 🤖📑 (we call it Agentic Document Workflows)\n\nA lot of knowledge work is dominated by PDFs, PowerPoints, Excel. “Basic RAG over your docs” doesn’t capture the full… https://t.co/azFKclHwRt",
"is_quote_status": true,
"lang": "en",
"possibly_sensitive": false,
"possibly_sensitive_editable": true,
"quote_count": 0,
"quoted_status_id_str": "1915098378880602555",
"quoted_status_permalink": {
"url": "https://t.co/yJsXrvI0Ki",
"expanded": "https://twitter.com/llama_index/status/1915098378880602555",
"display": "x.com/llama_index/st…"
},
"reply_count": 2,
"retweet_count": 25,
"retweeted": false,
"user_id_str": "369777416",
"id_str": "1915109277498585569"
},
"quick_promote_eligibility": {
"eligibility": "IneligibleNotProfessional"
}
}
},
"tweetDisplayType": "Tweet"
},
"clientEventInfo": {
"component": "tweet",
"element": "tweet"
}
}
},
{
"entryId": "conversationthread-1915109957122568594",
"sortIndex": "1953521498761199606",
"content": {
"entryType": "TimelineTimelineModule",
"__typename": "TimelineTimelineModule",
"items": [
{
"entryId": "conversationthread-1915109957122568594-tweet-1915109957122568594",
"item": {
"itemContent": {
"itemType": "TimelineTweet",
"__typename": "TimelineTweet",
"tweet_results": {
"result": {
"__typename": "Tweet",
"rest_id": "1915109957122568594",
"has_birdwatch_notes": false,
"core": {
"user_results": {
"result": {
"__typename": "User",
"id": "VXNlcjoxODY1MDYwNzQ4MTIyMjk2MzIw",
"rest_id": "1865060748122296320",
"affiliates_highlighted_label": {},
"has_graduated_access": true,
"is_blue_verified": false,
"profile_image_shape": "Circle",
"legacy": {
"can_dm": true,
"can_media_tag": true,
"created_at": "Fri Dec 06 15:48:42 +0000 2024",
"default_profile": true,
"default_profile_image": false,
"description": "Marketing @Skywork_ai \nVisit our website to discover innovative solutions.",
"entities": {
"description": {
"urls": []
}
},
"fast_followers_count": 0,
"favourites_count": 95,
"followers_count": 24,
"friends_count": 409,
"has_custom_timelines": false,
"is_translator": false,
"listed_count": 0,
"location": "",
"media_count": 5,
"name": "Lam",
"normal_followers_count": 24,
"pinned_tweet_ids_str": [],
"possibly_sensitive": false,
"profile_banner_url": "https://pbs.twimg.com/profile_banners/1865060748122296320/1741145633",
"profile_image_url_https": "https://pbs.twimg.com/profile_images/1865060810751643653/bg7mJrlB_normal.jpg",
"profile_interstitial_type": "",
"screen_name": "LanqiJiang",
"statuses_count": 159,
"translator_type": "none",
"verified": false,
"want_retweets": false,
"withheld_in_countries": []
},
"tipjar_settings": {}
}
}
},
"unmention_data": {},
"edit_control": {
"edit_tweet_ids": [
"1915109957122568594"
],
"editable_until_msecs": "1745436369000",
"is_edit_eligible": false,
"edits_remaining": "5"
},
"is_translatable": false,
"views": {
"count": "29",
"state": "EnabledWithCount"
},
"source": "<a href=\"https://mobile.twitter.com\" rel=\"nofollow\">Twitter Web App</a>",
"legacy": {
"bookmark_count": 0,
"bookmarked": false,
"created_at": "Wed Apr 23 18:26:09 +0000 2025",
"conversation_id_str": "1915109277498585569",
"display_text_range": [
12,
259
],
"entities": {
"hashtags": [],
"symbols": [],
"timestamps": [],
"urls": [],
"user_mentions": [
{
"id_str": "369777416",
"name": "Jerry Liu",
"screen_name": "jerryjliu0",
"indices": [
0,
11
]
}
]
},
"favorite_count": 1,
"favorited": false,
"full_text": "@jerryjliu0 Agentic workflows are a game-changer for docs! Basic RAG often misses the nuance in PDFs/PPTs. Love how structured mapping can turn data chaos into clarity—been grinding on similar multimodal challenges. Excited to see your architecture in action!",
"in_reply_to_screen_name": "jerryjliu0",
"in_reply_to_status_id_str": "1915109277498585569",
"in_reply_to_user_id_str": "369777416",
"is_quote_status": false,
"lang": "en",
"quote_count": 0,
"reply_count": 0,
"retweet_count": 0,
"retweeted": false,
"user_id_str": "1865060748122296320",
"id_str": "1915109957122568594"
},
"quick_promote_eligibility": {
"eligibility": "IneligibleNotProfessional"
}
}
},
"tweetDisplayType": "Tweet"
},
"clientEventInfo": {
"component": "tweet",
"element": "tweet",
"details": {
"conversationDetails": {
"conversationSection": "HighQuality"
},
"timelinesDetails": {
"controllerData": "DAACDAAEDAABCgABAAAAAAAAAAEKAAIAAAAAAAAAAAAAAAA="
}
}
}
}
}
],
"metadata": {
"conversationMetadata": {
"allTweetIds": [
"1915109957122568594"
],
"enableDeduplication": true
}
},
"displayType": "VerticalConversation",
"clientEventInfo": {
"component": "tweet",
"details": {
"conversationDetails": {
"conversationSection": "HighQuality"
},
"timelinesDetails": {
"controllerData": "DAACDAAEDAABCgABAAAAAAAAAAEKAAIAAAAAAAAAAAAAAAA="
}
}
}
}
},
{
"entryId": "conversationthread-1915116845725856254",
"sortIndex": "1953521498761199596",
"content": {
"entryType": "TimelineTimelineModule",
"__typename": "TimelineTimelineModule",
"items": [
{
"entryId": "conversationthread-1915116845725856254-tweet-1915116845725856254",
"item": {
"itemContent": {
"itemType": "TimelineTweet",
"__typename": "TimelineTweet",
"tweet_results": {
"result": {
"__typename": "Tweet",
"rest_id": "1915116845725856254",
"has_birdwatch_notes": false,
"core": {
"user_results": {
"result": {
"__typename": "User",
"id": "VXNlcjoxODQ1ODkwOTA0MTUxNzI4MTI4",
"rest_id": "1845890904151728128",
"affiliates_highlighted_label": {},
"has_graduated_access": true,
"is_blue_verified": false,
"profile_image_shape": "Circle",
"legacy": {
"can_dm": false,
"can_media_tag": true,
"created_at": "Mon Oct 14 18:14:27 +0000 2024",
"default_profile": true,
"default_profile_image": false,
"description": "The autonomous company",
"entities": {
"description": {
"urls": []
},
"url": {
"urls": [
{
"display_url": "o-mega.ai",
"expanded_url": "https://o-mega.ai",
"url": "https://t.co/ECC6zpnYw9",
"indices": [
0,
23
]
}
]
}
},
"fast_followers_count": 0,
"favourites_count": 145,
"followers_count": 176,
"friends_count": 244,
"has_custom_timelines": false,
"is_translator": false,
"listed_count": 0,
"location": "San Francisco, CA",
"media_count": 14,
"name": "o-mega.ai",
"normal_followers_count": 176,
"pinned_tweet_ids_str": [
"1935241092808720886"
],
"possibly_sensitive": false,
"profile_banner_url": "https://pbs.twimg.com/profile_banners/1845890904151728128/1748851090",
"profile_image_url_https": "https://pbs.twimg.com/profile_images/1929439233095122944/vn_Y92Li_normal.jpg",
"profile_interstitial_type": "",
"screen_name": "o_mega___",
"statuses_count": 1623,
"translator_type": "none",
"url": "https://t.co/ECC6zpnYw9",
"verified": false,
"want_retweets": false,
"withheld_in_countries": []
},
"tipjar_settings": {}
}
}
},
"unmention_data": {},
"edit_control": {
"edit_tweet_ids": [
"1915116845725856254"
],
"editable_until_msecs": "1745438011000",
"is_edit_eligible": false,
"edits_remaining": "5"
},
"is_translatable": false,
"views": {
"count": "242",
"state": "EnabledWithCount"
},
"source": "<a href=\"https://o-mega.ai\" rel=\"nofollow\">feel-the-omega</a>",
"note_tweet": {
"is_expandable": true,
"note_tweet_results": {
"result": {
"id": "Tm90ZVR3ZWV0OjE5MTUxMTY4NDU1Nzg5ODU0NzI=",
"text": "Facts: Agentic Document Workflows extend beyond basic RAG by orchestrating sequences of retrieval, reasoning, and multi-document integration, not just answering a single query over static chunks.\nIn @jerryjliu0's architecture, agents can iteratively retrieve, evaluate, and produce synthesized outputs across PDFs, PPTs, and Excel—bridging the workflow gaps that single-turn RAG leaves.\nExamples include agents handling financial reporting: pulling source data, validating numbers, and updating presentations across document types—autonomously, end-to-end.\nKey difference: Agentic workflows enable context-aware multi-step decisions and memory—RAG cannot handle document-linked actions, workflow branching, or coordinated updates.\nAgentic approaches fundamentally shift the boundary from Q&A over data to reliable action chains over interlinked knowledge work artifacts.",
"entity_set": {
"hashtags": [],
"symbols": [],
"urls": [],
"user_mentions": [
{
"id_str": "369777416",
"name": "Jerry Liu",
"screen_name": "jerryjliu0",
"indices": [
199,
210
]
}
]
}
}
}
},
"legacy": {
"bookmark_count": 0,
"bookmarked": false,
"created_at": "Wed Apr 23 18:53:31 +0000 2025",
"conversation_id_str": "1915109277498585569",
"display_text_range": [
12,
286
],
"entities": {
"hashtags": [],
"symbols": [],
"timestamps": [],
"urls": [],
"user_mentions": [
{
"id_str": "369777416",
"name": "Jerry Liu",
"screen_name": "jerryjliu0",
"indices": [
0,
11
]
},
{
"id_str": "369777416",
"name": "Jerry Liu",
"screen_name": "jerryjliu0",
"indices": [
211,
222
]
}
]
},
"favorite_count": 2,
"favorited": false,
"full_text": "@jerryjliu0 Facts: Agentic Document Workflows extend beyond basic RAG by orchestrating sequences of retrieval, reasoning, and multi-document integration, not just answering a single query over static chunks.\nIn @jerryjliu0's architecture, agents can iteratively retrieve, evaluate, and…",
"in_reply_to_screen_name": "jerryjliu0",
"in_reply_to_status_id_str": "1915109277498585569",
"in_reply_to_user_id_str": "369777416",
"is_quote_status": false,
"lang": "en",
"quote_count": 0,
"reply_count": 0,
"retweet_count": 0,
"retweeted": false,
"user_id_str": "1845890904151728128",
"id_str": "1915116845725856254"
},
"quick_promote_eligibility": {
"eligibility": "IneligibleNotProfessional"
}
}
},
"tweetDisplayType": "Tweet"
},
"clientEventInfo": {
"component": "tweet",
"element": "tweet",
"details": {
"conversationDetails": {
"conversationSection": "HighQuality"
},
"timelinesDetails": {
"controllerData": "DAACDAAEDAABCgABAAAAAAAAAAEKAAIAAAAAAAAAAAAAAAA="
}
}
}
}
}
],
"metadata": {
"conversationMetadata": {
"allTweetIds": [
"1915116845725856254"
],
"enableDeduplication": true
}
},
"displayType": "VerticalConversation",
"clientEventInfo": {
"component": "tweet",
"details": {
"conversationDetails": {
"conversationSection": "HighQuality"
},
"timelinesDetails": {
"controllerData": "DAACDAAEDAABCgABAAAAAAAAAAEKAAIAAAAAAAAAAAAAAAA="
}
}
}
}
},
{
"entryId": "cursor-bottom-1953521498761199595",
"sortIndex": "1953521498761199595",
"content": {
"entryType": "TimelineTimelineCursor",
"__typename": "TimelineTimelineCursor",
"value": "DAAFCgABGxxNc_K__-kLAAIAAAA8RW1QQzZ3QUFBZlEvZ0dKTjB2R3AvQUFBQUFNYWs5eWYzTnN4L2hxVDFsdjhHckdTR3BQVnZiOWJzZUU9CAADAAAAAgAA",
"cursorType": "Bottom"
}
}
]
},
{
"type": "TimelineTerminateTimeline",
"direction": "Top"
},
{
"type": "TimelineTerminateTimeline",
"direction": "Bottom"
}
],
"metadata": {
"scribeConfig": {
"page": "ranked_replies"
}
}
}
}
}