Viewing enriched Twitter post
OpenAI recently released a guide on building agents which contains some misguided takes There's a lot of FUD, confusion, hype, and noise around agents I wrote a blog on how to think about agent frameworks. Includes: Background Info - What is an agent? - What is hard about… https://t.co/7VKe9VMBad
{
"media": [
{
"type": "image",
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1914035527608897897/media_0.jpg?",
"filename": "media_0.jpg"
}
],
"nlp": {
"sentiment": "negative",
"topics": [
"OpenAI",
"agents",
"blog"
],
"entities": [
"OpenAI"
],
"summary": "The tweet expresses criticism of OpenAI's guide on building agents, highlighting confusion and misinformation in the field.",
"language": "en",
"processed_at": "2025-08-07T12:10:51.393506"
}
}{
"data": {
"threaded_conversation_with_injections_v2": {
"instructions": [
{
"type": "TimelineClearCache"
},
{
"type": "TimelineAddEntries",
"entries": [
{
"entryId": "tweet-1914016302261506421",
"sortIndex": "1953519202228764672",
"content": {
"entryType": "TimelineTimelineItem",
"__typename": "TimelineTimelineItem",
"itemContent": {
"itemType": "TimelineTweet",
"__typename": "TimelineTweet",
"tweet_results": {
"result": {
"__typename": "Tweet",
"rest_id": "1914016302261506421",
"has_birdwatch_notes": false,
"core": {
"user_results": {
"result": {
"__typename": "User",
"id": "VXNlcjoyNzI4NDM5MTQ2",
"rest_id": "2728439146",
"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": "Tue Jul 29 19:22:50 +0000 2014",
"default_profile": true,
"default_profile_image": false,
"description": "@LangChainAI, previously @robusthq @kensho\n\nMLOps ∪ Generative AI ∪ sports analytics",
"entities": {
"description": {
"urls": []
}
},
"fast_followers_count": 0,
"favourites_count": 12793,
"followers_count": 77453,
"friends_count": 469,
"has_custom_timelines": true,
"is_translator": false,
"listed_count": 1536,
"location": "",
"media_count": 531,
"name": "Harrison Chase",
"normal_followers_count": 77453,
"pinned_tweet_ids_str": [
"1950597664174907681"
],
"possibly_sensitive": false,
"profile_image_url_https": "https://pbs.twimg.com/profile_images/1569345624935485442/R67C4wCQ_normal.jpg",
"profile_interstitial_type": "",
"screen_name": "hwchase17",
"statuses_count": 13149,
"translator_type": "none",
"verified": false,
"want_retweets": false,
"withheld_in_countries": []
},
"tipjar_settings": {}
}
}
},
"unmention_data": {},
"edit_control": {
"edit_tweet_ids": [
"1914016302261506421"
],
"editable_until_msecs": "1745175621000",
"is_edit_eligible": false,
"edits_remaining": "5"
},
"is_translatable": false,
"views": {
"count": "447047",
"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": "Tm90ZVR3ZWV0OjE5MTQwMTYzMDIxNTI1MzE5Njg=",
"text": "OpenAI recently released a guide on building agents which contains some misguided takes\n\nThere's a lot of FUD, confusion, hype, and noise around agents\n\nI wrote a blog on how to think about agent frameworks. Includes:\n\nBackground Info\n- What is an agent?\n- What is hard about building agents?\n- What is LangGraph?\n\nFlavors of agentic frameworks\n- “Agents” vs “workflows”\n- Declarative vs non-declarative\n- Agent abstractions\n- Multi agent\n\nCommon Questions\n- What is the value of a framework?\n- As the models get better, will everything become agents instead of workflows?\n- What did OpenAI get wrong in their take?\n- How do all the agent frameworks compare?",
"entity_set": {
"hashtags": [],
"symbols": [],
"urls": [],
"user_mentions": []
},
"richtext": {
"richtext_tags": []
},
"media": {
"inline_media": []
}
}
}
},
"legacy": {
"bookmark_count": 1533,
"bookmarked": false,
"created_at": "Sun Apr 20 18:00:21 +0000 2025",
"conversation_id_str": "1914016302261506421",
"display_text_range": [
0,
276
],
"entities": {
"hashtags": [],
"media": [
{
"display_url": "pic.x.com/7VKe9VMBad",
"expanded_url": "https://x.com/hwchase17/status/1914016302261506421/photo/1",
"id_str": "1914016192492445698",
"indices": [
277,
300
],
"media_key": "3_1914016192492445698",
"media_url_https": "https://pbs.twimg.com/media/Go_zlg_boAIO_Sz.png",
"type": "photo",
"url": "https://t.co/7VKe9VMBad",
"ext_media_availability": {
"status": "Available"
},
"features": {
"large": {
"faces": []
},
"medium": {
"faces": []
},
"small": {
"faces": []
},
"orig": {
"faces": []
}
},
"sizes": {
"large": {
"h": 582,
"w": 1506,
"resize": "fit"
},
"medium": {
"h": 464,
"w": 1200,
"resize": "fit"
},
"small": {
"h": 263,
"w": 680,
"resize": "fit"
},
"thumb": {
"h": 150,
"w": 150,
"resize": "crop"
}
},
"original_info": {
"height": 582,
"width": 1506,
"focus_rects": [
{
"x": 467,
"y": 0,
"w": 1039,
"h": 582
},
{
"x": 924,
"y": 0,
"w": 582,
"h": 582
},
{
"x": 995,
"y": 0,
"w": 511,
"h": 582
},
{
"x": 1169,
"y": 0,
"w": 291,
"h": 582
},
{
"x": 0,
"y": 0,
"w": 1506,
"h": 582
}
]
},
"media_results": {
"result": {
"media_key": "3_1914016192492445698"
}
}
}
],
"symbols": [],
"timestamps": [],
"urls": [],
"user_mentions": []
},
"extended_entities": {
"media": [
{
"display_url": "pic.x.com/7VKe9VMBad",
"expanded_url": "https://x.com/hwchase17/status/1914016302261506421/photo/1",
"id_str": "1914016192492445698",
"indices": [
277,
300
],
"media_key": "3_1914016192492445698",
"media_url_https": "https://pbs.twimg.com/media/Go_zlg_boAIO_Sz.png",
"type": "photo",
"url": "https://t.co/7VKe9VMBad",
"ext_media_availability": {
"status": "Available"
},
"features": {
"large": {
"faces": []
},
"medium": {
"faces": []
},
"small": {
"faces": []
},
"orig": {
"faces": []
}
},
"sizes": {
"large": {
"h": 582,
"w": 1506,
"resize": "fit"
},
"medium": {
"h": 464,
"w": 1200,
"resize": "fit"
},
"small": {
"h": 263,
"w": 680,
"resize": "fit"
},
"thumb": {
"h": 150,
"w": 150,
"resize": "crop"
}
},
"original_info": {
"height": 582,
"width": 1506,
"focus_rects": [
{
"x": 467,
"y": 0,
"w": 1039,
"h": 582
},
{
"x": 924,
"y": 0,
"w": 582,
"h": 582
},
{
"x": 995,
"y": 0,
"w": 511,
"h": 582
},
{
"x": 1169,
"y": 0,
"w": 291,
"h": 582
},
{
"x": 0,
"y": 0,
"w": 1506,
"h": 582
}
]
},
"media_results": {
"result": {
"media_key": "3_1914016192492445698"
}
}
}
]
},
"favorite_count": 927,
"favorited": false,
"full_text": "OpenAI recently released a guide on building agents which contains some misguided takes\n\nThere's a lot of FUD, confusion, hype, and noise around agents\n\nI wrote a blog on how to think about agent frameworks. Includes:\n\nBackground Info\n- What is an agent?\n- What is hard about… https://t.co/7VKe9VMBad",
"is_quote_status": false,
"lang": "en",
"possibly_sensitive": false,
"possibly_sensitive_editable": true,
"quote_count": 43,
"reply_count": 90,
"retweet_count": 126,
"retweeted": false,
"user_id_str": "2728439146",
"id_str": "1914016302261506421"
},
"quick_promote_eligibility": {
"eligibility": "IneligibleNotProfessional"
}
}
},
"tweetDisplayType": "Tweet"
},
"clientEventInfo": {
"component": "tweet",
"element": "tweet"
}
}
},
{
"entryId": "tweet-1914035527608897897",
"sortIndex": "1953519202228764662",
"content": {
"entryType": "TimelineTimelineItem",
"__typename": "TimelineTimelineItem",
"itemContent": {
"itemType": "TimelineTweet",
"__typename": "TimelineTweet",
"tweet_results": {
"result": {
"__typename": "Tweet",
"rest_id": "1914035527608897897",
"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": [
"1914035527608897897"
],
"editable_until_msecs": "1745180205000",
"is_edit_eligible": false,
"edits_remaining": "5"
},
"is_translatable": false,
"views": {
"count": "20418",
"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": "Tm90ZVR3ZWV0OjE5MTQwMzU1MjczOTQ5NTExNjg=",
"text": "Dude - I like the overall idea of the blog and I'm not expecting a 100% unbiased comparison, but the checkboxes on @llama_index are inaccurate. We've been working on both high-level agent abstractions and low-level workflow abstractions for almost a year now. \n\n✅ We have a low-level \"event-driven\" workflows API that's half-declarative and imperative. This allows both visualization/tracing, but also flexible orchestration patterns. Should honestly check both the boxes around \"declarative\" and \"imperative\". \n\nI have no idea what an \"actor model API\" means. \n\nWe also have pre-built multi-agent abstractions.\n\n✅ Support for short-term and long-term memory through composable memory abstractions: https://t.co/v0d8Frk4Lj\n✅ Human-in-the-loop and human-on-the-loop (letting the user pass event messages if needed) https://t.co/YD0L3JPlQo\n✅ Code interpreter through integrations and also pre-built CodeAct agent: https://t.co/w3kJgsKkuV\n✅ Tracing through native logging + partners (we intentionally don't have a first-party tool here) \n✅ Fault tolerance through retries in our core workflows: https://t.co/FsBumRoOHm\n\nIk this is a LangGraph-centered blog post but would appreciate a more accurate representation of our stuff",
"entity_set": {
"hashtags": [],
"symbols": [],
"urls": [
{
"display_url": "docs.llamaindex.ai/en/stable/exam…",
"expanded_url": "https://docs.llamaindex.ai/en/stable/examples/agent/memory/composable_memory/",
"url": "https://t.co/v0d8Frk4Lj",
"indices": [
699,
722
]
},
{
"display_url": "docs.llamaindex.ai/en/stable/unde…",
"expanded_url": "https://docs.llamaindex.ai/en/stable/understanding/agent/human_in_the_loop/",
"url": "https://t.co/YD0L3JPlQo",
"indices": [
814,
837
]
},
{
"display_url": "docs.llamaindex.ai/en/latest/exam…",
"expanded_url": "https://docs.llamaindex.ai/en/latest/examples/agent/code_act_agent/",
"url": "https://t.co/w3kJgsKkuV",
"indices": [
912,
935
]
},
{
"display_url": "docs.llamaindex.ai/en/stable/modu…",
"expanded_url": "https://docs.llamaindex.ai/en/stable/module_guides/workflow/#retry-steps-execution-in-case-of-failures",
"url": "https://t.co/FsBumRoOHm",
"indices": [
1092,
1115
]
}
],
"user_mentions": [
{
"id_str": "1604278358296055808",
"name": "LlamaIndex 🦙",
"screen_name": "llama_index",
"indices": [
115,
127
]
}
]
},
"richtext": {
"richtext_tags": []
},
"media": {
"inline_media": []
}
}
}
},
"legacy": {
"bookmark_count": 52,
"bookmarked": false,
"created_at": "Sun Apr 20 19:16:45 +0000 2025",
"conversation_id_str": "1914016302261506421",
"display_text_range": [
11,
285
],
"entities": {
"hashtags": [],
"symbols": [],
"timestamps": [],
"urls": [],
"user_mentions": [
{
"id_str": "2728439146",
"name": "Harrison Chase",
"screen_name": "hwchase17",
"indices": [
0,
10
]
},
{
"id_str": "1604278358296055808",
"name": "LlamaIndex 🦙",
"screen_name": "llama_index",
"indices": [
126,
138
]
}
]
},
"favorite_count": 150,
"favorited": false,
"full_text": "@hwchase17 Dude - I like the overall idea of the blog and I'm not expecting a 100% unbiased comparison, but the checkboxes on @llama_index are inaccurate. We've been working on both high-level agent abstractions and low-level workflow abstractions for almost a year now. \n\n✅ We have a…",
"in_reply_to_screen_name": "hwchase17",
"in_reply_to_status_id_str": "1914016302261506421",
"in_reply_to_user_id_str": "2728439146",
"is_quote_status": false,
"lang": "en",
"quote_count": 1,
"reply_count": 5,
"retweet_count": 6,
"retweeted": false,
"user_id_str": "369777416",
"id_str": "1914035527608897897"
},
"quick_promote_eligibility": {
"eligibility": "IneligibleNotProfessional"
}
}
},
"tweetDisplayType": "Tweet"
},
"clientEventInfo": {
"component": "tweet",
"element": "tweet"
}
}
},
{
"entryId": "conversationthread-1914040135886463153",
"sortIndex": "1953519202228764652",
"content": {
"entryType": "TimelineTimelineModule",
"__typename": "TimelineTimelineModule",
"items": [
{
"entryId": "conversationthread-1914040135886463153-tweet-1914040135886463153",
"item": {
"itemContent": {
"itemType": "TimelineTweet",
"__typename": "TimelineTweet",
"tweet_results": {
"result": {
"__typename": "Tweet",
"rest_id": "1914040135886463153",
"has_birdwatch_notes": false,
"core": {
"user_results": {
"result": {
"__typename": "User",
"id": "VXNlcjoyNzI4NDM5MTQ2",
"rest_id": "2728439146",
"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": "Tue Jul 29 19:22:50 +0000 2014",
"default_profile": true,
"default_profile_image": false,
"description": "@LangChainAI, previously @robusthq @kensho\n\nMLOps ∪ Generative AI ∪ sports analytics",
"entities": {
"description": {
"urls": []
}
},
"fast_followers_count": 0,
"favourites_count": 12793,
"followers_count": 77453,
"friends_count": 469,
"has_custom_timelines": true,
"is_translator": false,
"listed_count": 1536,
"location": "",
"media_count": 531,
"name": "Harrison Chase",
"normal_followers_count": 77453,
"pinned_tweet_ids_str": [
"1950597664174907681"
],
"possibly_sensitive": false,
"profile_image_url_https": "https://pbs.twimg.com/profile_images/1569345624935485442/R67C4wCQ_normal.jpg",
"profile_interstitial_type": "",
"screen_name": "hwchase17",
"statuses_count": 13149,
"translator_type": "none",
"verified": false,
"want_retweets": false,
"withheld_in_countries": []
},
"tipjar_settings": {}
}
}
},
"unmention_data": {},
"edit_control": {
"edit_tweet_ids": [
"1914040135886463153"
],
"editable_until_msecs": "1745181304000",
"is_edit_eligible": false,
"edits_remaining": "5"
},
"is_translatable": false,
"views": {
"count": "13723",
"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": "Tm90ZVR3ZWV0OjE5MTQwNDAxMzU2OTM2MTEwMDg=",
"text": "I tried to be unbiased! I will admit I haven't look at llama index for agents so this was based on superficial glancing. would love to correct!\n\n❌\"Tracing\" is checked if the authors of the framework also implement an LLM/agent specific tracing platform\n\n❌\"Code interpreter\" is checked if the authors of the framework also implement a code interpreter\n\n✅You are right you do have human-in-the-loop I have updated!\n\n❌I don't think you support human-on-the-loop (or at least I can't see an example of \"time-travel\" like functionality - can you point me an example?)\n\n❌All your examples of memory look very single process/tenant centric. Is multi-tenancy built into your orchestration framework storage by default? If so can you point to docs?\n\n❌For multi agent: is the main thing you have AgentWorkflow? From docs (https://t.co/pPSuR78Uwe) \n\n\"We will use AgentWorkflow to create a multi-agent system that will execute these agents in order.\" \n\n- so this is just a sequential pipeline? I dont really think thats a multi agent abstraction (thats more a workflow abstraction)",
"entity_set": {
"hashtags": [],
"symbols": [],
"urls": [
{
"display_url": "docs.llamaindex.ai/en/stable/unde…",
"expanded_url": "https://docs.llamaindex.ai/en/stable/understanding/agent/multi_agent/",
"url": "https://t.co/pPSuR78Uwe",
"indices": [
812,
835
]
}
],
"user_mentions": []
},
"richtext": {
"richtext_tags": []
},
"media": {
"inline_media": []
}
}
}
},
"legacy": {
"bookmark_count": 7,
"bookmarked": false,
"created_at": "Sun Apr 20 19:35:04 +0000 2025",
"conversation_id_str": "1914016302261506421",
"display_text_range": [
25,
302
],
"entities": {
"hashtags": [],
"symbols": [],
"timestamps": [],
"urls": [],
"user_mentions": [
{
"id_str": "369777416",
"name": "Jerry Liu",
"screen_name": "jerryjliu0",
"indices": [
0,
11
]
},
{
"id_str": "1604278358296055808",
"name": "LlamaIndex 🦙",
"screen_name": "llama_index",
"indices": [
12,
24
]
}
]
},
"favorite_count": 21,
"favorited": false,
"full_text": "@jerryjliu0 @llama_index I tried to be unbiased! I will admit I haven't look at llama index for agents so this was based on superficial glancing. would love to correct!\n\n❌\"Tracing\" is checked if the authors of the framework also implement an LLM/agent specific tracing platform\n\n❌\"Code interpreter\" is…",
"in_reply_to_screen_name": "jerryjliu0",
"in_reply_to_status_id_str": "1914035527608897897",
"in_reply_to_user_id_str": "369777416",
"is_quote_status": false,
"lang": "en",
"quote_count": 1,
"reply_count": 3,
"retweet_count": 0,
"retweeted": false,
"user_id_str": "2728439146",
"id_str": "1914040135886463153"
},
"quick_promote_eligibility": {
"eligibility": "IneligibleNotProfessional"
}
}
},
"tweetDisplayType": "Tweet"
},
"clientEventInfo": {
"component": "tweet",
"element": "tweet",
"details": {
"conversationDetails": {
"conversationSection": "HighQuality"
},
"timelinesDetails": {
"controllerData": "DAACDAAEDAABCgABAAAAAAAAAAEKAAIAAAAAAAAAAAAAAAA="
}
}
}
}
},
{
"entryId": "conversationthread-1914040135886463153-tweet-1914045802806382883",
"item": {
"itemContent": {
"itemType": "TimelineTweet",
"__typename": "TimelineTweet",
"tweet_results": {
"result": {
"__typename": "Tweet",
"rest_id": "1914045802806382883",
"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": [
"1914045802806382883"
],
"editable_until_msecs": "1745182655000",
"is_edit_eligible": false,
"edits_remaining": "5"
},
"is_translatable": false,
"views": {
"count": "4772",
"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": "Tm90ZVR3ZWV0OjE5MTQwNDU4MDI2NTEyNzkzNjA=",
"text": "* We do have human-on-the-loop, from my understanding of how you defined as \"time travel\" it it's basically being able to do 1) checkpointing so you can reload from an earlier state on user input, and 2) HITL which in our setting is event-driven, so you can both \"observe\" an input without acting upon it, and/or pass a user message while the workflow is running.\n\nHITL is already shown in my example above, in the meantime we have state management tutorials: https://t.co/AFVN9JI2FU\n\n* Our multi-agent workflow isn't sequential, it's a swarm/supervisor pattern (not that dissimilar from your abstractions). Not sure what checkboxes that's supposed to check though..l\n\nLooking at the checklist my main gripes are:\n1. A bit misleading that both declarative API and imperative functional API aren't checked, and only actor model API is checked \n2. human on the loop should checked\n3. fault tolerance should be checked\n\neverything else w/e. appreciate the response btw",
"entity_set": {
"hashtags": [],
"symbols": [],
"urls": [
{
"display_url": "docs.llamaindex.ai/en/stable/unde…",
"expanded_url": "https://docs.llamaindex.ai/en/stable/understanding/agent/state/#maintaining-state",
"url": "https://t.co/AFVN9JI2FU",
"indices": [
460,
483
]
}
],
"user_mentions": []
},
"richtext": {
"richtext_tags": []
},
"media": {
"inline_media": []
}
}
}
},
"legacy": {
"bookmark_count": 4,
"bookmarked": false,
"created_at": "Sun Apr 20 19:57:35 +0000 2025",
"conversation_id_str": "1914016302261506421",
"display_text_range": [
24,
300
],
"entities": {
"hashtags": [],
"symbols": [],
"timestamps": [],
"urls": [],
"user_mentions": [
{
"id_str": "2728439146",
"name": "Harrison Chase",
"screen_name": "hwchase17",
"indices": [
0,
10
]
},
{
"id_str": "1604278358296055808",
"name": "LlamaIndex 🦙",
"screen_name": "llama_index",
"indices": [
11,
23
]
}
]
},
"favorite_count": 17,
"favorited": false,
"full_text": "@hwchase17 @llama_index * We do have human-on-the-loop, from my understanding of how you defined as \"time travel\" it it's basically being able to do 1) checkpointing so you can reload from an earlier state on user input, and 2) HITL which in our setting is event-driven, so you can both \"observe\" an…",
"in_reply_to_screen_name": "hwchase17",
"in_reply_to_status_id_str": "1914040135886463153",
"in_reply_to_user_id_str": "2728439146",
"is_quote_status": false,
"lang": "en",
"quote_count": 0,
"reply_count": 1,
"retweet_count": 0,
"retweeted": false,
"user_id_str": "369777416",
"id_str": "1914045802806382883"
},
"quick_promote_eligibility": {
"eligibility": "IneligibleNotProfessional"
}
}
},
"tweetDisplayType": "Tweet"
},
"clientEventInfo": {
"component": "tweet",
"element": "tweet",
"details": {
"conversationDetails": {
"conversationSection": "HighQuality"
},
"timelinesDetails": {
"controllerData": "DAACDAAEDAABCgABAAAAAAAAAAEKAAIAAAAAAAAAAAAAAAA="
}
}
}
}
},
{
"entryId": "conversationthread-1914040135886463153-cursor-showmore-1163978588",
"item": {
"itemContent": {
"itemType": "TimelineTimelineCursor",
"__typename": "TimelineTimelineCursor",
"value": "DAABCwABAAAAMEVtUEM2d0FBQUFnL2dHSk4wdkdwL0FBQUFBSWFrQTZFUUJvUkl4cVFDVnpSV21DeAgAAgAAAAYKAAMakAlc0VpgsQ8ABAoAAAACGpAJXNFaYLEakA6EQBoRIwAA",
"cursorType": "ShowMore",
"displayTreatment": {
"actionText": "Show replies"
}
},
"clientEventInfo": {
"component": "cursor",
"element": "tweet",
"details": {
"conversationDetails": {
"conversationSection": "HighQuality"
},
"timelinesDetails": {
"controllerData": "DAACDAAEDAABCgABAAAAAAAAAAEKAAIAAAAAAAAAAAAAAAA="
}
}
}
}
}
],
"metadata": {
"conversationMetadata": {
"allTweetIds": [
"1914052797877944618"
],
"enableDeduplication": true
}
},
"displayType": "VerticalConversation",
"clientEventInfo": {
"component": "tweet",
"details": {
"conversationDetails": {
"conversationSection": "HighQuality"
},
"timelinesDetails": {
"controllerData": "DAACDAAEDAABCgABAAAAAAAAAAEKAAIAAAAAAAAAAAAAAAA="
}
}
}
}
},
{
"entryId": "conversationthread-1914283826387325293",
"sortIndex": "1953519202228764642",
"content": {
"entryType": "TimelineTimelineModule",
"__typename": "TimelineTimelineModule",
"items": [
{
"entryId": "conversationthread-1914283826387325293-tweet-1914283826387325293",
"item": {
"itemContent": {
"itemType": "TimelineTweet",
"__typename": "TimelineTweet",
"tweet_results": {
"result": {
"__typename": "Tweet",
"rest_id": "1914283826387325293",
"has_birdwatch_notes": false,
"core": {
"user_results": {
"result": {
"__typename": "User",
"id": "VXNlcjoxODcwMTYyMzIzMjAzMTA4ODY1",
"rest_id": "1870162323203108865",
"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": "Fri Dec 20 17:40:27 +0000 2024",
"default_profile": true,
"default_profile_image": false,
"description": "(New account. Prev: @hadiazouni)\n\nhttps://t.co/aGUgzJKruG: AI agent for DevOps (VC)\nhttps://t.co/ED7bl7PgwK: Building enterprise AI agents (45k MRR)\nhttps://t.co/aquc9xtU1d (5k users)\nhttps://t.co/T5pfQeSxRE",
"entities": {
"description": {
"urls": [
{
"display_url": "heycloud.ai",
"expanded_url": "http://heycloud.ai",
"url": "https://t.co/aGUgzJKruG",
"indices": [
34,
57
]
},
{
"display_url": "ragbase.ai",
"expanded_url": "http://ragbase.ai",
"url": "https://t.co/ED7bl7PgwK",
"indices": [
84,
107
]
},
{
"display_url": "draft1.ai",
"expanded_url": "http://draft1.ai",
"url": "https://t.co/aquc9xtU1d",
"indices": [
150,
173
]
},
{
"display_url": "heycli.com",
"expanded_url": "http://heycli.com",
"url": "https://t.co/T5pfQeSxRE",
"indices": [
185,
208
]
}
]
},
"url": {
"urls": [
{
"display_url": "linkedin.com",
"expanded_url": "https://www.linkedin.com/",
"url": "https://t.co/TnRjG0yeal",
"indices": [
0,
23
]
}
]
}
},
"fast_followers_count": 0,
"favourites_count": 72,
"followers_count": 317,
"friends_count": 284,
"has_custom_timelines": false,
"is_translator": false,
"listed_count": 3,
"location": "Paris",
"media_count": 62,
"name": "Hadi",
"normal_followers_count": 317,
"pinned_tweet_ids_str": [
"1897207717133214094"
],
"possibly_sensitive": false,
"profile_image_url_https": "https://pbs.twimg.com/profile_images/1888234525148237824/3NodOLpf_normal.jpg",
"profile_interstitial_type": "",
"screen_name": "savage_agi",
"statuses_count": 470,
"translator_type": "none",
"url": "https://t.co/TnRjG0yeal",
"verified": false,
"want_retweets": false,
"withheld_in_countries": []
},
"tipjar_settings": {}
}
}
},
"unmention_data": {},
"edit_control": {
"edit_tweet_ids": [
"1914283826387325293"
],
"editable_until_msecs": "1745239404000",
"is_edit_eligible": false,
"edits_remaining": "5"
},
"is_translatable": false,
"views": {
"count": "549",
"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": "Tm90ZVR3ZWV0OjE5MTQyODM4MjYzMTE4Mjc0NTY=",
"text": "not sure anyone (in 2025) should use someone else's abstractions and do all sorts of gymnastics to fit it into their own business workflows. \n\nwe literally spend 80% of our effort convincing our customers to drop langchain , llamaindex and all other fluff. That ends up solving 90% of their issues.",
"entity_set": {
"hashtags": [],
"symbols": [],
"urls": [],
"user_mentions": []
},
"richtext": {
"richtext_tags": []
},
"media": {
"inline_media": []
}
}
}
},
"legacy": {
"bookmark_count": 2,
"bookmarked": false,
"created_at": "Mon Apr 21 11:43:24 +0000 2025",
"conversation_id_str": "1914016302261506421",
"display_text_range": [
36,
314
],
"entities": {
"hashtags": [],
"symbols": [],
"timestamps": [],
"urls": [],
"user_mentions": [
{
"id_str": "369777416",
"name": "Jerry Liu",
"screen_name": "jerryjliu0",
"indices": [
0,
11
]
},
{
"id_str": "2728439146",
"name": "Harrison Chase",
"screen_name": "hwchase17",
"indices": [
12,
22
]
},
{
"id_str": "1604278358296055808",
"name": "LlamaIndex 🦙",
"screen_name": "llama_index",
"indices": [
23,
35
]
}
]
},
"favorite_count": 9,
"favorited": false,
"full_text": "@jerryjliu0 @hwchase17 @llama_index not sure anyone (in 2025) should use someone else's abstractions and do all sorts of gymnastics to fit it into their own business workflows. \n\nwe literally spend 80% of our effort convincing our customers to drop langchain , llamaindex and all other fluff. That ends up solving…",
"in_reply_to_screen_name": "jerryjliu0",
"in_reply_to_status_id_str": "1914035527608897897",
"in_reply_to_user_id_str": "369777416",
"is_quote_status": false,
"lang": "en",
"quote_count": 0,
"reply_count": 1,
"retweet_count": 0,
"retweeted": false,
"user_id_str": "1870162323203108865",
"id_str": "1914283826387325293"
},
"quick_promote_eligibility": {
"eligibility": "IneligibleNotProfessional"
}
}
},
"tweetDisplayType": "Tweet"
},
"clientEventInfo": {
"component": "tweet",
"element": "tweet",
"details": {
"conversationDetails": {
"conversationSection": "HighQuality"
},
"timelinesDetails": {
"controllerData": "DAACDAAEDAABCgABAAAAAAAAAAEKAAIAAAAAAAAAAAAAAAA="
}
}
}
}
}
],
"metadata": {
"conversationMetadata": {
"allTweetIds": [
"1914283826387325293"
],
"enableDeduplication": true
}
},
"displayType": "VerticalConversation",
"clientEventInfo": {
"component": "tweet",
"details": {
"conversationDetails": {
"conversationSection": "HighQuality"
},
"timelinesDetails": {
"controllerData": "DAACDAAEDAABCgABAAAAAAAAAAEKAAIAAAAAAAAAAAAAAAA="
}
}
}
}
},
{
"entryId": "conversationthread-1915289366228000964",
"sortIndex": "1953519202228764632",
"content": {
"entryType": "TimelineTimelineModule",
"__typename": "TimelineTimelineModule",
"items": [
{
"entryId": "conversationthread-1915289366228000964-tweet-1915289366228000964",
"item": {
"itemContent": {
"itemType": "TimelineTweet",
"__typename": "TimelineTweet",
"tweet_results": {
"result": {
"__typename": "Tweet",
"rest_id": "1915289366228000964",
"has_birdwatch_notes": false,
"core": {
"user_results": {
"result": {
"__typename": "User",
"id": "VXNlcjoxMTI1ODQ3NzEyMTE1NDgyNjI0",
"rest_id": "1125847712115482624",
"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": "Tue May 07 19:39:46 +0000 2019",
"default_profile": true,
"default_profile_image": false,
"description": "Co-founder & CTO @diagridio \\\\\nCo-creator of Dapr, KEDA \\\\\nAuthor of Learning Dapr\n\nOffice Hours: https://t.co/VbLQpXADOi",
"entities": {
"description": {
"urls": [
{
"display_url": "calendly.com/yaron2/cloud-n…",
"expanded_url": "https://calendly.com/yaron2/cloud-native-30m-chat",
"url": "https://t.co/VbLQpXADOi",
"indices": [
98,
121
]
}
]
},
"url": {
"urls": [
{
"display_url": "diagrid.io",
"expanded_url": "https://www.diagrid.io",
"url": "https://t.co/WreUe9Dkoa",
"indices": [
0,
23
]
}
]
}
},
"fast_followers_count": 0,
"favourites_count": 3284,
"followers_count": 1528,
"friends_count": 226,
"has_custom_timelines": true,
"is_translator": false,
"listed_count": 20,
"location": "Federal Way, WA",
"media_count": 15,
"name": "Yaron Schneider",
"normal_followers_count": 1528,
"pinned_tweet_ids_str": [],
"possibly_sensitive": false,
"profile_banner_url": "https://pbs.twimg.com/profile_banners/1125847712115482624/1661196031",
"profile_image_url_https": "https://pbs.twimg.com/profile_images/1125847940012994560/BLtNCI2T_normal.jpg",
"profile_interstitial_type": "",
"screen_name": "yaronschneider",
"statuses_count": 753,
"translator_type": "none",
"url": "https://t.co/WreUe9Dkoa",
"verified": false,
"want_retweets": false,
"withheld_in_countries": []
},
"tipjar_settings": {}
}
}
},
"unmention_data": {},
"edit_control": {
"edit_tweet_ids": [
"1915289366228000964"
],
"editable_until_msecs": "1745479143000",
"is_edit_eligible": false,
"edits_remaining": "5"
},
"is_translatable": false,
"views": {
"count": "87",
"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": "Tm90ZVR3ZWV0OjE5MTUyODkzNjYxNjkzNDYwNTM=",
"text": "Since I couldn't find anything about it in the docs - where does LlamaIndex Workflows store it's state? In-memory can never be used in production scenarios so I assume there's a way to allow users to store in a database of their choice? (Without needing to write this complex logic themselves of course)",
"entity_set": {
"hashtags": [],
"symbols": [],
"urls": [],
"user_mentions": []
},
"richtext": {
"richtext_tags": []
},
"media": {
"inline_media": []
}
}
}
},
"legacy": {
"bookmark_count": 0,
"bookmarked": false,
"created_at": "Thu Apr 24 06:19:03 +0000 2025",
"conversation_id_str": "1914016302261506421",
"display_text_range": [
36,
312
],
"entities": {
"hashtags": [],
"symbols": [],
"timestamps": [],
"urls": [],
"user_mentions": [
{
"id_str": "369777416",
"name": "Jerry Liu",
"screen_name": "jerryjliu0",
"indices": [
0,
11
]
},
{
"id_str": "2728439146",
"name": "Harrison Chase",
"screen_name": "hwchase17",
"indices": [
12,
22
]
},
{
"id_str": "1604278358296055808",
"name": "LlamaIndex 🦙",
"screen_name": "llama_index",
"indices": [
23,
35
]
}
]
},
"favorite_count": 1,
"favorited": false,
"full_text": "@jerryjliu0 @hwchase17 @llama_index Since I couldn't find anything about it in the docs - where does LlamaIndex Workflows store it's state? In-memory can never be used in production scenarios so I assume there's a way to allow users to store in a database of their choice? (Without needing to write this complex…",
"in_reply_to_screen_name": "jerryjliu0",
"in_reply_to_status_id_str": "1914035527608897897",
"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": "1125847712115482624",
"id_str": "1915289366228000964"
},
"quick_promote_eligibility": {
"eligibility": "IneligibleNotProfessional"
}
}
},
"tweetDisplayType": "Tweet"
},
"clientEventInfo": {
"component": "tweet",
"element": "tweet",
"details": {
"conversationDetails": {
"conversationSection": "HighQuality"
},
"timelinesDetails": {
"controllerData": "DAACDAAEDAABCgABAAAAAAAAAAEKAAIAAAAAAAAAAAAAAAA="
}
}
}
}
}
],
"metadata": {
"conversationMetadata": {
"allTweetIds": [
"1915289366228000964"
],
"enableDeduplication": true
}
},
"displayType": "VerticalConversation",
"clientEventInfo": {
"component": "tweet",
"details": {
"conversationDetails": {
"conversationSection": "HighQuality"
},
"timelinesDetails": {
"controllerData": "DAACDAAEDAABCgABAAAAAAAAAAEKAAIAAAAAAAAAAAAAAAA="
}
}
}
}
},
{
"entryId": "conversationthread-1914289142994776520",
"sortIndex": "1953519202228764622",
"content": {
"entryType": "TimelineTimelineModule",
"__typename": "TimelineTimelineModule",
"items": [
{
"entryId": "conversationthread-1914289142994776520-tweet-1914289142994776520",
"item": {
"itemContent": {
"itemType": "TimelineTweet",
"__typename": "TimelineTweet",
"tweet_results": {
"result": {
"__typename": "Tweet",
"rest_id": "1914289142994776520",
"has_birdwatch_notes": false,
"core": {
"user_results": {
"result": {
"__typename": "User",
"id": "VXNlcjoxOTg3OTkxNDQ=",
"rest_id": "198799144",
"affiliates_highlighted_label": {},
"has_graduated_access": true,
"is_blue_verified": false,
"profile_image_shape": "Circle",
"legacy": {
"can_dm": false,
"can_media_tag": false,
"created_at": "Tue Oct 05 08:24:34 +0000 2010",
"default_profile": true,
"default_profile_image": false,
"description": "privacy accelerationism = a cornerstone in todays continued fight for freedom (obtw: blood spills in this war regularly) 💎 “… & keep the law.” ⚖️📖 Acts 21:24",
"entities": {
"description": {
"urls": []
}
},
"fast_followers_count": 0,
"favourites_count": 44894,
"followers_count": 51,
"friends_count": 1491,
"has_custom_timelines": true,
"is_translator": false,
"listed_count": 1,
"location": "",
"media_count": 409,
"name": "inner voice priv/acc",
"normal_followers_count": 51,
"pinned_tweet_ids_str": [
"1743815354466386213"
],
"possibly_sensitive": false,
"profile_image_url_https": "https://pbs.twimg.com/profile_images/1150607647/9id48vfd_normal",
"profile_interstitial_type": "",
"screen_name": "thotsonrecord",
"statuses_count": 9160,
"translator_type": "none",
"verified": false,
"want_retweets": false,
"withheld_in_countries": []
},
"tipjar_settings": {}
}
}
},
"unmention_data": {},
"edit_control": {
"edit_tweet_ids": [
"1914289142994776520"
],
"editable_until_msecs": "1745240672000",
"is_edit_eligible": false,
"edits_remaining": "5"
},
"is_translatable": false,
"views": {
"count": "324",
"state": "EnabledWithCount"
},
"source": "<a href=\"http://twitter.com/download/iphone\" rel=\"nofollow\">Twitter for iPhone</a>",
"legacy": {
"bookmark_count": 0,
"bookmarked": false,
"created_at": "Mon Apr 21 12:04:32 +0000 2025",
"conversation_id_str": "1914016302261506421",
"display_text_range": [
36,
118
],
"entities": {
"hashtags": [],
"symbols": [],
"timestamps": [],
"urls": [],
"user_mentions": [
{
"id_str": "369777416",
"name": "Jerry Liu",
"screen_name": "jerryjliu0",
"indices": [
0,
11
]
},
{
"id_str": "2728439146",
"name": "Harrison Chase",
"screen_name": "hwchase17",
"indices": [
12,
22
]
},
{
"id_str": "1604278358296055808",
"name": "LlamaIndex 🦙",
"screen_name": "llama_index",
"indices": [
23,
35
]
}
]
},
"favorite_count": 1,
"favorited": false,
"full_text": "@jerryjliu0 @hwchase17 @llama_index Great engagement on this 💎 shows we need a single crowd source edition of this! ⚡️",
"in_reply_to_screen_name": "jerryjliu0",
"in_reply_to_status_id_str": "1914035527608897897",
"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": "198799144",
"id_str": "1914289142994776520"
},
"quick_promote_eligibility": {
"eligibility": "IneligibleNotProfessional"
}
}
},
"tweetDisplayType": "Tweet"
},
"clientEventInfo": {
"component": "tweet",
"element": "tweet",
"details": {
"conversationDetails": {
"conversationSection": "HighQuality"
},
"timelinesDetails": {
"controllerData": "DAACDAAEDAABCgABAAAAAAAAAAEKAAIAAAAAAAAAAAAAAAA="
}
}
}
}
}
],
"metadata": {
"conversationMetadata": {
"allTweetIds": [
"1914289142994776520"
],
"enableDeduplication": true
}
},
"displayType": "VerticalConversation",
"clientEventInfo": {
"component": "tweet",
"details": {
"conversationDetails": {
"conversationSection": "HighQuality"
},
"timelinesDetails": {
"controllerData": "DAACDAAEDAABCgABAAAAAAAAAAEKAAIAAAAAAAAAAAAAAAA="
}
}
}
}
},
{
"entryId": "conversationthread-1914341557823549773",
"sortIndex": "1953519202228764612",
"content": {
"entryType": "TimelineTimelineModule",
"__typename": "TimelineTimelineModule",
"items": [
{
"entryId": "conversationthread-1914341557823549773-tweet-1914341557823549773",
"item": {
"itemContent": {
"itemType": "TimelineTweet",
"__typename": "TimelineTweet",
"tweet_results": {
"result": {
"__typename": "Tweet",
"rest_id": "1914341557823549773",
"has_birdwatch_notes": false,
"core": {
"user_results": {
"result": {
"__typename": "User",
"id": "VXNlcjoyNTY3MjQ5Mjgy",
"rest_id": "2567249282",
"affiliates_highlighted_label": {},
"has_graduated_access": true,
"is_blue_verified": false,
"profile_image_shape": "Circle",
"legacy": {
"can_dm": false,
"can_media_tag": false,
"created_at": "Sat Jun 14 14:54:32 +0000 2014",
"default_profile": false,
"default_profile_image": false,
"description": "📈 AI Engineer @ https://t.co/Du2lQ9AFgU 🗞 Ho scritto spiegoni @ilpost 🎓 MSc Econ & Stats @LaStatale 🎓 BA Filosofia @UniBergamo & @SorbonneParis1",
"entities": {
"description": {
"urls": [
{
"display_url": "xtreamers.io",
"expanded_url": "http://xtreamers.io",
"url": "https://t.co/Du2lQ9AFgU",
"indices": [
16,
39
]
}
]
}
},
"fast_followers_count": 0,
"favourites_count": 31804,
"followers_count": 531,
"friends_count": 1660,
"has_custom_timelines": true,
"is_translator": false,
"listed_count": 7,
"location": "",
"media_count": 63,
"name": "Luca Baggi",
"normal_followers_count": 531,
"pinned_tweet_ids_str": [
"908341085927342080"
],
"possibly_sensitive": false,
"profile_banner_url": "https://pbs.twimg.com/profile_banners/2567249282/1494766824",
"profile_image_url_https": "https://pbs.twimg.com/profile_images/791402729893687297/M9oqXLGx_normal.jpg",
"profile_interstitial_type": "",
"screen_name": "baggiponte",
"statuses_count": 1551,
"translator_type": "none",
"verified": false,
"want_retweets": false,
"withheld_in_countries": []
},
"tipjar_settings": {}
}
}
},
"unmention_data": {},
"edit_control": {
"edit_tweet_ids": [
"1914341557823549773"
],
"editable_until_msecs": "1745253168000",
"is_edit_eligible": false,
"edits_remaining": "5"
},
"is_translatable": false,
"views": {
"count": "260",
"state": "EnabledWithCount"
},
"source": "<a href=\"https://mobile.twitter.com\" rel=\"nofollow\">Twitter Web App</a>",
"legacy": {
"bookmark_count": 0,
"bookmarked": false,
"created_at": "Mon Apr 21 15:32:48 +0000 2025",
"conversation_id_str": "1914016302261506421",
"display_text_range": [
36,
153
],
"entities": {
"hashtags": [],
"symbols": [],
"timestamps": [],
"urls": [],
"user_mentions": [
{
"id_str": "369777416",
"name": "Jerry Liu",
"screen_name": "jerryjliu0",
"indices": [
0,
11
]
},
{
"id_str": "2728439146",
"name": "Harrison Chase",
"screen_name": "hwchase17",
"indices": [
12,
22
]
},
{
"id_str": "1604278358296055808",
"name": "LlamaIndex 🦙",
"screen_name": "llama_index",
"indices": [
23,
35
]
}
]
},
"favorite_count": 0,
"favorited": false,
"full_text": "@jerryjliu0 @hwchase17 @llama_index I wonder, what made you \"rewrite\" an orchestration framework instead of going for prefect/airflow/temporal as a base?",
"in_reply_to_screen_name": "jerryjliu0",
"in_reply_to_status_id_str": "1914035527608897897",
"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": "2567249282",
"id_str": "1914341557823549773"
},
"quick_promote_eligibility": {
"eligibility": "IneligibleNotProfessional"
}
}
},
"tweetDisplayType": "Tweet"
},
"clientEventInfo": {
"component": "tweet",
"element": "tweet",
"details": {
"conversationDetails": {
"conversationSection": "HighQuality"
},
"timelinesDetails": {
"controllerData": "DAACDAAEDAABCgABAAAAAAAAAAEKAAIAAAAAAAAAAAAAAAA="
}
}
}
}
}
],
"metadata": {
"conversationMetadata": {
"allTweetIds": [
"1914341557823549773"
],
"enableDeduplication": true
}
},
"displayType": "VerticalConversation",
"clientEventInfo": {
"component": "tweet",
"details": {
"conversationDetails": {
"conversationSection": "HighQuality"
},
"timelinesDetails": {
"controllerData": "DAACDAAEDAABCgABAAAAAAAAAAEKAAIAAAAAAAAAAAAAAAA="
}
}
}
}
},
{
"entryId": "cursor-bottom-1953519202228764611",
"sortIndex": "1953519202228764611",
"content": {
"entryType": "TimelineTimelineCursor",
"__typename": "TimelineTimelineCursor",
"value": "DAAFCgABGxxLXT6__8ELAAIAAABwRW1QQzZ3QUFBZlEvZ0dKTjB2R3AvQUFBQUFnYWtPdlZUWmN4eUJxUURvUkFHaEVqR3BBSlhORmFZTEVha0FVcjNwc1JhUnFVZVlmc0dtREVHby96cjU2YWtYVWFrT2IvYnhlUmJScVJHNEVVMXpGTggAAwAAAAIAAA",
"cursorType": "Bottom"
}
}
]
},
{
"type": "TimelineTerminateTimeline",
"direction": "Top"
},
{
"type": "TimelineTerminateTimeline",
"direction": "Bottom"
}
],
"metadata": {
"scribeConfig": {
"page": "ranked_replies"
}
}
}
}
}