🐦 Twitter Post Details

Viewing enriched Twitter post

@omarsar0

// Scalable Patterns for Agentic AI Workflows // Besides context engineering, we should be putting a lot more system engineering efforts around agents. This paper shows an example of why it matters. (bookmark it) Let's start with an important question: Where does your agentic RAG pipeline actually lose time? It's almost never the LLM call. It's usually the data plane underneath. Serialization between preprocessing, embedding, and vector retrieval, plus coordination overhead between distributed services. New work introduces AAFLOW, a unified distributed runtime that models agentic workflows as an operator abstraction over Apache Arrow and Cylon. A zero-copy data plane connects preprocessing, embedding, and retrieval directly. Resource-deterministic scheduling and async batching cut coordination cost. The result: up to 4.64× pipeline speedup and 2.8× gains in embedding and upsert phases, with comparable LLM throughput. None of that comes from LLM inference acceleration. It all comes from cleaner data flow. Paper: https://t.co/9fqkRRsV39 Learn to build effective AI agents in our academy: https://t.co/1e8RZKs4uX

Media 1
View on Twitter

📊 Media Metadata

{
  "media": [
    {
      "type": "photo",
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2053515178482999533/media_0.png",
      "filename": "media_0.png"
    }
  ],
  "processed_at": "2026-05-11T22:29:15.287069",
  "pipeline_version": "2.0"
}

🔧 Raw API Response

{
  "type": "tweet",
  "id": "2053515178482999533",
  "url": "https://x.com/omarsar0/status/2053515178482999533",
  "twitterUrl": "https://twitter.com/omarsar0/status/2053515178482999533",
  "text": "// Scalable Patterns for Agentic AI Workflows //\n\nBesides context engineering, we should be putting a lot more system engineering efforts around agents.\n\nThis paper shows an example of why it matters.\n\n(bookmark it)\n\nLet's start with an important question: Where does your agentic RAG pipeline actually lose time?\n\nIt's almost never the LLM call. It's usually the data plane underneath. Serialization between preprocessing, embedding, and vector retrieval, plus coordination overhead between distributed services.\n\nNew work introduces AAFLOW, a unified distributed runtime that models agentic workflows as an operator abstraction over Apache Arrow and Cylon. A zero-copy data plane connects preprocessing, embedding, and retrieval directly. Resource-deterministic scheduling and async batching cut coordination cost.\n\nThe result: up to 4.64× pipeline speedup and 2.8× gains in embedding and upsert phases, with comparable LLM throughput.\n\nNone of that comes from LLM inference acceleration. It all comes from cleaner data flow.\n\nPaper: https://t.co/9fqkRRsV39\n\nLearn to build effective AI agents in our academy: https://t.co/1e8RZKs4uX",
  "source": "Twitter for iPhone",
  "retweetCount": 32,
  "replyCount": 20,
  "likeCount": 190,
  "quoteCount": 1,
  "viewCount": 14599,
  "createdAt": "Sun May 10 16:39:05 +0000 2026",
  "lang": "en",
  "bookmarkCount": 248,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2053515178482999533",
  "displayTextRange": [
    0,
    280
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "omarsar0",
    "url": "https://x.com/omarsar0",
    "twitterUrl": "https://twitter.com/omarsar0",
    "id": "3448284313",
    "name": "elvis",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/939313677647282181/vZjFWtAn_normal.jpg",
    "coverPicture": "https://pbs.twimg.com/profile_banners/3448284313/1565974901",
    "description": "",
    "location": "DAIR.AI Academy",
    "followers": 303366,
    "following": 830,
    "status": "",
    "canDm": true,
    "canMediaTag": true,
    "createdAt": "Fri Sep 04 12:59:26 +0000 2015",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 35835,
    "hasCustomTimelines": true,
    "isTranslator": true,
    "mediaCount": 4645,
    "statusesCount": 17833,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "2053575378208256086"
    ],
    "profile_bio": {
      "description": "Building @dair_ai • Prev: Meta AI, Elastic, PhD • New AI learning portal: https://t.co/1e8RZKs4uX",
      "entities": {
        "description": {
          "urls": [
            {
              "display_url": "academy.dair.ai",
              "expanded_url": "https://academy.dair.ai/",
              "indices": [
                74,
                97
              ],
              "url": "https://t.co/1e8RZKs4uX"
            }
          ],
          "user_mentions": [
            {
              "id_str": "",
              "indices": [
                9,
                17
              ],
              "name": "",
              "screen_name": "dair_ai"
            }
          ]
        },
        "url": {
          "urls": [
            {
              "display_url": "dair.ai",
              "expanded_url": "https://www.dair.ai/",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/XQto5ypSIk"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {
    "media": [
      {
        "display_url": "pic.twitter.com/QWGvYBqc1r",
        "expanded_url": "https://twitter.com/omarsar0/status/2053515178482999533/photo/1",
        "ext_media_availability": {
          "status": "Available"
        },
        "features": {
          "large": {
            "faces": []
          },
          "orig": {
            "faces": []
          }
        },
        "id_str": "2053515174934609921",
        "indices": [
          281,
          304
        ],
        "media_key": "3_2053515174934609921",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARx/jSvu2gABCgACHH+NLMJaIO0AAA==",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAABCgABHH+NK+7aAAEKAAIcf40swlog7QAA",
            "media_key": "3_2053515174934609921"
          }
        },
        "media_url_https": "https://pbs.twimg.com/media/HH-NK-7aAAE9v_x.png",
        "original_info": {
          "focus_rects": [
            {
              "h": 824,
              "w": 1472,
              "x": 0,
              "y": 0
            },
            {
              "h": 1472,
              "w": 1472,
              "x": 0,
              "y": 0
            },
            {
              "h": 1678,
              "w": 1472,
              "x": 0,
              "y": 0
            },
            {
              "h": 1882,
              "w": 941,
              "x": 235,
              "y": 0
            },
            {
              "h": 1882,
              "w": 1472,
              "x": 0,
              "y": 0
            }
          ],
          "height": 1882,
          "width": 1472
        },
        "sizes": {
          "large": {
            "h": 1882,
            "w": 1472
          }
        },
        "type": "photo",
        "url": "https://t.co/QWGvYBqc1r"
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "urls": [
      {
        "display_url": "arxiv.org/abs/2605.02162",
        "expanded_url": "https://arxiv.org/abs/2605.02162",
        "indices": [
          1036,
          1059
        ],
        "url": "https://t.co/9fqkRRsV39"
      },
      {
        "display_url": "academy.dair.ai",
        "expanded_url": "https://academy.dair.ai/",
        "indices": [
          1112,
          1135
        ],
        "url": "https://t.co/1e8RZKs4uX"
      }
    ],
    "user_mentions": []
  },
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "communityInfo": null,
  "article": null
}