🐦 Twitter Post Details

Viewing enriched Twitter post

@jerryjliu0

Many AI agents in finance rely on extremely high quality context engineering from documents 📑 They can be roughly divided into two categories: 1️⃣ Repetitive, operational work common in back-office use cases - invoice processing, loan origination, KYC 2️⃣ Assistive agents for open-ended research and generation of reports/presentations - e.g. diligence, equity research We gave a workshop last week in NYC on how to build a high-quality document context layer to enable these AI agent use cases. At this stage, you need a rigorous OCR layer, evaluation checks, and good UI/UX for HITL review/audit - even a slight mistake in number can have catastrophic consequences downstream. Check out the resources below: ✅ My slides: talk a lot about document processing and the general landscape of knowledge work: https://t.co/qpxRK0yzdc ✅ Logan’s repo on building an agentic document parsing pipeline over financial documents, with full HITL review: https://t.co/VlrRzV5Vi6 Our core mission is extracting the highest-quality document context for AI agents in finance and more. Come talk to us if you’re facing relevant challenges: https://t.co/Ht5jwxSrQB

Media 1
Media 2
Media 3

📊 Media Metadata

{
  "media": [
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2055817368253997244/media_0.jpg",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2055817368253997244/media_0.jpg",
      "type": "photo",
      "filename": "media_0.jpg"
    },
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2055817368253997244/media_2.jpg",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2055817368253997244/media_2.jpg",
      "type": "photo",
      "filename": "media_2.jpg"
    },
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2055817368253997244/media_3.jpg",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2055817368253997244/media_3.jpg",
      "type": "photo",
      "filename": "media_3.jpg"
    }
  ],
  "processed_at": "2026-05-17T04:30:56.697139",
  "pipeline_version": "2.0"
}

🔧 Raw API Response

{
  "type": "tweet",
  "id": "2055817368253997244",
  "url": "https://x.com/jerryjliu0/status/2055817368253997244",
  "twitterUrl": "https://twitter.com/jerryjliu0/status/2055817368253997244",
  "text": "Many AI agents in finance rely on extremely high quality context engineering from documents 📑\n\nThey can be roughly divided into two categories:\n1️⃣ Repetitive, operational work common in back-office use cases - invoice processing, loan origination, KYC\n2️⃣ Assistive agents for open-ended research and generation of reports/presentations - e.g. diligence, equity research\n\nWe gave a workshop last week in NYC on how to build a high-quality document context layer to enable these AI agent use cases. At this stage, you need a rigorous OCR layer, evaluation checks, and good UI/UX for HITL review/audit - even a slight mistake in number can have catastrophic consequences downstream.\n\nCheck out the resources below:\n✅ My slides: talk a lot about document processing and the general landscape of knowledge work: https://t.co/qpxRK0yzdc\n✅ Logan’s repo on building an agentic document parsing pipeline over financial documents, with full HITL review: https://t.co/VlrRzV5Vi6\n\nOur core mission is extracting the highest-quality document context for AI agents in finance and more. Come talk to us if you’re facing relevant challenges: https://t.co/Ht5jwxSrQB",
  "source": "Twitter for iPhone",
  "retweetCount": 7,
  "replyCount": 5,
  "likeCount": 29,
  "quoteCount": 0,
  "viewCount": 2392,
  "createdAt": "Sun May 17 01:07:10 +0000 2026",
  "lang": "en",
  "bookmarkCount": 52,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2055817368253997244",
  "displayTextRange": [
    0,
    277
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "jerryjliu0",
    "url": "https://x.com/jerryjliu0",
    "twitterUrl": "https://twitter.com/jerryjliu0",
    "id": "369777416",
    "name": "Jerry Liu",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/1283610285031460864/1Q4zYhtb_normal.jpg",
    "coverPicture": "",
    "description": "",
    "location": "",
    "followers": 74281,
    "following": 1478,
    "status": "",
    "canDm": true,
    "canMediaTag": true,
    "createdAt": "Wed Sep 07 22:54:31 +0000 2011",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 8760,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 1513,
    "statusesCount": 6959,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [],
    "profile_bio": {
      "description": "Parsing the world's hardest PDFs @llama_index. cofounder/CEO\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",
              "indices": [
                71,
                94
              ],
              "url": "https://t.co/EUnMNmbCtx"
            },
            {
              "display_url": "llamaindex.ai/contact",
              "expanded_url": "https://www.llamaindex.ai/contact",
              "indices": [
                107,
                130
              ],
              "url": "https://t.co/Ht5jwxSrQB"
            }
          ],
          "user_mentions": [
            {
              "id_str": "",
              "indices": [
                33,
                45
              ],
              "name": "",
              "screen_name": "llama_index"
            }
          ]
        },
        "url": {
          "urls": [
            {
              "display_url": "llamaindex.ai",
              "expanded_url": "https://www.llamaindex.ai/",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/YiIfjVlzb6"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {
    "media": [
      {
        "display_url": "pic.twitter.com/MQaADUsgkz",
        "expanded_url": "https://twitter.com/jerryjliu0/status/2055817368253997244/photo/1",
        "ext_media_availability": {
          "status": "Available"
        },
        "features": {
          "large": {
            "faces": []
          },
          "orig": {
            "faces": []
          }
        },
        "id_str": "2055817342140268544",
        "indices": [
          278,
          301
        ],
        "media_key": "3_2055817342140268544",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARyHuvsBW8AACgACHIe7ARXboLwAAA==",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAABCgABHIe6+wFbwAAKAAIch7sBFdugvAAA",
            "media_key": "3_2055817342140268544"
          }
        },
        "media_url_https": "https://pbs.twimg.com/media/HIe6-wFbwAAGm3G.jpg",
        "original_info": {
          "focus_rects": [
            {
              "h": 1135,
              "w": 2027,
              "x": 1,
              "y": 0
            },
            {
              "h": 1135,
              "w": 1135,
              "x": 700,
              "y": 0
            },
            {
              "h": 1135,
              "w": 996,
              "x": 769,
              "y": 0
            },
            {
              "h": 1135,
              "w": 568,
              "x": 983,
              "y": 0
            },
            {
              "h": 1135,
              "w": 2028,
              "x": 0,
              "y": 0
            }
          ],
          "height": 1135,
          "width": 2028
        },
        "sizes": {
          "large": {
            "h": 1135,
            "w": 2028
          }
        },
        "type": "photo",
        "url": "https://t.co/MQaADUsgkz"
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "urls": [
      {
        "display_url": "figma.com/slides/QUUMQqh…",
        "expanded_url": "https://www.figma.com/slides/QUUMQqhCsmV6tz8s5Iq9Iu",
        "indices": [
          809,
          832
        ],
        "url": "https://t.co/qpxRK0yzdc"
      },
      {
        "display_url": "github.com/logan-markewic…",
        "expanded_url": "https://github.com/logan-markewich/finparse-pipeline",
        "indices": [
          946,
          969
        ],
        "url": "https://t.co/VlrRzV5Vi6"
      },
      {
        "display_url": "llamaindex.ai/contact",
        "expanded_url": "https://www.llamaindex.ai/contact",
        "indices": [
          1128,
          1151
        ],
        "url": "https://t.co/Ht5jwxSrQB"
      }
    ],
    "user_mentions": []
  },
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "communityInfo": null,
  "article": null
}