šŸ¦ Twitter Post Details

Viewing enriched Twitter post

@llama_index

Context engineering is the new prompt engineering ā€” and if you're building AI agents, you need to understand the difference and why parsing your data correctly sits at the heart of it Andrej Karpathy put it well: context engineering is "the delicate art and science of filling the context window with just the right information for the next step." It's not just about the instructions you give an LLM. It's about what you put IN front of it. That context can come from a lot of places: ā€” System prompts ā€” Chat history & long-term memory ā€” Knowledge base retrieval ā€” Tool definitions & responses ā€” Structured outputs One of the most underrated levers? Structured information. This is exactly what LlamaParse + LlamaExtract are built for. Parse your complex documents properly ā†’ extract structured, relevant fields ā†’ pass clean, dense context to your agent. Better parsing = better context = better agents. It really is that simple. Take a look back on a piece by @tuanacelik and @LoganMarkewich about the full breakdown: what context engineering is, what makes up context, and the key techniques to consider ā€” from memory blocks to workflow engineering. Read it here šŸ‘‡ https://t.co/fE6cuzDJMj

Media 1
Media 2
View on Twitter

šŸ“Š Media Metadata

{
  "media": [
    {
      "type": "photo",
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2034347384973762694/media_0.png",
      "filename": "media_0.png"
    },
    {
      "type": "photo",
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2034347384973762694/media_1.png",
      "filename": "media_1.png"
    }
  ],
  "processed_at": "2026-03-18T19:16:35.924986",
  "pipeline_version": "2.0"
}

šŸ”§ Raw API Response

{
  "type": "tweet",
  "id": "2034347384973762694",
  "url": "https://x.com/llama_index/status/2034347384973762694",
  "twitterUrl": "https://twitter.com/llama_index/status/2034347384973762694",
  "text": "Context engineering is the new prompt engineering ā€” and if you're building AI agents, you need to understand the difference and why parsing your data correctly sits at the heart of it\n\nAndrej Karpathy put it well: context engineering is \"the delicate art and science of filling the context window with just the right information for the next step.\"\nIt's not just about the instructions you give an LLM. It's about what you put IN front of it.\n\nThat context can come from a lot of places:\nā€” System prompts\nā€” Chat history & long-term memory\nā€” Knowledge base retrieval\nā€” Tool definitions & responses\nā€” Structured outputs\n\nOne of the most underrated levers? Structured information.\nThis is exactly what LlamaParse + LlamaExtract are built for.\nParse your complex documents properly ā†’ extract structured, relevant fields ā†’ pass clean, dense context to your agent.\nBetter parsing = better context = better agents. It really is that simple.\n\nTake a look back on a piece by @tuanacelik and @LoganMarkewich about  the full breakdown: what context engineering is, what makes up context, and the key techniques to consider ā€” from memory blocks to workflow engineering.\nRead it here šŸ‘‡\nhttps://t.co/fE6cuzDJMj",
  "source": "Twitter for iPhone",
  "retweetCount": 1,
  "replyCount": 1,
  "likeCount": 2,
  "quoteCount": 0,
  "viewCount": 95,
  "createdAt": "Wed Mar 18 19:13:07 +0000 2026",
  "lang": "en",
  "bookmarkCount": 2,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2034347384973762694",
  "displayTextRange": [
    0,
    277
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "llama_index",
    "url": "https://x.com/llama_index",
    "twitterUrl": "https://twitter.com/llama_index",
    "id": "1604278358296055808",
    "name": "LlamaIndex šŸ¦™",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": "Business",
    "profilePicture": "https://pbs.twimg.com/profile_images/1967920417760251904/0ytfduMQ_normal.png",
    "coverPicture": "https://pbs.twimg.com/profile_banners/1604278358296055808/1770092126",
    "description": "",
    "location": "",
    "followers": 110353,
    "following": 32,
    "status": "",
    "canDm": false,
    "canMediaTag": true,
    "createdAt": "Sun Dec 18 00:52:44 +0000 2022",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 1504,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 1840,
    "statusesCount": 3768,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "2029767312195117278"
    ],
    "profile_bio": {
      "description": "AI Agents for document OCR + workflows\n\nLlamaParse: https://t.co/yQGTiRSfFL\nDocs: https://t.co/us6GCS14vD",
      "entities": {
        "description": {
          "hashtags": [],
          "symbols": [],
          "urls": [
            {
              "display_url": "cloud.llamaindex.ai",
              "expanded_url": "https://cloud.llamaindex.ai/",
              "indices": [
                52,
                75
              ],
              "url": "https://t.co/yQGTiRSfFL"
            },
            {
              "display_url": "developers.llamaindex.ai/python/cloud/",
              "expanded_url": "https://developers.llamaindex.ai/python/cloud/",
              "indices": [
                82,
                105
              ],
              "url": "https://t.co/us6GCS14vD"
            }
          ],
          "user_mentions": []
        },
        "url": {
          "urls": [
            {
              "display_url": "llamaindex.ai",
              "expanded_url": "https://www.llamaindex.ai/",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/epzefqPT9Z"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {
    "media": [
      {
        "display_url": "pic.twitter.com/lT7MGIJ2lh",
        "expanded_url": "https://twitter.com/llama_index/status/2034347384973762694/photo/1",
        "ext_media_availability": {
          "status": "Available"
        },
        "features": {
          "large": {
            "faces": []
          },
          "orig": {
            "faces": []
          }
        },
        "id_str": "2034347382402686976",
        "indices": [
          278,
          301
        ],
        "media_key": "3_2034347382402686976",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARw7dCp126AACgACHDt0Kw8bIIYAAA==",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAABCgABHDt0KnXboAAKAAIcO3QrDxsghgAA",
            "media_key": "3_2034347382402686976"
          }
        },
        "media_url_https": "https://pbs.twimg.com/media/HDt0KnXboAAQJdM.png",
        "original_info": {
          "focus_rects": [
            {
              "h": 379,
              "w": 677,
              "x": 0,
              "y": 0
            },
            {
              "h": 379,
              "w": 379,
              "x": 0,
              "y": 0
            },
            {
              "h": 379,
              "w": 332,
              "x": 0,
              "y": 0
            },
            {
              "h": 379,
              "w": 190,
              "x": 0,
              "y": 0
            },
            {
              "h": 379,
              "w": 734,
              "x": 0,
              "y": 0
            }
          ],
          "height": 379,
          "width": 734
        },
        "sizes": {
          "large": {
            "h": 379,
            "w": 734
          }
        },
        "type": "photo",
        "url": "https://t.co/lT7MGIJ2lh"
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "urls": [
      {
        "display_url": "llamaindex.ai/blog/context-eā€¦",
        "expanded_url": "https://www.llamaindex.ai/blog/context-engineering-what-it-is-and-techniques-to-consider?utm_source=socials&utm_medium=li_social",
        "indices": [
          1173,
          1196
        ],
        "url": "https://t.co/fE6cuzDJMj"
      }
    ],
    "user_mentions": [
      {
        "id_str": "209600624",
        "indices": [
          966,
          977
        ],
        "name": "Tuana",
        "screen_name": "tuanacelik"
      },
      {
        "id_str": "1676011773810360320",
        "indices": [
          982,
          997
        ],
        "name": "Logan Markewich",
        "screen_name": "LoganMarkewich"
      }
    ]
  },
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "article": null
}