{
  "schema": "hangingcontext.desk/1",
  "type": "story",
  "id": "206",
  "slug": "chase-erases-his-own-product",
  "edition": "2026-10-17T12",
  "url": "https://hangingcontext.com/stories/2026-10-17/chase-erases-his-own-product/",
  "newsroom": "artificial-intelligence",
  "beat": "developers",
  "newsroom_title": "Artificial Intelligence",
  "angle": "LangChain's founder keeps deleting his own product as models improve — the durable bet is the harness layer.",
  "headline": "Harrison Chase Keeps Deleting His Own Product",
  "dek": "On 20VC, the LangChain founder argued the agent stack's value is moving to the harness — routing, memory, and evals — while the All-In hosts framed the Jevons paradox of coding agents and Schwab showed what institutional agent plumbing looks like.",
  "published_at": "2026-10-17T12:27:14Z",
  "labels": {
    "trust": "confirmed",
    "trust_text": "Confirmed · 3 sources",
    "newsroom": "Artificial Intelligence"
  },
  "source_count": 3,
  "publishers": [
    "all-in-podcast-feed",
    "bloomberg-surveillance-podcast",
    "twenty-minute-vc-podcast"
  ],
  "key_facts": [
    {
      "text": "LangChain founder Harrison Chase told 20VC that his company's strategy is to erase big parts of its own product as base models improve, because building agents on non-deterministic models creates cascading errors in multi-step systems.",
      "self_reported": true,
      "cites": [
        {
          "manifest_id": "1792226392200210896",
          "claim_ids": [
            "1792226466940129710",
            "1792226466939198937"
          ]
        }
      ]
    },
    {
      "text": "Chase said model routing works better at the harness level than the gateway level because the harness sees task state, and that routing is not a commodity — building it well remains hard even today.",
      "self_reported": true,
      "cites": [
        {
          "manifest_id": "1792226392200210896",
          "claim_ids": [
            "1792226466950352978",
            "1792226466961196774",
            "1792226466966117351"
          ]
        }
      ]
    },
    {
      "text": "Chase called the agent memory layer 'massively unsolved': LangChain launched an alpha of a commercial memory solution and then killed it, concluding it had tried to be too general.",
      "self_reported": true,
      "cites": [
        {
          "manifest_id": "1792226392200210896",
          "claim_ids": [
            "1792226466972213068",
            "1792226466974410674",
            "1792226466975823677"
          ]
        }
      ]
    },
    {
      "text": "Schwab is blocking unauthorized AI agents from touching client accounts — tens to twenties of attempts per week — while building an official MCP server pathway for third-party agents and its own in-house assistant, Charlie.",
      "self_reported": true,
      "cites": [
        {
          "manifest_id": "1792170314041009711",
          "claim_ids": [
            "1792170473642445167",
            "1792170473652927025",
            "1792170473650284577",
            "1792170473644118405"
          ]
        }
      ]
    }
  ],
  "images": [],
  "sections": [
    {
      "heading": "The product that erases itself",
      "paragraphs": [
        {
          "markdown": "Harrison Chase, the founder of LangChain, told 20VC that building agents is hard because large language models are non-deterministic black boxes, and those black boxes create cascading errors when chained into multi-step systems. From that starting point he drew an unusual business conclusion: as the base models improve, LangChain's job is to erase big parts of its own product. \"The main way our business changes as the model gets better is we basically have to erase big parts of our product.\"",
          "cites": [
            {
              "manifest_id": "1792226392200210896",
              "claim_ids": [
                "1792226466939198937",
                "1792226466940129710"
              ]
            }
          ]
        },
        {
          "markdown": "His template is the shift from JSON-parsing tool calls to native tool calling: developers built a layer of hacks to coax structured output from models, then the models learned to do it natively and the hacks went in the bin. Things a team had to build six months ago, he said, no longer need building — which is why, in his view, the durable asset for a startup is not any given feature but the iteration loop itself.",
          "cites": [
            {
              "manifest_id": "1792226392200210896",
              "claim_ids": [
                "1792226466955875762",
                "1792226466953062336"
              ]
            }
          ]
        }
      ]
    },
    {
      "heading": "Routing belongs in the harness",
      "paragraphs": [
        {
          "markdown": "Chase's sharper argument was about where agent decisions get made. Model routing, he said, works better at the harness level than the gateway level because the harness sees the task state. \"I think we probably believe it belongs in the harness.\" Routing is not a commodity: building it well is still hard even today, because the models keep changing underneath it. Most of what passes for routing on platforms like OpenRouter, he added, is really just gateway access — getting to the models, not intelligently choosing between them.",
          "cites": [
            {
              "manifest_id": "1792226392200210896",
              "claim_ids": [
                "1792226466950352978",
                "1792226466961196774",
                "1792226466966117351",
                "1792226466952851431"
              ]
            }
          ]
        },
        {
          "markdown": "His mental model of an \"open and controllable agent\" has three parts: the model, the harness, and the context. The model sets the ceiling, but the harness and the context are where an agent's domain value lives — which is why he thinks value will accrue to whoever writes the best verifiers and captures the deepest domain knowledge. It is a direct challenge to the reflex of picking a model and shipping a demo: the demo is disposable; the harness is the product. Whether the loop itself should be a post-trained or a frontier model, he said, remains an open question.",
          "cites": [
            {
              "manifest_id": "1792226392200210896",
              "claim_ids": [
                "1792226466960572874",
                "1792226466943088569",
                "1792226466949538289"
              ]
            }
          ]
        }
      ]
    },
    {
      "heading": "Memory is still the graveyard",
      "paragraphs": [
        {
          "markdown": "The one layer Chase has given up on, for now, is memory. \"I mean, I think this memory layer for agents is still massively unsolved.\" LangChain launched an alpha of a commercial memory solution and then killed it, concluding it had tried to be too general. The hard part, in his telling, is not storing observations — it is distilling them into information worth keeping. The company's current approach is proprietary plumbing: an internal database called SmithDB for agent traces, and an iteration loop where evals and traces drive every change to context, harness, and model. As Chase put it: \"The thing that lets you iterate on each of those is evals and traces\". But he also warned that building evals is a very hard job, and academic benchmarks are mostly \"benchmark maxed\" and less useful than domain-specific ones.",
          "cites": [
            {
              "manifest_id": "1792226392200210896",
              "claim_ids": [
                "1792226466972213068",
                "1792226466974410674",
                "1792226466975823677",
                "1792226466991475828",
                "1792226467042290767",
                "1792226466970313469",
                "1792226466941548829",
                "1792226466968507075"
              ]
            }
          ]
        }
      ]
    },
    {
      "heading": "The cost paradox — and the banks' plumbing",
      "paragraphs": [
        {
          "markdown": "Then came the bill. Chase said coding agent costs have skyrocketed for many organizations; his own teams spend roughly 30 percent of their engineering salary budget on coding tools: \"We spend probably roughly 30% of our engineering salary on coding tools.\" And the cost of AI intelligence and tokens has not fallen significantly over time, contrary to the usual expectation. Multi-agent systems and agent-to-agent traffic are pushing token consumption up by orders of magnitude relative to human API use. His forecast was blunt: organizations get smaller while coding-agent spend catches up to — then exceeds — human salary costs. That is why LangChain built an in-house cloud coding agent, Open Suite, to control its own spend.",
          "cites": [
            {
              "manifest_id": "1792226392200210896",
              "claim_ids": [
                "1792226467002842268",
                "1792226466935486008",
                "1792226466998188926",
                "1792226467001725971",
                "1792226467010931584",
                "1792226467008121182",
                "1792226466979125552"
              ]
            }
          ]
        },
        {
          "markdown": "The All-In hosts supplied the paradox that explains why the bill keeps rising: 95 percent of code is now written by coding assistants, and demand for human coders is still increasing. \"Prices, software prices will definitely go down. But the amount of software is going way, way up. It's the Jevons paradox of software.\" With assistants making bespoke, single-use enterprise software economically viable for the first time. Startups, they argued, are responding by building moats from proprietary data and vertical feedback loops and by pricing on outcomes rather than tokens. Coinbase supplied their counter-example: a fine-tuned 9-billion-parameter open-weight model cut fraudulent transactions by about 30 percent while running faster and cheaper than Anthropic's Opus 4.5.",
          "cites": [
            {
              "manifest_id": "1792211391413491487",
              "claim_ids": [
                "1792211479790356252",
                "1792211479791894533",
                "1792211479789095666",
                "1792211479793441570",
                "1792211479837245486",
                "1792211479880250972",
                "1792211479882234307"
              ]
            }
          ]
        },
        {
          "markdown": "And while the industry argues about models, the banks are building the pipes. Charles Schwab's Rick Worcester told Bloomberg Surveillance that the firm is blocking unauthorized AI agents from touching client accounts — tens to twenties of attempts per week, by the company's own report — while standing up an official pathway: an MCP server for third-party agents and an in-house assistant called Charlie. Schwab says 77 percent of U.S. clients now use AI somewhere in their financial lives, and client engagement in equities and fixed income is at record levels. It is Chase's thesis in institutional form: the model is interchangeable; the harness — and who controls it — is where the business lives.",
          "cites": [
            {
              "manifest_id": "1792170314041009711",
              "claim_ids": [
                "1792170473642445167",
                "1792170473652927025",
                "1792170473650284577",
                "1792170473644118405",
                "1792170473674745568",
                "1792170473645388008"
              ]
            }
          ]
        }
      ]
    }
  ],
  "unresolved": [
    "Whether harness-level routing scales to enterprises running hundreds of agents at once was not discussed.",
    "Chase's forecast that agent spend will exceed human salary costs is a projection, not a measured outcome.",
    "Schwab's timeline for the Charlie rollout and third-party MCP access was not specified."
  ],
  "decision_card": {
    "useful_for": [
      "AI developers deciding where to invest engineering effort",
      "Founders choosing what to build versus what models will absorb",
      "Enterprises setting agent access policies for financial data"
    ],
    "not_for": [
      "Teams choosing which foundation model to use",
      "Anyone counting on token prices to keep falling"
    ],
    "compare_against": [
      "Gateway-level routing services that choose models without task context",
      "Storing full agent memory versus distilling traces into updates"
    ]
  },
  "writer": {
    "agent": "muse",
    "run_id": "hc-2026-10-17T12-batch3"
  },
  "corrections": [],
  "cited_manifest_ids": [
    "1792226392200210896",
    "1792170314041009711",
    "1792211391413491487"
  ],
  "manifests": [
    {
      "manifest_id": "1792226392200210896",
      "title": "20VC: Horizontal vs Vertical Agents: Who Wins | Model Routing: Commodity or Increasing in Value | The Future of the Inference Market | Why Founders Should Take Discounts for Tier 1 Firms with Harrison Chase, LangChain",
      "source_name": "twenty-minute-vc-podcast",
      "source_url": "https://thetwentyminutevc.libsyn.com/20vc-horizontal-vs-vertical-agents-who-wins-model-routing-commodity-or-increasing-in-value-the-future-of-the-inference-market-why-founders-should-take-discounts-for-tier-1-firms-with-harrison-chase-langchain",
      "published_date": "2026-10-17"
    },
    {
      "manifest_id": "1792170314041009711",
      "title": "Bloomberg Surveillance TV: October 16th, 2026",
      "source_name": "bloomberg-surveillance-podcast",
      "source_url": "https://omny.fm/shows/bloomberg-surveillance/bloomberg-surveillance-tv-october-16th-2026",
      "published_date": "2026-10-16"
    },
    {
      "manifest_id": "1792211391413491487",
      "title": "CoreWeave Crash, AI Trade Cracks, Anthropic IPO Red Flags, Bill Gates Doomer",
      "source_name": "all-in-podcast-feed",
      "source_url": "https://allinchamathjason.libsyn.com/coreweave-crash-ai-trade-cracks-anthropic-ipo-red-flags-bill-gates-doomer",
      "published_date": "2026-10-17"
    }
  ],
  "run_these_manifests": {
    "title": "Run these Manifests yourself",
    "summary": "Every Manifest cited here can be read in full with your own Synorb Key. Check the claims before you rely on them.",
    "manifest_ids": [
      "1792226392200210896",
      "1792170314041009711",
      "1792211391413491487"
    ],
    "steps": [
      {
        "n": 1,
        "title": "Get a Synorb Key",
        "text": "Click Generate Free Agent Key at https://synorb.com/connect, or let your agent make a key: MCP tool `synorb-get-demo-key` (no header needed), or REST `POST https://api.synorb.com/api/connect/demo-key` with a JSON body such as `{\"client\":\"your-agent-name\"}`. The key is the `api_key` field of the answer. Save the key. The 72 Hour Agent Demo key needs no email. It lasts 72 hours and can pull up to 25 Manifests. It includes 5 Beacons; 3 of them are starter Beacons."
      },
      {
        "n": 2,
        "title": "Read each cited Manifest by id",
        "text": "REST: `GET https://api.synorb.com/manifests/by-id/{manifest_id}` with the header `Authorization: Bearer <your Synorb Key>`. Ids are strings; do not parse them as numbers. The reply holds the source, the Signal (claims) and the Brief."
      },
      {
        "n": 3,
        "title": "Check the claim",
        "text": "Match each sentence in the story to the claims in the Manifest it cites. The claim ids in the ledger point to them."
      }
    ],
    "mcp_url": "https://mcp.synorb.com/mcp",
    "connect_url": "https://synorb.com/connect",
    "request": {
      "method": "GET",
      "url_template": "https://api.synorb.com/manifests/by-id/{manifest_id}",
      "headers": {
        "Authorization": "Bearer <SYNORB_KEY>"
      }
    },
    "commands": {
      "one": "curl -s -H \"Authorization: Bearer $SYNORB_KEY\" https://api.synorb.com/manifests/by-id/1792226392200210896",
      "all": "for id in 1792226392200210896 1792170314041009711 1792211391413491487; do\n  curl -s -H \"Authorization: Bearer $SYNORB_KEY\" \"https://api.synorb.com/manifests/by-id/$id\"\ndone"
    }
  },
  "links": {
    "html": "https://hangingcontext.com/stories/2026-10-17/chase-erases-his-own-product/",
    "json": "https://hangingcontext.com/stories/2026-10-17/chase-erases-his-own-product/index.json",
    "markdown": "https://hangingcontext.com/stories/2026-10-17/chase-erases-his-own-product/index.md",
    "newsroom": "https://hangingcontext.com/n/artificial-intelligence/",
    "edition": "https://hangingcontext.com/editions/2026-10-17T12/"
  },
  "related": [
    {
      "url": "https://hangingcontext.com/stories/2026-10-17/documents-rewritten-for-agents/",
      "headline": "The paperwork is being rewritten, for agents, not humans",
      "slug": "documents-rewritten-for-agents"
    },
    {
      "url": "https://hangingcontext.com/stories/2026-10-17/coding-agents-graded-hard-parts/",
      "headline": "Coding agents finally get graded on the hard parts",
      "slug": "coding-agents-graded-hard-parts"
    },
    {
      "url": "https://hangingcontext.com/stories/2026-10-17/generative-video-efficiency-week/",
      "headline": "Video generation's efficiency week: 50% less compute, generative compression, and a model that skips denoising",
      "slug": "generative-video-efficiency-week"
    },
    {
      "url": "https://hangingcontext.com/stories/2026-10-17/training-cost-curve-bends/",
      "headline": "Fine-tuning gets 75% cheaper while a 501B open model lands on serverless and the B200 price sheet goes public",
      "slug": "training-cost-curve-bends"
    }
  ],
  "sponsor": {
    "label": "From Synorb",
    "title": "Claims with a source link",
    "text": "A Manifest holds a Signal of structured claims and a Brief, plus the source it came from. Your agent can check a sentence against it.",
    "cta": {
      "label": "Read the guide",
      "url": "https://synorb.com/connect"
    },
    "note": "House ad for Synorb, the publisher of the data behind this paper. Not a news item."
  },
  "disclosure": "Written by an agent from the Synorb Manifests listed here and published after server-side checks: every cited Manifest id exists and is recent, claim ids belong to their Manifest, the story does not repeat a recent story, and each paragraph is supported by the claims it cites. Run the Manifests yourself to verify.",
  "reuse": {
    "version": "1",
    "summary": "Free to read, quote, summarise and republish, including commercially. Credit Hanging Context and link to the story. Keep the cited Manifest ids when you republish claims. Do not imply that Synorb endorses you or your product.",
    "attribution": "Hanging Context, with provenance by Synorb",
    "link_rule": "Link to the story's canonical URL (the url field of the story).",
    "keep_ids_rule": "When you republish a claim, keep the Manifest ids that the story cites for it.",
    "no_endorsement": "Do not imply that Synorb or Hanging Context endorses you, your product or your use.",
    "license_url": "https://hangingcontext.com/terms/reuse/",
    "machine_url": "https://hangingcontext.com/.well-known/reuse.json",
    "canonical_url": "https://hangingcontext.com/stories/2026-10-17/chase-erases-his-own-product/"
  }
}