--- title: The agent company has a shape now: small team, harness, and a kill list description: Box's Levie, LangChain's internal agents, Revolut's automation and a VC portfolio all point to the same operating model for running agents inside a company. canonical: https://hangingcontext.com/stories/2026-10-26/companies-build-agent-harness/ last-updated: 2026-10-26 url: https://hangingcontext.com/stories/2026-10-26/companies-build-agent-harness/ published: 2026-10-26T00:29:42Z edition: 2026-10-26T00 newsroom: artificial-intelligence beat: infrastructure trust: confirmed source_count: 4 cited_manifest_ids: ['1792929259294830435', '1792958322312422244', '1792920002427266942', '1792962335654138943'] --- # The agent company has a shape now: small team, harness, and a kill list *Box's Levie, LangChain's internal agents, Revolut's automation and a VC portfolio all point to the same operating model for running agents inside a company.* Confirmed · 4 sources · Artificial Intelligence · Published 2026-10-26 00:29 UTC ## Key facts - Aaron Levie says a 3-10 person startup team using AI agents can produce the output of a 50-200 person company, and that the founder bottleneck has shifted to managing and reviewing agents. [cites: 1792929259294830435] - LangChain describes five primitives for an internal agent harness: platform integration, identity, memory tiers, sandboxed execution, and scheduled or event-triggered runs. [cites: 1792958322312422244] - Revolut says it has automated 90% of its customer support team using AI and increased engineering speed by 30% with AI tools; it is developing a foundational model called Pragma trained on transactional data. (self-reported) [cites: 1792920002427266942] - Social Leverage reports Sunlight AI raised $17.4 million in seed funding and Elio Mortgage raised $5.1 million; Fiscal.ai launched Agentic Estimates with an API and MCP covering nearly 10,000 stocks. (self-reported) [cites: 1792962335654138943] ## The bottleneck moved Box chief executive Aaron Levie argues that the founder's job has changed shape. He says a team of 3 to 10 people using AI agents can now produce the output of a company of 50 to 200 people, and that the bottleneck for founders has shifted from doing the work themselves to managing and reviewing the agents that do it. Levie calls the current startup environment the most different from previous eras that he has seen in 27 years. [cites: 1792929259294830435] Levie expects hundreds of new companies worth $1 billion to $10 billion or more to be built on automating specific job functions with AI agents, and he says AI progress is currently more valuable for enterprise use cases than for consumer ones. He also argues that large incumbents will struggle to adopt agents because their existing processes are too rigid, and that AI does not fundamentally change the distribution model for startups. [cites: 1792929259294830435] His prescription for builders is specific: the best way to build an agent startup is to have a founder with deep, direct experience in the exact job function being automated. That claim is worth holding against what companies actually report doing internally, because the inside of an agent deployment looks less like a single clever model and more like plumbing. [cites: 1792929259294830435] > **From Synorb** — Ask what Synorb covers. The MCP tool synorb-stream-search answers questions like "do you have this publisher?" without using any Manifest allowance. [Connect and ask](https://synorb.com/connect/start) ## Five pieces every harness needs LangChain's account of its own internal agents describes five primitives that a company harness has to get right. The harness must integrate with existing communication platforms like Slack. It must settle identity: agents act either on behalf of a user or under fixed service-account credentials. It must use both global and user-specific memory tiers. It must run code in sandboxed environments connected to secret proxies. And it must handle the fact that a large percentage of agent runs are scheduled or triggered by background events rather than started by a person. [cites: 1792958322312422244] The examples make the primitives concrete. LangChain says its GTM Agent monitors emails, responds to leads and sends daily briefs; OpenSWE drafts and reviews pull requests; and Content Studio drafts marketing assets including blogs, images and videos. Agents can break out into their own Slack threads so they do not pollute human conversations, and LangChain says its Managed Deep Agents product provides infrastructure for channels, crons, sandboxes, memory and identity, with LangSmith used for debugging decisions, evaluating changes and one-click deployment. [cites: 1792958322312422244] Identity turns out to be the decision that shapes the rest. OpenSWE acts on behalf of the user when messaged, but uses its own identity for background code reviews, while Content Studio uses fixed credentials for Twitter, restricted to a whitelisted set of users. The pattern is that one harness serves several identity models at once, chosen per task rather than per company. [cites: 1792958322312422244] ## The same pattern at Revolut Revolut chief executive Nik Storonsky describes a version of the same operating model at much larger scale. He says Revolut has automated 90% of its customer support team using AI, and that its engineering speed has increased by 30% because of AI tools. The company is also developing a foundational AI model called Pragma, trained on transactional data. Storonsky says he aims to build the number one bank in at least 100 countries, and that fintech companies without a banking license are relegated to niche audiences. [cites: 1792920002427266942] Storonsky's management method echoes the harness logic: Revolut uses a staging process where bets are funded, tracked and sunsetted if they fall into the bottom 25% of performance. He also argues that professional chief executives in banking are inherently risk-averse and prioritize job protection over innovation, which is his explanation for why founder-led companies move faster. His own venture fund, Quantum Light, uses machine learning models to select investments, so the automation story extends to capital allocation itself. [cites: 1792920002427266942] ## The portfolio evidence The venture portfolio news points the same way, at smaller scale. Social Leverage reports that Sunlight AI raised $17.4 million in seed funding to help independent medical practices manage their business operations, and that Elio Mortgage raised $5.1 million after rebranding from Boost Mortgage. Fiscal.ai, another portfolio company, launched Wall St. Estimates and Agentic Estimates, with an API and MCP that provide estimates on nearly 10,000 stocks. The firm also says it is integrating AI throughout its own tech stack. [cites: 1792962335654138943] This suggests the agent-era company is converging on a recognizable shape: a small team, a founder who knows the job being automated, a harness that handles identity, memory, sandboxes and scheduling, and a ruthless process for killing bets that fall behind. The open question is whether that shape works as well outside coding and support, where the tasks are less structured and the failure modes are harder to see. Levie's own caveat is relevant here: incumbents struggle not because they lack models, but because their processes are rigid, and a harness is, in the end, a process. [cites: 1792929259294830435, 1792958322312422244] ## What is still unresolved - Whether the small-team output claim holds outside coding and customer support, where tasks are less structured. - Whether Revolut's Pragma model ships and what it is used for beyond internal automation. - Which identity model — on-behalf-of or service account — becomes standard for background agent work. ## Decision card - **Useful for:** Founders designing an internal agent deployment; Operators choosing identity and memory models for agents - **Not for:** Teams buying a single agent product off the shelf - **Compare against:** Hiring for the automated function; Outsourcing the workflow to a vendor ## Provenance ledger | Manifest id | Title | Source | Claims used | Published | |---|---|---|---|---| | `1792929259294830435` | The New Startup Playbook \| Box CEO Aaron Levie | [andreessen-horowitz-a16z-show-podcast](https://a16z.simplecast.com/episodes/the-new-startup-playbook-box-ceo-aaron-levie-I0FN5_nv) | 1792930024961995163, 1792930024965065978, 1792930024976028103, 1792930024969122952, 1792930024970534884, 1792930024967434178, 1792930024972626092, 1792930024974668021 | 10-25 00:00 | | `1792958322312422244` | The five components of building a "company harness" | [langchain-blog](https://langchain.com/blog/components-building-company-harness) | 1792958776777288769, 1792958776779878554, 1792958776780903866, 1792958776783186111, 1792958776785646842, 1792958776787776728, 1792958776788900350, 1792958776789838741, 1792958776791715555, 1792958776811126977, 1792958776817382006, 1792958776799482494, 1792958776805284906 | 10-24 00:00 | | `1792920002427266942` | Competition, Intensity & Building a $115 Billion Global Bank \| Nik Storonsky, Revolut | [david-senra](https://davidsenra.com/nik-storonsky) | 1792920905716043742, 1792920905717823591, 1792920905719968803, 1792920905708798185, 1792920905711792387, 1792920905714966432, 1792920905713848398, 1792920905722683025 | 10-25 00:00 | | `1792962335654138943` | Sunlight Emerges & Fiscal Estimates | [social-leverage-blog](https://socialleverage.com/stories/sunlight-emerges-fiscal-estimates) | 1792962634198682635, 1792962634203828361, 1792962634194462375, 1792962634196627073, 1792962634200376173, 1792962634202870507, 1792962634192905822, 1792962634189250992 | 10-25 00:00 | ## Run these Manifests yourself Every Manifest cited here can be read in full with your own Synorb Key. Check the claims before you rely on them. 1. **Get a Synorb Key.** Click Generate Free Agent Key at https://synorb.com/connect/start, 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. 2. **Read each cited Manifest by id.** REST: `GET https://api.synorb.com/manifests/by-id/{manifest_id}` with the header `Authorization: Bearer `. Ids are strings; do not parse them as numbers. The reply holds the source, the Signal (claims) and the Brief. 3. **Check the claim.** Match each sentence in the story to the claims in the Manifest it cites. The claim ids in the ledger point to them. Cited Manifest ids: - `1792929259294830435` - `1792958322312422244` - `1792920002427266942` - `1792962335654138943` ```sh for id in 1792929259294830435 1792958322312422244 1792920002427266942 1792962335654138943; do curl -s -H "Authorization: Bearer $SYNORB_KEY" "https://api.synorb.com/manifests/by-id/$id" done ``` > **From Synorb** — Run the cited Manifests yourself. Every claim in this paper points to a Manifest id. Get a Synorb Key and read the Manifests behind it. 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. [Get a key](https://synorb.com/connect/start) ## Related stories - [The Agent Shift Is a Jobs Story: Founders Orchestrate, Workers Retrain, Labs Automate](https://hangingcontext.com/stories/2026-10-25/agents-change-work/) - [AI Drug Discovery Gets a Deal, a Candidate, and an Agent Pipeline](https://hangingcontext.com/stories/2026-10-25/ai-drug-discovery-pipeline/) - [TARSphere, HyperDrone, BrickWright, and robot navigation training all measure what agents do in a world, not what they say about it](https://hangingcontext.com/stories/2026-10-24/embodied-agents-execution-benchmarks/) - [Sub-2B models are doing real work: permissible-data reasoning, Vietnamese and Arabic distillation, edge compression](https://hangingcontext.com/stories/2026-10-24/small-models-real-work/) ## Links - HTML: https://hangingcontext.com/stories/2026-10-26/companies-build-agent-harness/ - JSON: https://hangingcontext.com/stories/2026-10-26/companies-build-agent-harness/index.json - Markdown: https://hangingcontext.com/stories/2026-10-26/companies-build-agent-harness/index.md 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 (terms v1): 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. Credit: "Hanging Context, with provenance by Synorb", with a link to https://hangingcontext.com/stories/2026-10-26/companies-build-agent-harness/. Terms: https://hangingcontext.com/terms/reuse/