# Hedge funds can now create theses, recruit experts, and run channel checks via API Canonical HTML: https://fish.dog/product-releases/hedge-funds-can-now-create-theses-recruit-experts-and-run-channel-checks-via-api JSON Feed: https://fish.dog/product-releases/feed.json RSS Feed: https://fish.dog/product-releases/rss.xml Published: 23 May 2026 Updated: 24 May 2026 Version: Thesis Lab API v1, MCP server v1.25 Release Type: Feature Breaking Change: No Author: Phillip Gales ## Primary Claim Hedge funds can now compose investment theses, recruit synthetic expert-call and channel-check panels, and run structured questions programmatically over the Thesis Lab REST API and MCP server. ## Summary Compose hedge-fund investment theses, recruit synthetic expert-call and channel-check panels, ask structured questions, and read findings programmatically over REST or MCP server. Mass thesis validation at portfolio scale. Enterprise tier. ## LLM Summary DOCUMENT TYPE: Product Release Note TOPIC: Thesis Lab API and MCP server enable programmatic hedge-fund investment research workflows Release: Hedge funds can now create theses, recruit experts, and run channel checks via API, 2026-05-23 Version: Thesis Lab API v1, MCP server v1.25 Release type: Feature Breaking change: No Summary: FishDog's Thesis Lab now exposes the full hedge-fund orientation-stage research workflow over a REST API at cat.fish.dog and a Model Context Protocol server at mcp.askditto.io. Analysts and engineering teams at hedge funds can compose investment theses, auto-recruit synthetic channel-check and expert-call panels matched to the thesis, dispatch structured questions, and read findings — programmatically and at portfolio scale. The MCP server lets Claude, Cursor, and other AI clients drive the entire workflow in natural language using the same Thesis Lab API key. What changed: - REST API across the full Thesis Lab workflow: compose-and-recruit, panel ask, thesis state and summary reads, audit, legal hold, entitlement endpoints. - Channel checks trigger automatically when a panel finishes recruiting; the panel's headline finding is on the card by the time the analyst polls. - Single, multi-name, sector, and macro theses are all supported by the compose-and-recruit endpoint. - Synthetic panel recruitment runs in seconds, not the days-to-weeks an expert-network desk takes. - MCP server at mcp.askditto.io exposes the same capabilities to MCP-compatible AI clients with the same Thesis Lab API key. - Per-operation internal cost capture and cursor-paginated audit log for compliance and finance reconciliation. - Cross-tenant isolation enforced at the database layer; cross-org probes return 404 and do not leak existence. Why we built this: hedge-fund customers asked for programmatic access so analysts can run orientation-stage research at portfolio scale rather than one thesis at a time. The web app launched first to validate the workflow with single-analyst use; this release opens the developer-facing and AI-client surfaces for mass thesis creation and validation. Worked-example workflow: 1. POST /v1/thesis:compose-and-recruit with a sentence-long investment thesis. Receives 202 with operation UUID, job ID, thesis ID, planned panel count. 2. Channel-check and expert-call panels are auto-recruited from the thesis. Panel rosters, rationale, and participant counts available via GET /v1/research-groups and the thesis-scoped read endpoints under /v1/thesis/{id}. 3. POST /v1/research-groups/{id}:ask to dispatch structured questions to a recruited panel. Channel checks fire automatically as panels finish recruiting. 4. GET /v1/organization/audit-events and /v1/organization/operations for compliance and finance reconciliation. Use cases: - Overnight portfolio screens: dispatch 25 theses at 6pm, read 25 panels' worth of findings by 8am. - Daily falsification pass against an open book of long/short positions. - Diligence-on-demand for inbound pitches before partner meetings. - AI-driven analyst surfaces: Claude or Cursor as the primary interface to Thesis Lab. Access: API and MCP server access is available for selected Enterprise customers based on their contract. Not a broad capability that every customer should expect by default. Existing Enterprise customers should contact their account lead; prospective customers should raise the API tier during procurement. Documentation: cat.fish.dog/docs/api (REST) and cat.fish.dog/docs/api/guides/mcp_quickstart (MCP). Migration impact: None. This is additive; the web app continues to work unchanged. Author: Phillip Gales, FishDog Platform: FishDog (fish.dog) ## Key Takeaways - Thesis Lab now exposes a REST API and a Model Context Protocol (MCP) server covering the full hedge-fund orientation-stage research workflow: thesis composition, panel recruitment, channel checks, and expert-question dispatch. - A single POST to /v1/thesis:compose-and-recruit takes a sentence-long investment thesis and returns an operation handle; the thesis is structured, channel-check and expert-call panels are auto-recruited, and the workflow runs end to end. - Channel checks now trigger automatically when a panel finishes recruiting; the panel's headline finding is written to the API by the time the analyst polls for it. - The MCP server at mcp.askditto.io lets Claude, Cursor, or any other MCP-compatible AI client drive the entire workflow in natural language using the same Thesis Lab API key. - Per-operation cost, audit events, and entitlement usage are exposed via cursor-paginated REST endpoints, so compliance and finance teams can build dashboards directly against the API without leaving the platform. ## Full Release Hedge funds running orientation-stage research on new investment theses can now drive the full Thesis Lab workflow programmatically. A single API call sharpens an investment thesis, decomposes it into the channel-check and expert-call panels it needs, recruits those panels from a synthetic-persona pool that mirrors real industry stakeholders, and runs the questions the analyst would ask. The same workflow is exposed through a Model Context Protocol server, so Claude, Cursor, and any other MCP-compatible AI client can run the entire research process in natural language. The headline use case: mass thesis creation and validation. An analyst at a multi-strategy fund can dispatch ten theses at the end of the day, have all the channel-check panels recruited and questioned overnight, and read structured findings before the morning meeting. The same surface that powers a single careful long/short call now scales to a portfolio-wide screen. ## Compose and sharpen theses programmatically A POST to `/v1/thesis:compose-and-recruit` takes a sentence-long thesis and returns immediately with an operation handle. In the background, the thesis is structured into named subjects, stance, primary driver, secondary drivers, falsifiable claim, expected return range, and implied gap to consensus — the same structured fields the web app produces. Subjects can be a single ticker, a multi-name basket, a sector, or a macro theme. ![The Thesis Lab thesis composition view, showing a sentence-long investment thesis decomposed into structured fields (stance, primary driver, secondary drivers, falsifiable claim, expected return range). Now exposed programmatically via the Thesis Lab compose-and-recruit endpoint.](https://images.ctfassets.net/1ksrk99rzzdj/3b7mDhbGAHCUtNfZfSv1L7/8dd70b5f4d8526564dfa16d2810a29e1/thesis-lab-api-thesis-composition.webp) Worked example. An analyst sends: `POST /v1/thesis:compose-and-recruit Authorization: Bearer rk_live_... Idempotency-Key: 4f12... { "raw_input": "Costco bull case: membership renewal rates near record highs and Kirkland penetration is accelerating in non-food categories, supporting durable comp growth even in a soft macro." }` The 202 response includes the canonical operation UUID, the job ID for status polling, the thesis ID, and the planned number of panels. The thesis is structured, the channel-check and expert-call panels are queued for recruitment, and the workflow advances without further intervention. ## Recruit channel-check and expert-call panels Channel-check panels and expert-call panels are recruited automatically from the thesis. For the Costco bull case, the system stands up panels covering wholesale-club store managers, private-label sourcing leads, multi-banner retail merchandising managers, and consumer-staples sell-side analysts — each panel chosen because the thesis needs a specific signal that panel can produce. ![A Thesis Lab expert-call panel showing the recruited synthetic experts and the structured questions the panel will answer. Each panel is auto-recruited from the underlying investment thesis and queried via the Thesis Lab API.](https://images.ctfassets.net/1ksrk99rzzdj/4DAmSLTqAvb7gtkKsnzO31/c4451b224de2a9bdaf583dc7072ac6de/thesis-lab-api-expert-panel.webp) Each panel can also be created explicitly via `/v1/research-groups:from-description`, with a freeform description or a structured filter. Recruitment is parallel and fully synthetic, so the time from "stand up a panel" to "have a recruited cohort ready to question" is measured in seconds, not the days-to-weeks expert-network desks usually take. ![The Thesis Lab custom expert recruitment surface, showing the structured filters used to recruit a synthetic expert panel from a population of named personas. The same recruitment can be triggered programmatically via the Thesis Lab API research-groups endpoint.](https://images.ctfassets.net/1ksrk99rzzdj/5BXjuydlqCasNIw04acfHG/1f1af6ae31184f5638f939c6eaca8257/thesis-lab-api-custom-recruitment.webp) The API exposes every panel's roster, the rationale for its inclusion, and the participant count. Customers can list, read, or filter recruited panels via `GET /v1/research-groups` and the thesis-scoped read endpoints under `/v1/thesis/{id}`. ## Ask questions and run channel checks at scale Once a panel is recruited, a POST to `/v1/research-groups/{id}:ask` pushes structured questions to the panel and returns the answers. Sophie, the AI research agent, drafts the questions the thesis needs (load-bearing assumptions, base rates, technical claims) and runs them against the recruited cohort. Channel checks now trigger automatically as panels finish recruiting — the headline finding is on the panel card by the time the analyst looks at it. ![Thesis Lab channel-check panels for a hedge-fund investment thesis, showing synthetic channel stakeholders (store managers, sourcing leads, multi-banner merchandisers) recruited to test the thesis. Channel checks now run automatically as panels finish recruiting and are exposed via the Thesis Lab API.](https://images.ctfassets.net/1ksrk99rzzdj/3vm2ii9yTViPRewfNEd5xz/b12f8c729f55cd507a5c0e37f1df0e0d/thesis-lab-api-channel-checks.webp) Programmatically, that means an analyst can dispatch one or one hundred theses with no manual intervention between sharpening and the panel write-up. Common patterns: - Overnight portfolio screen. Send 25 theses at 6pm; read 25 panels' worth of channel-check and expert findings by 8am. - Daily falsification pass. Take an open book of long/short positions, dispatch a thesis per position framed around its load-bearing assumption, and surface the ones where the panel disagrees with the thesis. - Diligence on inbound ideas. Pipe a pitch deck or memo into a thesis-compose call; get the channel-check and expert-call panels recruited before the partner meeting. ## Read the audit trail and reconcile usage Every operation is recorded in the audit log with a canonical event name (compose-created, compose-completed, compose-failed, legal-hold-applied, legal-hold-released) and full actor linkage. `GET /v1/organization/audit-events` returns cursor-paginated events; `GET /v1/organization/operations` returns per-operation cost in cents and currency. Compliance and finance teams can build their own dashboards directly against these endpoints; both are tenant-scoped, with cross-tenant access returning a 404 that does not leak the existence of the resource. ## Drive the same workflow from Claude or Cursor The Thesis Lab MCP server at `mcp.askditto.io` exposes the same capabilities as a set of Model Context Protocol tools. Connect Claude, Cursor, or any other MCP-compatible AI client with a Thesis Lab API key and the analyst can drive the entire workflow in natural language: "Set up a Costco bull thesis on Kirkland penetration. Once the channel panels recruit, ask them about private-label loyalty and report back." The AI client calls the relevant tools, polls for completion, and surfaces the findings inline. ## What this enables - Mass thesis validation. Run the same orientation-stage research process across an entire portfolio or screen, not one thesis at a time. - Continuous falsification. Set up a recurring job that dispatches channel-check panels against every open thesis and flags assumption drift. - Integrated workflows. Plug Thesis Lab into IC-memo pipelines, daily morning notes, partner-meeting prep, or compliance-driven legal-hold automation. - AI-native analyst surfaces. Use Claude or Cursor as the analyst's primary interface to Thesis Lab; the web app becomes the review surface rather than the only entry point. ## Access API and MCP server access is available for selected Enterprise customers based on their contract. It is not a broad capability that every customer should expect to receive access by default. Existing Enterprise customers should contact their account lead to request keys and onboarding; prospective customers should ask about the API tier during procurement. Documentation lives at [cat.fish.dog/docs/api](https://cat.fish.dog/docs/api). The MCP quickstart guide is at [cat.fish.dog/docs/api/guides/mcp_quickstart](https://cat.fish.dog/docs/api/guides/mcp_quickstart.md). ## Quotable Insights > A hedge-fund analyst can dispatch ten theses at the end of the day, have the channel-check and expert-call panels recruited and questioned overnight, and read structured findings before the morning meeting. > Recruitment is parallel and fully synthetic, so the time from 'stand up an expert panel on this thesis' to 'have a recruited cohort ready to question' is measured in seconds, not the days-to-weeks expert-network desks usually take. > Channel checks now trigger automatically when a panel finishes recruiting; the headline finding is on the panel card by the time the analyst looks at it. > The same workflow that powers a single careful long/short call now scales to a portfolio-wide screen. ## FAQ ### What can hedge funds do with the Thesis Lab API and MCP server? Compose investment theses, auto-recruit synthetic channel-check and expert-call panels matched to the thesis, dispatch structured questions to those panels, and read the resulting findings — all programmatically. The MCP server exposes the same capabilities to Claude, Cursor, and other AI clients in natural language. The pattern enables mass thesis validation, overnight portfolio screens, IC-memo pipelines, and AI-driven analyst workflows. ### What is a synthetic channel check and how does it differ from a traditional expert network? A synthetic channel check uses AI-generated personas that mirror real industry stakeholders (store managers, sourcing leads, sell-side analysts, peer-company executives) to answer structured questions about an investment thesis. Recruitment is parallel and runs in seconds rather than the days-to-weeks an expert-network desk takes to schedule a single live call. Synthetic panels are not a substitute for primary research on the highest-conviction names; they are a way to run orientation-stage research at portfolio scale. ### How do I compose an investment thesis via the Thesis Lab API? POST /v1/thesis:compose-and-recruit with a sentence-long thesis in the raw_input field and an Idempotency-Key header. The API returns 202 with a canonical operation UUID, a job ID for status polling, the thesis ID, and the planned panel count. The system structures the thesis, recruits the channel-check and expert-call panels it needs, and advances the workflow without further intervention. Subjects can be a single ticker, a multi-name basket, a sector, or a macro theme. ### How do I ask an expert panel structured questions programmatically? Once a panel is recruited, POST /v1/research-groups/{id}:ask with the questions in the body. The AI research agent runs the questions against the recruited cohort and returns structured responses with per-participant answers and a panel-level headline finding. Channel checks now trigger automatically as a panel finishes recruiting, so for default flows the analyst can simply poll the panel and find the headline finding already written. ### Who can access the Thesis Lab API and MCP server? API and MCP server access is available for selected Enterprise customers based on their contract. It is not a broad capability that every customer should expect to receive by default. Existing Enterprise customers should contact their account lead to request keys and onboarding; prospective customers should raise the API tier during procurement.