Inside Startup Due Dil: the AI tool turning hours of VC diligence into 10 minutes

Vlad Tislenko, a partner at Ukrainian venture capital firm SMRK VC, launched Startup Due Dil on August 25, a web application that automates the collection, verification, and structuring of information during startup due diligence, per Tech.eu. The platform cost less than €1,000 to build and began as an internal tool Tislenko created to support his own investment assessment work.

The system orchestrates ten AI agents that analyse pitch decks, supporting documents, and public sources before producing a structured report, according to Tech.eu. Nine specialist agents each cover a distinct area — team and founders, market, competitors, technology and product, traction and financials, business model, regulatory compliance, ownership structure and cap table, and legal considerations. A tenth agent, called Oracle, acts as orchestrator: it plans the diligence process, provides context to the specialist agents, evaluates the completeness of their outputs, and can rerun any agent with additional context if results fall short. The final report flags findings in red, yellow, and green categories, ranging from material risks to verified positive signals, and includes source citations throughout.

To start an analysis, a user uploads a pitch deck; for deeper review, they can also supply financial statements, a cap table, legal documents, and links to additional sources. The platform then cross-references claims in the submitted materials against public sources. Tislenko told Tech.eu that one pattern the tool surfaces repeatedly is founders overestimating market size — figures the system frequently cannot verify.

SMRK VC focuses on Ukrainian technology startups, and Tislenko's portfolio work there includes Esper Bionics, Deus Robotics, Osavul, Ability.ai, and Principle. Before joining SMRK, he was a technology entrepreneur who led Concepter until its exit in 2021. He said he built Startup Due Dil partly to deepen his own understanding of AI progress, "so I can make better investment decisions in the AI space and give better advice to portfolio companies," as quoted by Tech.eu.

On data privacy — a significant concern given the confidential financial, legal, and ownership information involved — Tislenko says administrative dashboards do not display private workspace content and developers do not have access to user files or reports. The current version runs on the OpenAI API, with architecture that also supports Anthropic. OpenAI may retain API inputs and outputs for up to 30 days, per Tech.eu, though Tislenko said he designed the system so that neither OpenAI nor Anthropic use customer materials for model training.

Startup Due Dil is currently used in SMRK's own investment work and is being tested by other investors. It is aimed primarily at venture capital and private equity firms evaluating early-stage technology companies, though startups can also run a one-off analysis to assess their readiness before a fundraise. Tislenko frames the tool as a complement to, not a replacement for, human judgment — reference checks and founder conversations remain, in his view, essential parts of the process.