AgentCheck: A Reproduce-Intervene-Mitigate Workbench for LLM Agents over MCP
Tool-using LLM agents are mostly evaluated assuming all tools work. When a tool times out, returns a week-stale value, or has its description poisoned in deployment, the developer needs a controlled way to reproduce the failure, test a fix,
https://arxiv.org/abs/2607.11098v3 ↗Thesis fit
Good fit
Within your typical scope; diligence still required.
In your usual scope
Idea match
Light
How close the company’s idea is to your thesis statement
Sector
agents, llm, ai
Overlap with sectors you care about
Geography
Unknown
Location unknown — scores 0
Your thesis: “We back exceptional technical founders building AI-first products and infrastructure, deploying $100K checks within 24 hours.”
Founder → stable
Traction → stable
Idea vs market → stable
▸ Add / edit details
Correct facts used on the next screening or memo.
Activity & evidence
Similar baseline plays (YC · idea space)
Nir Gazit
Gal Kleinman
Coasty
· Active
The computer-use agent that doesn't break on real software. We will…
founders not scraped yet
Arga Labs
· Active
Real-world sandboxes to test agents and agent-facing software
founders not scraped yet
Shreyas Kaps
Rohan Kulkarni