Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harn
Frontier LLM agents are automating many business tasks, but their high inference cost makes large-scale deployment unsustainable. Small language models (SLMs) offer a cheaper alternative, yet they typically fall short when swapped into a ha
https://arxiv.org/abs/2607.08938v1 ↗Thesis fit
Good fit
Within your typical scope; diligence still required.
In your usual scope
Idea match
Moderate
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 ↓ declining
▸ Add / edit details
Correct facts used on the next screening or memo.
People
C
Chenyang Yang
1.0
low confidence
X
Xinran Zhao
1.0
low confidence
T
Tongshuang Wu
1.0
low confidence
C
Christian Kästner
1.0
low confidence
Activity & evidence
Similar baseline plays (YC · idea space)
Guide Labs
· Active
Frontier models and agents you can learn from, audit, and steer.
founders not scraped yet
Clarum
· Active
AI agents for private market diligence, monitoring, and reporting
founders not scraped yet