Contents

Pages

Contact Griffin Labs

Neuromorphic autonomous labs for therapy discovery.

Highlights

  1. Designing high-impact autonomous labs is critical for accelerating therapy discovery.
  2. Current AI falls short. We built a neuromorphic Campaign Engine that outperforms frontier models at lab design.
  3. We want to build on the Campaign Engine toward autonomous labs powerful enough to discover preventive cures for all disease.

1 Campaign optimization

Before building an autonomous lab you must decide on a campaign.

Self-driving labs excel at accelerating biological discovery⁠—but only if human scientists give them the right search space. When the answer lies within narrow, well-defined constraints, AI can rapidly iterate through experiments to find it (the experiment loop).

For complex disorders like Alzheimer’s, there is no obvious, narrow search space. Choosing a direction⁠—whether targeting amyloid plaques, tau vaccines, or astrocyte aging⁠—requires completely different biological substrates, instruments, and interventions. Deciding which physical lab setup and search space to build in the first place is the campaign loop.

“If I want an innovative research program, even from frontier AI models I can only get AI slop or at best things that have already been tried before.”

— Senior Scientist @Edison Scientific

Figure 1

The campaign loop

CAMPAIGN LOOP Better interventions Better measurements Better biological substrates AI Interventions Measurements EXPERIMENT LOOP AI Biological system CAMPAIGN LOOP Better interventions Better measurements Better biological substrates AI Interventions Measurements EXPERIMENT LOOP AI

Optimize the campaign, not just the experiments inside it.

The campaign loop is used to improve the research setup itself.

Example campaigns

Intervention

Anti-amyloid antibody

Measurement

Plasma p-tau217

Substrate

iPSC cortical neurons

Impact index

82

The types of interventions, measurements, and substrate choices combine to define a campaign. Impact index values are illustrative.

2 Results

Results

For the campaign loop problem, our Campaign Engine⁠—trained for 2 hours on a consumer GPU⁠—performs better than frontier LLMs.

Figure 2

Performance in designing impactful research campaigns

Performance in designing impactful research campaigns (out of 20; higher is better)
System Score
Campaign Engine 12 of 20
Claude Fable 5.2 10 of 20
Claude Opus 5.5 7 of 20
Gemini Argon 7 of 20
GPT 6 Astra 6 of 20

3 Previous innovation

Previous innovation

Before developing Campaign Engine, which we want to scale as a startup venture, we started as a nonprofit research organization, seizing the best opportunities we saw for using AI to automate scientific discovery in biomedicine. That work produced the projects below.

Applied AI

SUMMIT

The world’s first self-updating, multiscale platform for biological simulations, unifying thousands of causal connections from the scientific literature in minutes rather than weeks.

Read about SUMMIT

Contact

Let’s build the campaign loop.

For investors, scientific collaborators, and prospective partners who want to get involved in using the Campaign Engine to automate therapy discovery.