Critino

This is the story of how Critino is redefining AI Training.

Who We Are

At Startino, we’re on a mission to innovate within the AI space. Led by CEO Jorge Lewis and CTO Jonas Lindberg, we specialize in two key areas: building groundbreaking AI products and helping non-technical entrepreneurs launch MVPs and SaaS solutions. Our latest innovation, Critino, emerged from a need to tackle one of the most persistent challenges in AI: aligning large language models (LLMs) with human intentions.

The Challenge

While working with a client to create a life coach AI, we hit a wall. The traditional method of guiding LLMs. Prompt engineering was cumbersome and ineffective. Crafting detailed instructions consumed hours, yet still left critical edge cases unresolved. Worse, minor changes to prompts often derailed past improvements, leaving us without confidence in the AI’s behavior.

We realized the market was saturated with companies reusing existing solutions instead of innovating. To stand out, we needed a fresh approach that addressed these issues head-on.

The Solution: Critino

Critino is our solution to making LLMs behave in ways consistent with human expectations. By combining two fundamental concepts: few-shot learning with semantic search, Critino is able to use concrete examples (“critiques”) to guide AI responses. This shifts the focus from abstract rules in prompts to real-world examples, improving both consistency and alignment. With Critino, we were also able to enable reinforcement learning of the AI agents that used it, like in Reletino, to allow users to train their agents over time.

How Critino Works

1. Concrete Examples Over Abstract Rules:
2. Critiques replace vague, high-level instructions with specific examples of desired behavior. For instance, if a user’s AI handles customer complaints, a critique might include a sample query, context, and the optimal empathetic response.
3. Structured Critique Format:
4. Every critique includes:
5. • Context: Detailed context if required to set the scene for the query.
   • Query: The input the AI needs to answer.
   • Optimal Response: The ideal reply to the query.
   • Situation: A general description of the situation for future use in semantic search.
6. These are subject to, and likely will change as we continue to explore improvements to the platform. But fundamentally, the concept of semantic search to give an LLM relevant examples remains.
7. Semantic Search Integration:
8. Critino’s semantic search ensures that LLMs generalize effectively by matching new queries with relevant critiques.
9. Scalability:
10. As users add more critiques, they aren’t limited by context size. Each new critique adds to the available examples that can be referenced, enabling the system to handle an ever-growing range of situations and use cases.

Results

In a quick proof of concept (PoC), Critino demonstrated its ability to address key challenges and deliver meaningful results. After refining the platform and implementing core features like authentication and API integration, we launched an MVP that’s ready to transform AI training. Currently, Critino is being used in all our project, including Reletino Because the principles behind Critino are so fundamental in LLM applications, we’re excited to use Critino in future projects to save us time and efforts while improving the ability to train agents from feedback.

Lessons Learned

1. Master the Fundamentals:
2. A deep understanding of how LLMs work, "predicting the next word", enabled us to identify that examples often outperform instructions in teaching desired behavior.
3. Build Fast, Iterate Faster:
4. Shipping a PoC quickly allowed us to validate Critino’s potential and refine its capabilities based on real feedback.
5. Focus on Unique Value:
6. While Critino’s concept could be replicated, by keeping Critino affordable and continuously innovating, we’re building a product that people will want to use, not reinvent.

What’s Next for Critino

We’re just getting started. Critino is evolving to include:

• Automated Critique Generation: Leveraging AI to create critiques from historical data or user feedback, like YouTube videos or blog articles.
• Deeper Fine-Tuning Integration: Combining critiques with fine-tuning to achieve unparalleled model performance.

Conclusion

Critino represents a bold step forward in making AI more aligned with the desired goals. By focusing on concrete examples, semantic search, and rapid scalability, we’ve created a platform that not only solves today’s alignment challenges but also sets the stage for future innovation.