A bet on a smaller LLM model that actually know Polish law
A bet on a smaller LLM model that actually know Polish law
A bet on a smaller LLM model that actually know Polish law
Stage
Startup
Stage
Startup
Industry
Legal Ai
Industry
Legal Ai
Timeline
Sep 2025 – Sep 2026
Timeline
Sep 2025 – Sep 2026
context
At the beginning I thought we were competing with other legal AI companies. It soon became clear how wrong I was, as every lawyer was using GPT, Gemini or Perplexity.
But wait, were they satisfied?
What could we do better than big tech?
context
At the beginning I thought we were competing with other legal AI companies. It soon became clear how wrong I was, as every lawyer was using GPT, Gemini or Perplexity.
But wait, were they satisfied?
What could we do better than big tech?
goal
In Sep 2025, Gaius had a team of five and a major problem with usability.
App’s language was very technical
The visual hierarchy was poor
and we didn’t know exactly what kind of person we serve
but
the value was working 🎉
50 law firms were paying to find the right supreme court case reference, a source based on their line of case law or similar facts. And that's something I would call a great beginning.
After couple of weeks of talking with clients (not only about sales) I knew exactly with what expectations they came:
Quicker legal research without hallucination
Upload documents with sensitive data without worry
“proper” Ai answers
Wait, what 'proper Ai' answer even means?
Of course it depends.
But we can still test the assumptions.
goal
In Sep 2025, Gaius had a team of five and a major problem with usability.
App’s language was very technical
The visual hierarchy was poor
and we didn’t know exactly what kind of person we serve
but
the value was working 🎉
50 law firms were paying to find the right supreme court case reference, a source based on their line of case law or similar facts. And that's something I would call a great beginning.
After couple of weeks of talking with clients (not only about sales) I knew exactly with what expectations they came:
Quicker legal research without hallucination
Upload documents with sensitive data without worry
“proper” Ai answers
Wait, what 'proper Ai' answer even means?
Of course it depends.
But we can still test the assumptions.
Challenges
Although Gaius-Lex offered dedicated workflows for legal professionals, a vast majority of users came looking for one thing: an AI assistant they could trust.
Unpredictable technology
The biggest challenge was fighting with models themselves. There were days were bugs surprised us each morning. A prompt that worked yesterday could fail a day after.
The expectation gap
Users expected the speed, quality, and pricing of products backed by multi-billion-dollar investments.
Everyone uses AI, no one understands it
People expected prompts like "Don't hallucinate the law" to guarantee accurate answers.
Others believed telling chat to "delete sensitive information” meant fulfilling their confidentiality obligations. Some expected the AI to "write more like a human" without providing examples or teaching the system what "human" meant for them.
Each ‘user error’ is a design opportunity.
Challenges
Although Gaius-Lex offered dedicated workflows for legal professionals, a vast majority of users came looking for one thing: an AI assistant they could trust.
Unpredictable technology
The biggest challenge was fighting with models themselves. There were days were bugs surprised us each morning. A prompt that worked yesterday could fail a day after.
The expectation gap
Users expected the speed, quality, and pricing of products backed by multi-billion-dollar investments.
Everyone uses AI, no one understands it
People expected prompts like "Don't hallucinate the law" to guarantee accurate answers.
Others believed telling chat to "delete sensitive information” meant fulfilling their confidentiality obligations. Some expected the AI to "write more like a human" without providing examples or teaching the system what "human" meant for them.
Each ‘user error’ is a design opportunity.
My impact
Identified friction points in the core user journey
Introduced a reactivation flow ("remind me about Gaius") alongside subscription-cancellation, used by 1 in 4 clients
Converting a multitude of unintuitive features into a cohesive application
Redesigned the interaction model between users and the sLLM-based agent, increasing the first-message rate by +31.6% absolute improvement (from 39.8% in Feb to → 71.4 % in June 2026) by new signups.
Ran small-scale tests instead of shipping full features
I discovered that token count was irrelevant to users until they ran out (validated via client conversations and smoke tests) which let us cut 20% of backlog tied to token-limit tasks
My impact
Identified friction points in the core user journey
Introduced a reactivation flow ("remind me about Gaius") alongside subscription-cancellation, used by 1 in 4 clients
Converting a multitude of unintuitive features into a cohesive application
Redesigned the interaction model between users and the sLLM-based agent, increasing the first-message rate by +31.6% absolute improvement (from 39.8% in Feb to → 71.4 % in June 2026) by new signups.
Ran small-scale tests instead of shipping full features
I discovered that token count was irrelevant to users until they ran out (validated via client conversations and smoke tests) which let us cut 20% of backlog tied to token-limit tasks
Get in touch
Local time in Gdańsk, Poland
🇵🇱 🇪🇺
© 2025 Fembot Studio 👾 by Zuzanna Adamczyk. All rights reserved.
Get in touch
Local time in Gdańsk, Poland
🇵🇱 🇪🇺
© 2025 Fembot Studio 👾 by Zuzanna Adamczyk. All rights reserved.
Get in touch
Local time in Gdańsk, Poland
🇵🇱 🇪🇺
© 2025 Fembot Studio 👾 by Zuzanna Adamczyk. All rights reserved.