Building Madeline-s1, a World Class Reasoning Model

Madeline & Co. is an end-to-end AI-powered strategy, design, and innovation platform that helps anyone, from in-house teams and founders to marketers and creatives, navigate complex decisions with clarity and confidence.

When initially building out their product suite, Madeline & Co. tried off-the-shelf large language models (LLMs); however, they constantly ran into issues of high inference costs, poor performance at scale, and inconsistent accuracy for their specific domains. The accuracy issues they faced primarily revolved around a lack of context-specific reasoning, cross-disciplinary synthesis, and brand-safe output.

This dissatisfaction with LLMs led Madeline & Co. to partner with Arcee AI in building a custom reasoning model that could reason with depth, align with internal frameworks, and operate with the flexibility needed for creative and strategic exploration.

After 2 months of training, the joint team presented Madeline-s1, a 32-billion-parameter reasoning model explicitly trained to reflect how Madeline expert strategists and designers think, mapping tradeoffs, surfacing multiple valid options, and grounding decisions in strategic insights  and customer   research. Rather than producing templated or generic answers, we engineered Madeline-s1 to generate meaningful interpretations and actionable insights across disciplines.

The model's performance exceeded expectations in internal evaluations, particularly in domains where general models struggled. Madeline & Co. deployed Madeline-s1 into production and integrated the model across their core product offerings.

Arcee AI used its expertise in open-weights models and its advanced training stack to deliver a state-of-the-art model that outperforms the best OpenAI and Anthropic models.