AI Patent Drafting with Example-Based Customization

AI is changing how patent prosecution gets done, and the upside is real. So are the downsides: hallucinated citations, confidentiality exposure, export-control pitfalls, and prosecution-history estoppel. This is an honest account of the risks of AI patent software in prosecution, and what actually reduces each one.

Key takeaways

• Anyone presenting AI-assisted content to the USPTO must reasonably review it; relying on the tool's accuracy alone is not enough.
• Courts have already sanctioned attorneys for AI-hallucinated citations, and similar risk applies to office-action responses and PTAB briefs.
• The USPTO warns that AI tools on foreign servers can raise export-control, foreign-filing-license, and national-security problems.
• Grounded citations, exposed reasoning, zero data retention, and attorney oversight are what materially reduce AI risk in patent prosecution.

Solve Intelligence is proud to share that Maiwald, one of Germany’s largest and most progressive intellectual property firms, works with Solve Intelligence on selected AI-supported workflows in its patent and legal practice groups. Following an evaluation period during which selected functionalities were assessed for approved internal use cases, Maiwald and Solve have formed an enterprise partnership for 2026.

The rollout reflects the same careful approach Maiwald brings to its client work. Solve enables customers in Europe to process data on servers located within Europe and holds recognized information-security certifications. In addition, Solve offers contractual commitments designed to protect confidential professional information in line with applicable statutory confidentiality obligations and professional conduct requirements. Against that background, any use of AI-supported tools took place only within approved governance structures and under applicable professional, contractual, confidentiality and data-protection requirements.

That balance of innovation and professional judgment is characteristic of Maiwald. The firm has spent decades setting a standard for IP work in Europe: rigorous prosecution, a formidable contentious practice, and interdisciplinary teams of patent attorneys and attorneys-at-law working side by side. The firm approached AI the same way, methodically, with a clear sense of where it adds leverage and where an experienced attorney’s judgment remains irreplaceable. 

This article is the second of a series of Patent Trial & Appeal Board (PTAB) case studies (see Part I), which aims to inform applicants’ approach to satisfying the written description and enablement requirements for patenting artificial intelligence (AI) and machine learning technologies.

Both in-house teams and outside counsel can let a purpose-built platform carry the shared foundation for their patent work. They can then focus their limited time on the standards and judgment that set their work apart. AI has made this division of labor more valuable by raising the payoff for turning a practice into templates, instructions, and review criteria that run at scale. Let’s call that codification. The platform can encode a great deal of best practice out of the box, and a team can add its own custom templates and instructions on top. The real question is how much to add and how much to leave to the platform. There is no fixed formula because the right balance changes as the team’s practice, the law, and the technology evolve.

‍Key takeaways

• AI has raised the payoff for codifying patent practice. Codification now guides AI-assisted drafting and review directly, not just junior training.

• A purpose-built patent platform can encode a large body of best practice out of the box, so a team can begin with that foundation rather than write its own.

• Solve Intelligence maintains its shared foundation across more than 700 IP teams, keeping it current far more efficiently than any single team could alone.

• The strategic choice is how much of your own practice to codify on top; scarce expert time should go to the standards and judgment that differentiate your work.

• A named professional still signs off on every filing, so accountability for the result never shifts to the AI.