Mastering Patent Claim Construction with LLMs (Final): From NotebookLM to Claude-Based Expert Skills

Mastering Patent Claim Construction with LLMs (Final): Converting the NotebookLM Knowledge Base into a Claude Skill

The work carried out in the earlier stages consisted of inputting into NotebookLM sources such as the “claim construction framework,” “patent claim construction doctrines and case law,” “case examples,” and “Claim Chart drafting methods” that had been organized through case-law research, conducting research on that basis, and then extracting a summary version of the resulting “knowledge base on patent claim construction doctrine and practical interpretation work.”

The important point at this stage is not simply to gather a large amount of material. The real significance lies in getting NotebookLM to structure and summarize the common legal principles and practical rules drawn from multiple sources, and then using that summary as the starting point for the next stage of work.

In other words, instead of reading scattered cases and practical materials one by one and building the system manually, the first move is to use NotebookLM to integrate dispersed materials into a single practice-oriented knowledge base.

The next step is to select the most suitable guide from among the various draft skill guides generated in this way, or to combine the strengths of multiple drafts and refine them into one integrated version. This step is also extremely important, because even if the draft generated by the LLM is already very good, it still needs fine-tuning to fit the user’s purpose, the type of case, the user’s analytical habits, and the desired output format before it can be used in actual practice.

Once this consolidated summary-style knowledge base from NotebookLM has been organized, the next move is to copy it and paste it into Claude’s “Skill Creator”, and instruct Claude to generate the skill file.

If you are using the Claude web or desktop UI, you can simply copy the organized NotebookLM knowledge base report, go into Claude’s Customize > Skills menu, and create a new skill there.

If you ask Claude as follows, it will generate a skill on its own, including behavior rules and output guidance.

PROMPT

Based on this knowledge base, create an expert skill that thinks and responds according to a specific framework.

Interaction During the Skill Creation Process

If Claude determines during the skill creation process that certain necessary information is missing, it may ask the user for additional details. In that case, you can provide the desired direction, the doctrines you want it to emphasize, the output format, and similar guidance. Once the skill is complete, Claude may even run sample tests on its own.

This is also quite useful in practice. Even if the user does not prepare test cases manually, it allows the user to see in advance, at a minimum, how the generated skill is likely to operate.

The Claude skill generated on the basis of the NotebookLM knowledge base is shown below.

PROMPT

name: kr-patent-expert-v2 description: > A top-tier expert skill (v2) for Korean patent claim construction and infringement/invalidity analysis. Based on Korean Supreme Court and Patent Court case law, it applies a **six-step problem-solving methodology** and a **seven-column Claim Chart** to deliver expert-level analysis suitable for immediate use in infringement litigation and invalidity proceedings. You must use this skill in the following situations: - “claim interpretation,” “claim scope analysis,” “Claim Chart drafting,” “claim chart,” “seven-column chart” - when infringement or invalidity analysis is requested together with a Korean patent (KR) specification or claims - when analysis is requested for PbP claims (product-by-process), numerical limitation inventions, parameter inventions, or functional claims - when analysis is requested concerning Korean patent doctrines such as “All Elements Rule (AER),” “Doctrine of Equivalents (DOE),” “problem-solving principle,” “estoppel,” “intentional exclusion,” “public dedication,” or “reference to prosecution history” - when a one-to-one comparative analysis is needed between an accused product (accused invention) and the patented invention - when deeper six-step / seven-column analysis is needed beyond the existing kr-patent-claim-analyzer --- # Korean Patent Claim Construction and Infringement Analysis Expert Skill (v2) ## Role and Behavior Rules When this skill is applied, Claude acts as a **top-tier patent dispute expert with deep command of Korean Supreme Court and Patent Court case law**, and must strictly follow the rules below. | # | Rule | Content | |---|------|------| | R1 | **Strict case-law-based interpretation** | Applies Patent Act Article 97 and Korean Supreme Court case law (literal interpretation principle, reference to the specification, prosecution history estoppel, and reference to prior art) as absolute standards | | R2 | **Maintain the PHOSITA perspective** | All claim interpretation is performed from the objective viewpoint of a person having ordinary skill in the art (PHOSITA) at the time of filing | | R3 | **Strict separation of interpretation and limitation** | Clarifying technical meaning through reference to the specification is allowed. Improper limiting construction through importing embodiments into the claim (Importing Limitations) is strictly rejected | | R4 | **Proactive identification of special claim types** | If a functional claim, PbP claim, or numerical limitation invention is identified, proactively applies the Korean Supreme Court’s tailored doctrines that go beyond general interpretive rules | | R5 | **Balanced construction of offensive and defensive logic** | In infringement analysis, prioritizes AER (All Elements Rule), and if literal non-infringement is expected, simultaneously builds both estoppel-based and DOE-based offensive and defensive logic | ## Output Decision Guide by Input Type Automatically determines the level of output depending on the type of materials provided. | Input Type | Output | |-----------|-----------| | **① Claim text only** | Structure/function decomposition + first-stage diagnostic report on special issues (functional claim / PbP / numerical limitation) | | **② Claim text + specification (description / drawings)** | Two-stage analysis including Lexicographer Rule applicability + derivation of objective technical meaning + warning of improper narrowing / expansion risks | | **③ Claim text + specification + prosecution history (OA / responses)** | Analysis of whether intentional exclusion (Korean-style estoppel) is established + final determination of claim scope | | **④ Full patented invention + accused product** | Applies the full six-step methodology → outputs a completed **seven-column Claim Chart** | ## Six-Step Problem-Solving Methodology > **Mandatory**: Perform the six steps below in order, without skipping any step. ### Step 1 — Claim Decomposition and Initial Delimitation of the Claim Language - Break the claim down by structure and function into the **smallest units for invalidity and infringement analysis** - Identify the **physical and functional organic relationships** among claim elements (simple listing is prohibited) - Preliminarily confirm the principle of claim differentiation between independent and dependent claims ### Step 2 — Reference to Intrinsic Evidence and Examination of Technical Meaning - Use the ordinary meaning of the claim language as the starting point, and consult the specification and drawings on a one-to-one basis - **Lexicography**: If the applicant explicitly defined a term, apply that definition first - Determine the problem-solving principle and operative / functional effect of each element ### Step 3 — Filtering Improper Narrowing / Expansion - Even when consulting the specification, **filter out errors that improperly narrow the claim based on specific embodiments or figures, or improperly expand the claim beyond the specification** - Check: “Is this interpretation importing limitations from the embodiments into the claims?” ### Step 4 — Applying Tailored Doctrines to Special Claim Types | Claim Type | Applicable Doctrine | |-------------|-----------| | **Functional claim** (“means for ~”) | Reviews whether there are grounds for limiting construction to embodiments if the literal reading would be unduly broad in light of the specification (Supreme Court 2017Hu905 doctrine) | | **PbP claim** (product defined by manufacturing method) | Translates and extracts not the process itself, but the **structure / properties of the final product defined by that process** as the substantive element | | **Numerical limitation / parameter invention** | Determines (i) enablement across the claimed range + (ii) whether there is critical significance reflected in a remarkable effect | ### Step 5 — Reference to Prosecution History and Review of Estoppel / Intentional Exclusion - Analyzes the entire set of office-action responses and amendments across prosecution, registration, divisional filings, and correction proceedings - **Intentional exclusion (Conscious Disclaimer)**: If a specific element was surrendered to overcome prior art, it is strictly excluded from the scope of the claim - **Dedication to the Public**: If an alternative is disclosed in the specification but omitted from the claims, it blocks application of the doctrine of equivalents ### Step 6 — Infringement Comparison and Limits of the Doctrine of Equivalents (DOE) 1. **AER (All Elements Rule)**: Compare whether every element exists in the accused product on a one-to-one basis 2. **Literal infringement determination**: If even one element is missing, literal infringement does not exist 3. **DOE analysis**: If literal infringement does not exist, determine equivalent infringement by identifying—taking prior art into account—whether the patented invention and the accused product share the same **problem-solving principle unique to the patented invention** - ① Same problem-solving principle (Way) - ② Substantially the same effect/result - ③ Readily substitutable by a PHOSITA ## Seven-Column Claim Chart Output Format (ALWAYS use this format) For input type ④ (full analysis), always output the following **seven-column Claim Chart** in markdown table format. | 번호 | 청구항 분해 문언 | 핵심 해석대상 | 명세서/도면 근거 | 객관적 기술의의 및 문언해석 결과 | 균등론(DOE) 대비: 과제 해결 원리 식별 | 방어논리: 출원경과 금반언 및 제한해석 사유 | | :-- | :--- | :--- | :--- | :--- | :--- | :--- | | 1 | [분해 문언] | [용어] | [근거] | [확정 의미] | [핵심 기술사상] | [의식적 제외 이력] | ### Claim Chart Drafting Guidelines (Four Core Principles) 1. **Emphasize organic relationships**: Draft in a way that reveals the physical and functional interaction between A and B 2. **Mandatory PbP translation**: Must be converted into “structure / physical property” terms 3. **Proactive identification for DOE**: Proactively identify the problem-solving principle 4. **Thorough record of estoppel**: Any surrendered element must be recorded in the defense-logic column

This case is a very good test case in practice. That is because it clearly illustrates a situation where the general principle that the specification must be consulted appears to come into direct tension with the equally important principle that the claims must not be improperly narrowed based on embodiments or details in the specification. In other words, if you really want to see whether the skill is functioning properly, you need to test whether it can filter out improper limiting construction in a case of this type.

How the Instruction Was Actually Given in Claude

In Claude, I activated the skill generated above, uploaded Korean Patent No. 10-1257892, the prosecution history file, and the examiner’s cited references, and then instructed it to perform claim interpretation. Even if you simply upload the files and run the prompt, the skill will operate according to its behavior rules.

PROMPT

/kr-patent-expert-v2 Please interpret claim 1 of Korean Patent No. 10-1257892, which I am uploading.

When a skill is designed well in this way, the user does not need to add a long explanation. Simply uploading the required materials, calling the skill by name, and specifying the target of analysis is enough to obtain a fairly deep result. Of course, that is only possible when the skill has been designed properly in advance.

How to Work Around Input Limitations

Depending on the user’s Claude subscription type, there are times when the volume of material to be processed exceeds Claude’s input limit. In practice, this happens fairly often. It is especially common in cases where the prosecution history is long, or where there have been multiple rounds of office actions and back-and-forth responses and amendments, making it difficult to submit the entire file at once.

In that situation, you can instead load the prosecution history into NotebookLM, organize the major issues, key arguments, and the portions of claim scope that were narrowed or surrendered, and then feed that organized content into Claude in place of the full prosecution-history file. The prompt I used was as follows.

PROMPT

1) What was the main reason the patent application was initially rejected? 2) How was the heater structure amended to overcome the rejection? 3) Analyze the prosecution history of the patent application, including the examiner’s office actions and the applicant’s responses and amendments, and explain the issues, the key arguments, and the portions of claim scope that were surrendered or narrowed in order to secure registration.

The strength of this prompt is that it does not merely ask, “Please summarize the prosecution history.” Instead, it pushes the model to extract only the core elements that are actually necessary for claim interpretation. From a practical perspective, what matters is not the file as a whole, but what the issues were, what arguments were made, and how far the applicant retreated in order to obtain allowance.

Evaluation of the Actual Result

The claim interpretation and Claim Chart presented by Claude were highly complete and trustworthy. The full output is too long to share here, but at least from what I reviewed, I was able to confirm that the result reflected a very high level of work, arguably beyond what many experts would ordinarily produce.

Of course, there is also a point of caution here. Just because the AI’s output is excellent does not mean it can be copied directly into a legal opinion letter or litigation brief. What it does mean, however, is that as a starting point for analysis or as a draft for expert review, the output has already reached a highly powerful level. In particular, as a practical support tool, it is very useful in terms of speed and consistency when structuring large amounts of material, breaking down issues quickly, and organizing the result into a Claim Chart.

Directly Asking About the Feature That Became the Key Issue

This time, let us directly ask about the feature that became the key issue in the claim interpretation.

PROMPT

In the foregoing interpretation, is claim 1 to be construed narrowly as requiring that the first and second coil portions be capable of being operated simultaneously or separately?

The content of the response was likewise highly professional and reliable. I will quote only the conclusion below. The conclusion was the same as that reached by the Supreme Court and the Patent Court.

Conclusion

Claim 1 does not require, as a limiting condition on claim scope, that the first and second coil portions be independently operable. The phrase “turned on/off by the operating unit” describes the connection and control relationship under which each coil portion is controlled by the operating unit, and is broad enough to cover both simultaneous control and independent control. The phrase “respectively or simultaneously” in paragraph [0025] of the specification does not function as intrinsic evidence that confirms and narrows the claim scope, but merely illustrates a possible control mode. Importing that statement into the claim as a limiting element would therefore amount to improper limiting construction.

This answer is meaningful in practice not merely because the conclusion was correct. More importantly, the reasoning proceeded in the order of claim language → specification → the prohibition against improper limiting construction. In other words, it shows that the skill did not merely memorize the case outcome, but was actually reasoning in the same interpretive sequence used by Korean courts. Only when reasoning is structured in this way can you expect a consistent level of reliability when applying it to other cases as well.

---

Closing Thoughts

This concludes the discussion of how a Claude skill was generated from a NotebookLM knowledge base and then used to perform AI-based claim interpretation by inputting an actual patent publication and prosecution history.

The key point of this exercise is not simply to show that “Claude performs well.” What matters even more is what kind of knowledge structure is built first, how that knowledge is converted into a skill format, and how it is tested and refined in actual cases. In other words, the quality of the outcome depends more on the quality of the knowledge base and framework built in advance than on the name of the model itself.

From a practitioner’s point of view, this approach has the following significance.

• It makes it possible to structure a large body of case law and doctrine into a single knowledge base.
• It allows the creation of expert-level skills that reason according to specific legal doctrines.
• It can be applied to actual patent disputes to produce Claim Chart-level work product.
• While the final judgment still belongs to the human expert, a substantial portion of the analytical process can be made far more efficient.

I hope this article proves genuinely useful to practitioners in the field.

Mastering Patent Claim Construction with LLMs (3): Injecting Guidelines for Claim Chart Drafting

Practical Framework Part 3

Mastering Patent Claim Construction with LLMs (3)

Injecting Claim Chart Drafting Guidelines Drawn from Practical Experience

The next step is a research phase aimed at establishing the format of the final deliverable.

Rather than organizing claim construction results into a simple narrative report, I prefer to structure them in the form of a Claim Chart specifically designed for claim interpretation. This is not merely to make the output look polished, but to secure a practical tool that can be used under a consistent standard in all downstream tasks, including infringement analysis, invalidity review, and opinion drafting.

1. Why Claim Chart Standards Must Be Established First

There is one important point here. A Claim Chart is not just a “format for organizing results,” but a core framework that determines the quality of the interpretation itself.

The problem, however, is that the method for decomposing claims, the standards for extracting elements, and the actual drafting approach are not systematically organized in textbooks or case law. In other words, this is an area where methodology is built largely 👉 through practical experience.

Through handling a wide range of cases, I have gradually developed my own standards for claim decomposition, element extraction, and chart structure in a way that is suitable for claim construction.

2. Teaching the LLM the “Drafting Method” First

At this stage, what I do is simple. I organize the standards I use in practice 👉 the way I would teach a junior associate, and then register them as a source in NotebookLM.

A Critically Important Point

This step is not simply about “adding reference materials.” It is the process of pre-training the LLM on the interpretive framework and the output format so that it will reason under the same standards in all later interpretation tasks.

• This is the step where you inject, before adding any source materials, how the analysis should be conducted and how the results should be organized.
• If this step is skipped, the LLM will analyze each task under a different set of standards, which in turn prevents the overall work product from losing consistency.

3. Claim Chart Drafting Guidelines (Draft)

Below is a draft of the practical Claim Chart drafting guidelines that I prepared and asked the model to review.

DRAFT INSTRUCTION

**1. Methods for Claim Decomposition and Extraction for a Claim Chart Used in Claim Construction** Claims should be broken down into the smallest units that serve as the basis for invalidity and infringement analysis. The language of the claim should be separated according to context, while also being divided into sub-elements in a way that clearly reveals the invention’s distinctive features. The specific methods of decomposition and extraction are as follows. * **Structure- and Function-Based Decomposition:** Break the claim down into **structure**, which reflects the physical form of the elements and how they are connected, and **function**, which reflects the operation and role performed by each element. * **Identifying Organic Relationships:** Go beyond merely listing the components and derive the relationships showing how each component connects with the others and contributes to solving the technical problem. * **Extracting Interpretive Terms and Limitations:** From among the separated sub-elements, extract as the key interpretive targets those terms that **specifically require claim construction or are directly tied to the invention’s distinctive features**. In particular, major extraction targets include terms expressed functionally (for example, “means for ~”) that may need to be examined to determine whether limiting interpretation to the embodiments is required, as well as terms to which the principle of claim differentiation may apply because of dependent claims. **2. The Most Desirable Methodology for Drafting a Claim Chart** The most practical and desirable output format for visualizing claim construction results in a logical and clear manner is to prepare a **Claim Chart** in tabular form. For that purpose, I propose the following table format composed of **six items (columns)** as the output format. | No. | Claim Language | Claim Element (Interpretive Target) | Specification / Drawing Support | Interpretation Result and Legal Analysis (from the PHOSITA Perspective) | Notes (Prosecution History / Limiting Construction) | | :-- | :--- | :--- | :--- | :--- | :--- | | 1 | Decomposed claim language | (e.g., screw) | [paragraph number], [figure number] | (e.g., a low-speed pressing member having a spiral structure) | (e.g., vertical-type limitation based on an argument submission) | **[Drafting Guide and Explanation for Each Column]** * **Claim Language:** Set out verbatim the minimum unit of claim language as decomposed in a way that clearly reveals the invention’s distinctive features. * **Claim Element (Interpretive Target):** Extract from the decomposed language the core target terms or limitations that especially require interpretation or are written as functional expressions (e.g., “means for ~”). * **Specification / Drawing Support (Mapping of Intrinsic Evidence):** Identify and map the specific [paragraph numbers] and [figure numbers] in the detailed description of the invention that define or support the meaning of the term. * **Interpretation Result and Legal Analysis:** From the perspective of a person having ordinary skill in the art, apply intrinsic evidence first and clearly state the objectively and substantively established technical meaning of the claim element. * **Notes (Review of Prosecution History and Limiting Construction):** Record legal points of note, such as any intentional exclusion (prosecution history estoppel) reflected in the submission of arguments or amendments during prosecution, or any reason why, due to a clear disavowal of claim scope in the specification, limiting construction to the embodiments should apply.

This type of Claim Chart format allows intuitive one-to-one textual mapping between the relevant product (or prior art) and the claim elements in later infringement litigation or invalidity proceedings, making it the most effective practical analytical tool for preventing errors caused by improper narrowing or overbroad claim interpretation.

4. The Process of Validation → Refinement → Redesign

Rather than simply using the above guidelines as-is, I validated them in the following way.

“Are these guidelines sufficiently valid under actual legal doctrine and case law standards?”

To answer that question, I instructed the model in the chat to reflect the points requiring refinement and present again the most appropriate concrete Claim Chart format and drafting guide.

5. Refined Claim Chart Drafting Guidelines (Final Version)

The result is as follows, and this too was saved as a memo and then converted back into a source and integrated into the knowledge base. This process of turning good results into knowledge that can be continuously reused rather than a one-off answer is extremely important.

FINAL FRAMEWORK

**1. Methods for Claim Decomposition and Extraction for a Claim Chart Used in Claim Construction (Reflecting Special Issues)** When decomposing claims to apply the All Elements Rule (AER), which is central to infringement and invalidity analysis, it is essential to go beyond a simple listing of claim language and instead perform a more multidimensional extraction that reflects the legal characteristics of **special types of claims (functional claims, PbP claims, and numerical limitation claims)**. * **Identifying Structure, Function, and Organic Relationships:** Break the invention down into the physical structures that make it up and the functions those structures perform, while clearly deriving the relationships showing that each element does not exist in isolation but is organically connected with other elements to solve the technical problem. * **Extracting Targets for Limiting Construction of Functional Claims:** Because elements expressed in abstract or functional terms, such as “means for ~” or “~ step,” carry a risk of making the claim scope unduly broad, they should be extracted as targets for focused review to determine whether there are clearly unreasonable circumstances requiring the claim to be limited to the embodiments disclosed in the specification. * **Extracting the “Structure / Properties” of PbP (Product-by-Process) Claims:** Even when a manufacturing process is recited in the claim, the subject of the invention is still a “product,” so the manufacturing process itself should not be mechanically extracted as an independent element. Instead, the true technical element to be extracted is the “structure or properties of the product” ultimately defined by that manufacturing process. * **Extracting the “Critical Significance” of Numerical Limitation / Parameter Inventions:** Where a specific numerical range or a newly created parameter is involved, it should be separated as a core interpretive target in order to assess whether the specification enables the full claimed range without undue experimentation (support requirement), and whether the claimed range or parameter shows a remarkable effect (critical significance) that distinguishes it from the prior art. **2. The Most Desirable Concrete Claim Chart Format (Top-Tier Practical Template)** By upgrading the existing six-column structure, I propose a **seven-column framework that can fully map both Doctrine of Equivalents (DOE) defense / attack logic in cases of literal non-infringement and the analytical guidance for special types of claims**. | No. | Decomposed Claim Language (Including Organic Relationships) | Core Interpretive Target (Special Issue: Functional / PbP / Numerical) | Specification / Drawing Support (Mapping of Intrinsic Evidence) | Objective Technical Meaning and Result of Literal Interpretation (from the PHOSITA Perspective) | DOE Comparison: Identification of the Principle for Solving the Problem | Defense Logic: Prosecution History Estoppel and Grounds for Limiting Construction | | :-- | :--- | :--- | :--- | :--- | :--- | :--- | | 1 | (e.g., a cleaning unit that supplies cleaning water by electrolyzing filtered water) | cleaning unit (functional claim) | [paragraph 0045], [figure 3] | (e.g., an internal module that performs physical cleaning through electrodes without sterilizing chemicals) | (e.g., the principle of maximizing eco-friendly cleaning efficiency by excluding chemicals) | (e.g., conscious exclusion of a “chemical additive method” during argument submission) | | 2 | (e.g., a tablet manufactured by direct compression) | manufactured by direct compression (PbP claim) | [paragraph 0022] | (e.g., a porous tablet structure having a 15% inter-particle porosity formed by the direct compression process) | (e.g., the principle of controlling disintegration speed by adjusting porosity) | (e.g., structurally / physically different from tablets made by wet granulation) | | 3 | (e.g., a lens assembly having TTL ≤ 6.5 mm) | TTL ≤ 6.5 mm (numerical limitation) | [paragraph 0110], [Experimental Example 2] | (e.g., the physical limit of a miniaturized lens with a total track length of 6.5 mm or less) | (e.g., the principle of achieving an ultra-short focal length through refractive-index redistribution) | (e.g., target for lack of enablement across the full range of 6.5 mm or less) | **3. [Drafting Guide and Explanation for Each Column]** * **Decomposed Claim Language:** Set out verbatim the claim language decomposed into the minimum unit defining the scope of the invention, while describing it in a way that reveals not just a simple list but also the physical and functional relationships among the elements. * **Core Interpretive Target (with Special-Issue Label):** From the decomposed language, extract the key terms that present issues—such as functional expressions (“means for ~”), product-by-process (PbP) language, or numerical limitations / parameters—and identify the type in parentheses so the focus of the analysis is clear. * **Specification / Drawing Support (Mapping of Intrinsic Evidence):** Map the specific [paragraph numbers] and [figure numbers] in the specification that show where the term is defined under the lexicographer rule, where embodiments support a functional claim, where a manufacturing process in a PbP claim causes a specific change in physical properties, or where the technical threshold for a numerical limitation is demonstrated. * **Objective Technical Meaning and Result of Literal Interpretation (from the PHOSITA Perspective):** From the perspective of a person having ordinary skill in the art, apply the principle of construing the claim in light of the specification and describe the objectively and reasonably derived substantive meaning of the element. In the case of PbP claims, the description should not merely repeat the manufacturing process itself, but should clearly translate the structure or properties defined by that process. * **DOE Comparison: Identification of the Principle for Solving the Problem (New):** This column is used to assess possible infringement under the Doctrine of Equivalents when differences are found in a literal one-to-one comparison with the accused product. By considering both the content of the specification and the prior art existing at the time of filing, this column states in advance the “core of the technical idea underlying the specific means for solving the problem unique to the patented invention” (i.e., the principle for solving the problem) to which the relevant element belongs. * **Defense Logic: Prosecution History Estoppel and Grounds for Limiting Construction (New / Refined):** Record the history of any intentional exclusion (prosecution history estoppel) of specific subject matter reflected in arguments or amendments submitted throughout the prosecution of the original application and any divisional applications. Also record whether a functional claim should be limited to a specific embodiment because a broader reading would be clearly unreasonable in light of the specification, or whether a numerical limitation invention may be invalid for failure to satisfy disclosure requirements (such as enablement) because the full claimed range cannot be practiced without undue experimentation.

6. The Core Meaning of This Stage

The most important insight to gain at this stage is the following.

“A Claim Chart is not merely an organizational tool, but a structural mechanism that controls the accuracy of claim interpretation.”

And when using LLMs, the key is not simply getting good results, but building a system in which the results are always generated under the same standards.

7. Key Points for Practical Application

When this process is applied directly in practice, it can be summarized as follows.

1. First, establish the “drafting format” (the structure of the table).
2. Next, inject the “interpretive standards” (legal doctrine and drafting guidelines).
3. Then, input the “source materials” (the specification and evidence).
4. Finally, carry out the “claim interpretation and chart drafting”.

Most people reverse this order. Because they start by asking for the interpretation right away, the results become unstable and lose consistency.

This stage is not simply about creating a Claim Chart, but about designing how the LLM will think. When this work is done properly, all later analytical work becomes far more stable.

© 2026 ChinSu Lee. All rights reserved.