At Evolve, we have built our own proprietary AI tools and agents, engineered for the unique requirements of pharmaceutical IP. Albert is our proprietary AI agent for patent validity analysis. Albert lays out novelty, inventive step, support, added matter, priority entitlement and the strength of the data behind a patent, so that we can give our clients a fast, cost-effective view on validity. Whether you are preparing an opposition, deciding whether to file third party observations, reviewing a potentially blocking third-party patent, or completing diligence on an asset, Albert’s analysis quickly provides a clear strategic view. The core of Albert is its Data module, which extracts and analyses the experimental data in any biotech or pharma patent document and maps it to the claims.
When you need a quick validity assessment, not a full opinion
Companies and in-house IP teams frequently need a quick, well-founded read on whether a patent is valid: a competitor’s patent that has just granted, a third-party application heading for grant, or an asset that is about to be licensed in. In many cases, this is not the moment to spend large sums on an extensive invalidity opinion or a full freedom-to-operate (FTO) clearance. What is needed is a strategic view, fast: how strong the patent really is, where it is vulnerable, and whether an opposition or third party observations are worth filing. Our guide on freedom to operate versus patentability (Evolve Guides) explains why the two questions need different answers.
The problem for biotech and pharma companies is that, traditionally, even a quick validity assessment has required labour-intensive, expensive analysis. Albert changes that. It enables us to perform a deep, data-level analysis of a patent very quickly and cost-effectively, so we can give you a well-founded view on validity when you need it, without the cost and time associated with a full opinion.
What Albert does
- Validity analysis: Albert’s modules cover the full spectrum of attack, laying out novelty, inventive step, support, added matter, priority entitlement and data strength for our attorneys to review, whether we are attacking a patent or defending one. Albert Construe adds claim interpretation, so that the meaning of each claim term is settled before the validity questions are asked.
- Oppositions and third party observations: Albert gives us a quick validity assessment of a newly granted patent or a pending application, so that the decision on whether to oppose or file third party observations can be taken early, on the evidence, and well inside the deadline. Where we do proceed, the same analysis is the starting point for the grounds.
- Third-party IP review and due diligence: Whether a competitor patent, in-license target, IP portfolio, or contentious matter, Albert assists in a rapid in-depth review to support freedom-to-operate, due diligence, invalidity and infringement analysis. Albert provides fast, evidence-based analysis to find patent vulnerabilities and map data to enforceable claim scope.
- Competitive intelligence: Albert also lets us map a competitor portfolio or technology landscape at speed, pulling the key experimental data from across many patents at once to show where a competitor’s real strength lies and where the gaps are. Read more about our competitive intelligence service.
Importantly, Albert does not replace attorney review. Albert is instead a powerful tool that provides the first detailed analysis and facilitates a deeper dive by the attorney into the complexities of the data and claim scope. The judgement on whether a patent is a genuine threat, and what to do about it, is ours.
The Albert modules
Albert is a family of modules, one for each ground of attack or defence. Each takes a defined input, hands back a defined output for the attorney to review, and has a point in the life of a case where it earns its place.
- Novelty. Input: claims, specification, prior art. Output: a feature-by-feature table against each document, with a conclusion per claim. Runs: examination, diligence, validity attack or defence.
- Inventive step. Input: claims, prior art and the data. Output: the closest art, the objective problem, and the arguments both ways. Runs: inventive step objections, oppositions, diligence.
- Basis. Input: new claims, application as filed. Output: each amended feature traced to its basis, quoted and located, so added matter is found before an opponent finds it. Runs: before amendment and before allowance.
- Support. Input: claims, examples, results. Output: each feature mapped to the experiment behind it, with the evidence classified, showing which claims the data actually support. Runs: at allowance, sufficiency attack or defence.
- Data. Input: the specification in full. Output: embodiments ranked by data strength and mapped to the claims, which also finds the lead candidates in competitor patents. Runs: deciding what to claim, diligence.
- Priority. Input: two or more filings in the chain. Output: what each filing uniquely adds, with applicants and dates. Runs: diligence, and wherever priority will be attacked.
- Sequence. Input: the sequence listing and the case it belongs to. Output: leads and binders mapped to SEQ ID NOs, with an error sweep. Runs: before drafting, diligence, freedom to operate.
- Markush. Input: a generic formula claim. Output: the claim drawn back for the attorney to verify, then every compound it covers, to settle claim scope and whether a lead is covered. Runs: diligence, infringement or validity review.
- Construe. Input: a claim term whose meaning is in doubt. Output: each feature construed four ways and scored clear or inconsistency. Runs: before any other Albert module, and for clarity attacks.
Construe first, where it is needed: any of the other modules can be preceded by Albert Construe, which fixes what each feature of the claim means before the analysis is run on it. Every module works from the legal context of the jurisdiction chosen (the statute, the tests the Boards and the courts actually apply, and our reading of where that is heading, kept current as decisions are issued) and from the case context as it stands: the prosecution history, the objections raised and the responses filed, the related family members and the instructions.
Built by pharma IP experts
Albert is built by our own pharma patent attorney experts. As a purpose-built AI tool for pharma IP, it follows the science and knows the law. Albert reads figures, data and complex experimental reports to test whether the science genuinely supports the claims, and draws on a knowledge bank curated by our experienced patent attorneys and case-law specialists on the evidence requirements for pharma and biotech patents, from the plausibility and sufficiency standards for clinical inventions (Evolve Guides) to the definitions that hold up for antibodies and other biologics (Evolve Guides). Albert does the heavy lifting of data extraction, allowing us to focus on the strategic and commercially relevant questions. The result is the strategic review our clients actually need. With Albert we can efficiently provide a clear, data-grounded answer to the business questions: is this patent valid, is it vulnerable to challenge, is it a genuine threat (or opportunity), and is it worth opposing?
A typical Albert output maps each embodiment in a patent to its claimed technical effect, the supporting experimental evidence and the claims it underpins, and scores the strength of that evidence. The lead embodiment with in vivo data sits at the top, the variants resting on in vitro data alone sit in the middle, and the alternatives that are merely exemplified, with no data behind them, sit at the bottom, however far they reach into the claims. That gap between what a patent claims and what its data can support is where the strategic conversation starts. The same reading applies when the patent is one of your own, as our guide on how to read a biotech patent (Evolve Guides) sets out.
These analyses can form the basis of an expert review into the data, validity and scope of the patent, assisting rapid analysis of competitive landscapes and IP portfolios, for example when navigating a crowded platform landscape such as LNPs (Evolve Guides).
How Albert is built
Every Evolve agent is built from the same four parts. The case context: the client’s files, the prosecution history, the related family members and the instructions, connected from the case project folder. The legal context: the statute and case law of the jurisdiction, the tests the Boards and the courts actually apply, and our reading of where that is heading, kept current as decisions are issued. The instructions: the rules the agent follows, written by our own attorneys, which is where our expertise lives. And the workflow: the steps the agent takes with the attorney, interactive at every one, so that the attorney can challenge a finding and have it re-run.
Any of our agents can be called by name by any Evolve attorney or implementor, in the Claude Cowork desktop app or from inside Word, with a plain instruction such as “Run Albert on this file”. The agents are connected to the relevant case folders and legal resources and can call on each other, and on our coding scripts, as the job needs. We hold our AI to five tests: it adds tangible value and solves a problem we actually have, it runs on the latest foundational models, it works within the files and software we already use (Word, Excel and SharePoint), it carries our own expertise rather than someone else’s, and it is adaptable, transparent and usable by everyone in the firm. Our Evolve AI page sets out the thinking behind this.
A complete AI ecosystem for pharma IP
Albert is just one part of a wider suite of bespoke AI agents Evolve has built for pharmaceutical IP. As pharma IP specialists, we have thought deeply about what is actually useful day-to-day for pharma in-house teams. We are building systems that solve the problems our clients have and enable us to focus on providing strategic advice.
- Popper: Prosecution. Translates and summarises the office action and sets up the groundwork for our response.
- Darwin: Drafting. Claim sets, amendments, specification sections and ST.26 sequence listings, prepared to our instructions.
- Mendel: Amendments. Claim amendments and basis tables for EP, US and other jurisdictions.
- Gilbert: Quality. A second read of specifications, sequences, compounds and responses, with each issue graded.
- Franklin: Invention spotting. Finds inventions and disclosure risks in draft publications and competitor filings.
- Cassandra: Due diligence. Gathers and organises the evidence on coverage, validity, ownership and contract terms.
- Ammonite Chart: Patent estate and loss-of-exclusivity charts that show how long the protection runs.
As your fractional head of IP, or an extension of your existing in-house team, we use Albert to deliver validity assessments, oppositions and third party observations, freedom-to-operate and deal-readiness work to a high calibre, fast, and at a fraction of the cost and time of conventional review.
FAQs
Does Albert replace a full validity or freedom-to-operate opinion?
No. Albert gives us a fast, data-grounded view of how strong a patent is and where it is vulnerable, so that you can decide whether to oppose, file observations or take a licence without commissioning a full invalidity or FTO opinion first. Where a full opinion is needed, Albert’s analysis is where the attorney starts, and it makes that opinion quicker to produce.
What does Albert actually read?
The whole patent document: the claims, the description, the examples, the figures and the tables. Albert maps each embodiment to its technical effect, the supporting data and the claims it underpins, and classifies that data as clinical, in vivo, in vitro, in silico or absent. Our attorneys then review the mapping against the source.
Can Albert help with an opposition or third party observations?
Yes. A quick validity assessment from Albert is often the first step in deciding whether a newly granted competitor patent is worth opposing, or whether third party observations on a pending application would land. If the answer is yes, the analysis becomes the basis of the grounds. The same reading works in defence: it shows where your own claims reach beyond the data, which is what an opponent will look for, so we also use Albert on our clients’ own portfolios ahead of oppositions, licensing discussions and due diligence.
Is our confidential information safe?
Yes. Albert is built directly on foundational models from Google and Anthropic under enterprise terms, with no storing of users’ data and no training on inputs, and no third-party software layer between your documents and the model. Our guide on solving the confidentiality problem (Evolve Guides) explains our approach.
How does Albert fit with Evolve’s other agents?
Albert handles validity. Albert Construe settles what the claims mean first. Popper takes the validity analysis into a prosecution response, Mendel prepares the amendments, and Gilbert gives the final document a second, graded read before the attorney signs it off.
Working with Evolve
If you would like to hear more about how we use Albert and our other proprietary AI tools, or how Evolve can help you with your IP, please contact one of our attorneys. You can also read the original launch article for Albert (Evolve Insights), which includes three anonymised example analyses.