Specialized agents for specialized regulatory work.
Keenr agents are built one domain at a time: narrow retrieval over the right corpus, evidence-first reasoning, outputs you can audit. No general-purpose chat. Starting with 510(k) predicate research, expanding across the regulatory and commercial research stack.
Software is being rewritten as services-as-software.
Two of the largest growth investors, Coatue and Sequoia, independently published the same thesis in March 2026: the unit of value is shifting from per-seat software to per-output work. The addressable market expands roughly 25x as AI agents replace not just tools but the work itself.
The earliest wins are in what Sequoia calls "autopilot territory": outsourced, intelligence-heavy work where the budget already exists and substitution is a vendor swap. Legal transactional (Harvey, $11B). Tax advisory (TaxGPT). Healthcare revenue cycle (Anterior). The structure is the same in every case: rule-governed work, deep domain corpus, evidence-first reasoning, outputs you can audit.
Medtech regulatory research sits in the same quadrant. Keenr is building the medtech instance of that thesis, with the AI/ML depth nobody else has.
Three things general AI can't do for regulatory work.
Specialized beats general.
A generic chat model can't reason about substantial equivalence the way an agent purpose-built on the full 510(k) corpus can. Every Keenr agent is built for one domain, with the taxonomy, policy context, and evidence conventions of that domain already in hand.
Evidence beats assertions.
Every claim in a Keenr output links to its source: an actual 510(k) summary, an FDA guidance section, a MAUDE record. You audit the reasoning, not just the answer. Nothing is ever "because the AI said so."
Software speed beats manual cadence.
What used to be a multi-week research project compresses into a session you can rerun whenever the device or the landscape changes. The knowledge lives in the tool, not in a one-off deliverable.
One agent live. A portfolio in development.
Each agent compresses a discrete piece of regulatory or commercial research, work that today takes weeks of manual analysis, into a single session. AI/ML depth (Predetermined Change Control Plans, foundation model disclosure patterns, algorithm change precedents) runs across the full platform as a signature capability, not as a separate vertical.
Keenr Predicate Finder
510(k) regulatory research in a single session. Reads every 510(k) summary, reasons over substantial equivalence, scores against FDA's 2023 Best Practices guidance, drafts the 510(k) Summary narrative.
$499 / report · early access · Try →
Cybersecurity Package Generator
FDA 2023 cybersecurity guidance package, SBOM templates, threat modeling. Compresses a $20K–$50K engagement.
Pre-Submission Strategist
Q-Sub meeting prep, pathway analysis, precedent search across FDA correspondence. Compresses a $10K–$25K engagement.
Letter-to-File Engine
Post-clearance change decisions, LTF-vs-Special-510(k) analysis, audit-ready memos. Compresses $5K–$10K per decision.
Reimbursement Pathway Analyzer
CPT/HCPCS/NTAP crosswalks linked to cleared indications. Coverage and coding strategy from clearance forward. Compresses a $25K–$75K engagement.
- · Competitor Clearance Monitor
- · MAUDE Safety Surveillance
- · US→EU Crosswalk
- · Launch Readiness Playbook
- PCCP library: 66 cleared Predetermined Change Control Plans extracted from 510(k) summaries, queried by semantic similarity on every AI/ML report.
- Algorithm change precedents: modification frequency analysis by category (training data, model retraining, performance specs, deployment), sourced from real cleared filings.
- Foundation model disclosure tracker: cleared AI/ML devices indexed by foundation model family, refreshed weekly via auto-ingest cron.
- AI/ML guidance RAG: 1,200+ chunks of FDA AI/ML guidance documents, semantically retrieved per device. Daily corpus-health smoke test guards retrieval quality.
- Citation freshness: every cited guidance, precedent, and disclosure carries an "Indexed YYYY-MM-DD" timestamp on the report. Reviewers verify the corpus is current.
- De Novo pathway analytics: coming next.
Applied across every agent above. Not a separate vertical.
The regulatory surface area the agent actually reads.
-
91K+ indexed 510(k) summaries
Every publicly available 510(k) summary from the boleary.com corpus (CC BY 4.0) is extracted, embedded, and searchable by semantic similarity, not just by product code. Catches predicates keyword search misses.
-
Full openFDA clearance history
Queried live: structured 510(k) records, MAUDE adverse events, and recall data. Covers 180K+ clearances historically, fresh with each query.
-
FDA guidance documents
September 2023 Predicate Best Practices guidance, January 2025 AI-Enabled Device Software Functions guidance, and the supporting policy documents that shape substantial-equivalence reasoning. All chunked, embedded, and semantically retrievable. The agent cites what it's anchored to, by section.
-
PCCP & Foundation Model libraries
Two specialized libraries built on top of the 510(k) corpus: 66 cleared Predetermined Change Control Plans (extracted, embedded, semantically searchable) and a foundation model disclosure tracker that watches how AI/ML devices describe their models. Both auto-refresh weekly.
-
Citation freshness, on every page
Every guidance citation, PCCP precedent, and foundation model disclosure renders with an "Indexed YYYY-MM-DD" timestamp on the PDF. A daily smoke test asserts retrieval quality stays above threshold. Reviewers see when the corpus was last validated, not just what it says.
Retrieval, then a multi-step agent loop.
Hybrid retrieval runs first. A product-code anchor finds the obvious candidates; a semantic search across the summary corpus surfaces cross-code predicates keyword search misses. Every candidate comes with its clearance date, applicant, product code, and full summary text.
Then the agent loop: classify the submitted device, score candidates against FDA's four predicate best practices, cross-check safety (MAUDE + recalls), and run an 8-dimension substantial-equivalence comparison across intended use, indications, technology, performance, energy source, materials, patient contact, and special controls. Each step outputs evidence, not just conclusions.
The output is a drafted regulatory analysis: ranked candidates, primary recommendation, SE comparison table, pathway decision, testing implications, and a 510(k) Summary narrative you can adapt. Everything is citation-linked back to the underlying 510(k), guidance section, or openFDA record. Nothing is trust-me.
Not a generic AI wrapper.
Keenr is led by Vinod (Vinny) Kaimal, and built in close collaboration with industry practitioners and subject-matter experts: regulatory affairs leaders, consultants, clinical researchers, health system innovation teams. They shape each agent's design and validate its outputs against real workflows, real pain points, and tangible value. The tool reflects how the work actually gets done.
The posture: an operator's tool, built for operators, priced so an RA lead can run one themselves without opening a purchase order, and built to be used by the regulatory consultants their teams work with, too. Consultant white-label and team subscriptions are in development.
Read the full founder storyReady to run the first agent?
$499 per report. No account required for the first search.