Caddi vs Scientific Agent Skills: Features, Pricing & Which Is Better (2026)
A side-by-side comparison of Caddi and Scientific Agent Skills — features, pricing, and ideal use cases — to help you decide which AI tool fits your workflow.
Caddi
Caddi, Inc.
Agent that discovers repetitive back-office work, learns it from a screenshare, and automates it across the tools a firm already uses.
Key features
- Automatic Process Discovery: Reads the systems a firm already uses and surfaces the most repetitive jobs with volume and confidence scores, so nobody has to guess what to automate first.
- Record-to-Code Training: An employee screenshares and narrates a workflow once, and Caddi converts that recording into an API-driven hybrid agent with the rules it captured.
- Loop Studio and Loopy: A chat and studio interface where staff start sessions, ask what to automate, inspect the loop diagram, and question any past run in plain language.
- 150+ Native Integrations: Runs inside Clio, Salesforce, Microsoft 365, NetDocuments, DocuSign, iManage, Wealthbox, Tamarac and dozens more, including cross-app pairs.
- Exception Flagging: Executes the job as demonstrated and raises anything unusual, such as a half-signed envelope or an existing document version, instead of overwriting silently.
- Governed Runs and Audit Trail: Every run is logged with run history from 30 days up to 2 years, MFA, security logs, SAML SSO and action-level audit logging on higher tiers.
- Scout and Advanced Integrations: Business and Enterprise tiers add Scout plus advanced and centrally governed integrations, multi-instance support and priority loop execution.
- Credit-Based Metering: Work is metered in credits (standard AI data extraction costs one credit per page) with active loop limits that scale by plan.
Best for
- Client Intake and Conflict Checks: Automate new-business intake and run conflict checks across matter and CRM systems without manual re-keying.
- Email Triage at Volume: Classify a full inbox, route remittances to payables, file executed contracts, and leave personal mail untouched.
- Document Filing and Version Control: Pull the executed copy from DocuSign, verify both signatures, and file it into NetDocuments as a new version with the firm's naming convention.
- Pre-Billing and Time Entry: Draft time narratives from calendar blocks and push prebill batches through review in Clio or Aderant.
- Cross-System Data Sync: Keep matters, contacts and amounts consistent between Salesforce, document management and billing systems as records change.
- Report Generation and Follow-Ups: Produce recurring reports and schedule client follow-ups on a fixed cadence with every step logged.
Scientific Agent Skills
K-Dense Inc.
An open library of 163 validated Agent Skills that turn Cursor, Claude Code, Codex or Antigravity into a working AI scientist across 100+ databases.
Key features
- 163 Validated Skills: A tested library of domain skills covering concrete scientific procedures rather than generic prompt snippets.
- 100+ Scientific Databases: Skills wire agents into over a hundred research databases so answers are grounded in retrieved primary data.
- Agent-agnostic Standard: Built on the open Agent Skills standard, so it runs on Cursor, Claude Code, Codex and Google Antigravity rather than a single vendor.
- CI Skill Testing: A GitHub Actions skill-test workflow runs against the collection, so regressions in individual skills are caught in the repository.
- Automated Security Scanning: A dedicated security-scan workflow checks the skill set on every change, important when skills execute tools on a researcher's machine.
- K-Dense BYOK Companion: A free open-source desktop co-scientist that runs these skills locally with your own API keys and a choice of 40+ models.
- MIT License: The entire library is MIT-licensed and free to fork, audit or extend for lab-specific workflows.
Best for
- Literature and Database Retrieval: Have an agent pull and cross-reference records from specialised scientific databases during a literature review.
- Reproducible Analysis Pipelines: Use validated skills so the same analytical procedure runs identically across projects and lab members.
- Local Co-scientist Workspace: Run K-Dense BYOK on a laptop with your own API keys to keep unpublished data off third-party servers.
- Extending an Existing Coding Agent: Add scientific capability to Cursor or Claude Code without switching to a separate research platform.
- Teaching and Onboarding: Give students or new lab members an agent that already knows the standard procedures and data sources for the field.
- Custom Lab Skills: Fork the MIT-licensed repository and add institution-specific skills alongside the validated ones.