No, Claude Code has no native, governed way to read from or write to Westlaw. It's a coding agent, so connecting means writing and maintaining custom API scripts yourself (where an API even exists). Caddi does connect to Westlaw, through a secure, permissioned browser session (Westlaw has no open automation API), and runs the whole workflow across it without a person in the loop.
Litigation and knowledge teams pull authorities, dockets, and research results out of Westlaw and into memos, matters, and the DMS. Automating that work means actually reaching Westlaw, reliably and with the right permissions, which is exactly the gap a general coding agent or in-app assistant leaves.
Why Claude Code can't reach Westlaw
- It's a coding agent, not an integration platform. Claude Code runs in your terminal to read and write files and run commands. It has no built-in, governed connector to Westlaw, reaching it means writing custom API code (where an API exists) yourself.
- No managed credentials or permissions. Connecting Westlaw safely means handling tokens, scopes, and secrets. Doing that in ad-hoc scripts puts client-data access outside your firm's controls, with no central place to revoke or review it.
- You own every break. Even when you get a script working, an API change, a new login screen, or an expired token silently breaks it, and you're the one who has to notice and fix it.
What this leaves on your team's plate
Without a real connection, the work stays manual: someone opens Westlaw, copies data across systems, and double-checks it by hand. The "automation" only covers the easy middle and hands the integration back to a person, so the bottleneck, and the error risk, never actually move. For document- and data-heavy work in a law firm, that gap is where most of the hours (and mistakes) live.
| Claude Code | Caddi | |
|---|---|---|
| Reaching Westlaw | No native, governed connector | Real connection (API or secure browser session) |
| Reads & writes records | Copy-paste by hand, or custom scripts you maintain | Reads and writes the system directly, unattended |
| Cross-tool workflow | Stops at the boundary of what the tool can see | Spans 3 to 6 tools end to end |
| Credentials & access | Handled ad hoc, outside firm controls | Scoped, permissioned, audit-logged |
| Maintenance | Yours to fix when the script or UI changes | Built and maintained for you |
How Caddi connects to Westlaw
Caddi connects to Westlaw through a secure, permissioned browser session (Westlaw has no open automation API), then automates the full workflow around it. You show Caddi the task once over a screen share; it writes the automation as deterministic code and runs it unattended across Westlaw and the other tools the work touches, typically three to six of them, with scoped access and a complete audit trail. Most automations don't stop at one system: they pull data out of an email or PDF, update Westlaw, file a document, and post a confirmation.
Keep reading
- Caddi vs. Claude Code
- All Caddi integrations
- Caddi for law firms
- Is Claude Code reliable for law firms?
See deterministic automation in action
Caddi builds reliable automations from a screen recording and runs them across 70+ tools as deterministic code. Explore real workflows for law firms and RIAs & financial advisors, or book a demo to see your own workflow built live.
Do more with less
See Caddi in action
Tell us where to reach you and the calendar opens right here. In 30 minutes we'll show you how Caddi automates the back-office work that grows with your clients—built, run, and maintained for you.
Frequently asked questions
Can Claude Code connect to Westlaw?
Not in a governed, production-ready way. Claude Code is a coding agent, reaching Westlaw means writing and maintaining custom API integration code yourself, with credentials handled outside your firm's controls. Caddi connects to Westlaw directly and runs the workflow for you.
How does Caddi connect to Westlaw?
Through a secure, permissioned browser session (Westlaw has no open automation API). Caddi reads and writes Westlaw as part of an automated workflow, with scoped, permissioned access and a run-by-run audit trail (Caddi is SOC 2 attested).
Do I need a developer to set this up?
No. You show Caddi the workflow once over a screen share and Caddi builds and maintains the automation for you, including the Westlaw connection. There's no integration code for your team to write or keep running.
Is my client and matter data safe?
Yes. Caddi uses scoped, permissioned access and runs production work as deterministic code with a full audit trail. AI is used only at setup to understand the workflow, not to make decisions on every run, and Caddi is SOC 2 attested.