CodexIQ · Legal corpus and deep research
A legal library that is curated, versioned and yours to extend.
CodexIQ builds and maintains a curated corpus of legislation, case law and commentary. Every source carries its provenance, passes a person's review and ships in a numbered release. Access by entitlement and deep research, which finds new sources and adds them to a firm's own corpus with consent, are planned.
The curation workflow, numbered releases and consent records are built and running on our test server. Source discovery starts with one jurisdiction and one area of law, planned for December 2026. The corpus is not yet available.
How you reach CodexIQ. CodexIQ is reached through PracticeIQ, the one application you sign in to. CodexIQ has no sign-in of its own, and your firm's access to the corpus appears in PracticeIQ.
Capabilities
What CodexIQ does.
Each capability is marked with where it stands: built and in alpha testing, in development, or planned.
-
Built, in alpha testing
Curated by people
Every candidate source is reviewed before it is released, and described by jurisdiction, area of law and kind of source.
-
Built, in alpha testing
Provenance on every source
Where a source came from, when, and which release it joined. Generated content never becomes a source.
-
Built, in alpha testing
Numbered releases
Corpus versions on a permanent record, so you always know which version an answer drew on. Signed packages are planned so self-hosted sites can verify what they import.
-
Planned
Deep research, with consent
Find sources your firm does not have yet. Nothing joins your firm's corpus until someone at the firm consents, and the consent is recorded. The consent record is built; finding sources is planned.
-
Planned
Access by entitlement
Firms see what their plan includes, enforced inside retrieval rather than in the user interface.
-
Planned
Source discovery
Discovery of official and reputable sources, one jurisdiction and area of law at a time, starting from a small sample with a cost estimate.
Who it is for
Built for the people who carry the risk.
CodexIQ is built to supply the corpus that LexIQ searches next to your own documents. Releases are versioned, so research can always say which version of the corpus it used.
-
Firms that want wider coverage
Research beyond your own documents, against a corpus you can trace and verify.
-
Knowledge managers
Grow the firm's library deliberately, with a record of what was added and why.
-
Self-hosted and hybrid firms
Take corpus releases into your own environment as versioned packages.
Roadmap
Where CodexIQ is heading.
Dates are planning targets and can move. "Done" means built and tested by us in development or on our test server; it does not mean generally available. Nothing on this roadmap is generally available yet. Last updated 25 Oct 2026.
-
Curation foundations
DoneOctober 2026
The review workflow that every source passes through before it joins the corpus.
- Candidate review with facets (jurisdiction, area of law, kind) and provenance (Done)
- Numbered corpus releases on an append-only record (Done)
- Firm consent recorded before a source joins a firm's corpus (Done)
- Separate access for our curators and for firms (Done)
-
M1: first discovery
Planned14 Dec 2026 to 25 Dec 2026
Discovery on one jurisdiction and one area of law, starting from a small sample with a cost estimate.
- Source discovery for one jurisdiction and area of law (Planned)
- Facet classification, always reviewed by a person (Planned)
- Signed, versioned corpus packages (Planned)
-
M2: firm deep research
Planned4 Jan 2027 to 15 Jan 2027
Firms find new sources from inside LexIQ and choose, with a recorded consent, what joins their corpus.
- "Find sources" in LexIQ with a consent record (Planned)
- Corpus packages imported on a second site (Planned)
Try CodexIQ early.
Register for the beta and tell us about your practice. We will be in touch when invited trials open.