CoCounsel Legal (Thomson Reuters)

https://legaltechnology.com/2025/08/05/thomson-reuters-launches-cocounsel-legal-with-agentic-ai-and-deep-research-capabilities/

Aug 2025 relaunch added agentic deep-research workflows (plan-execute-cite). Holds context within a session; no persistent cross-session matter memory layer publicly documented yet. Thomson is building proprietary "Thomson" legal LLM for summer 2026.

At a glance

Type
Session-scoped agentic context
Tier
T2
Created
2013 (Casetext founded 2013; CoCounsel product launched 2023; acquired by Thomson Reuters Aug 2023 for $650M)
Latest release
not applicable — not OSS
License
not applicable — not OSS
GitHub
not applicable — no GitHub repo
Pricing
searched not found
Funding
Public company (Thomson Reuters)

Taxonomy

storage
vector
retrieval
similarity
persistence
session
update
overwrite
unit
document
governance
auditable
conflict
none

When to use

Optimised for: matter-scoped privilege + audit + firm-precedent memory

Anti-fit: not for non-legal verticals; not for self-represented litigants

Pros & cons

Pros

Backed by Thomson Reuters' Westlaw + Practical Law corpus — most authoritative legal-memory substrate.

Cons

Enterprise pricing; Thomson Reuters lock-in; less developer-API-friendly.

Claims & capabilities

1M users across 107 countries.

Technical surface

API surface
searched not found
Backend storage
searched not found
Deployment
searched not found
Embedding model
searched not found
Multi-tenancy
searched not found
MCP
no MCP support advertised — vertical product, no MCP server / client integration documented
A2A
no A2A protocol support advertised — vertical product, no A2A integration documented
OpenTelemetry
no OpenTelemetry integration advertised — vendor logs/observability not publicly documented

Similar systems

Other vertical / domain-specific ai memory in the catalog, ranked by inbound references.

  • NVIDIA ReMEmbR T3

    Builds long-horizon memory by captioning video segments with VILA, storing captions with timestamps + 3D position coordinates in MilvusDB. At query time, LLM iterates retrieval across text, time, and position modalities. Deployed on Nova Carter robot (Jetson Orin).

  • Abridge T1

    Clinician-assist ambient documentation. Source mapping: every AI-generated summary element traced back to the source utterance. Audit-and-trust layer over episodic memory. Built on proprietary 1.5M+ medical-encounter dataset.

  • ASAPP GenerativeAgent T1

    Treats memory as first-class architecture. Captures the digital footprint of every interaction; retrieves preference and history at engagement time. Public example: airline knowing a frequent flyer wants aisle seats with her son — preference-aware, not just history-lookup.

  • BenevolentAI T1

    Target identification / drug repurposing / mechanism tracing. 85+ data sources, petabyte-scale, rebuilt every few weeks. Wet-lab results re-enter the graph and shift downstream predictions — institutional experimental memory closing a feedback loop.

  • Causaly T1

    Drug discovery / target identification / causal mechanism tracing. The graph is the memory: 7 years of curated biomedical cause-effect relationships compounding with each new ingestion. Scientific RAG retrieves from a versioned causal substrate.

  • Character.ai T1

    Chat Memories (user-defined facts), auto-memories for c.ai+ subscribers, pinned memories, in-context retention. PipSqueak 2 model (April 2026) reduces in-conversation drift. Memory Visualization meter forthcoming.

Row last verified 2026-05-14. Catalog data is CC-BY-4.0 — see how to read this.