The default stack for an in-house Legal Ops team that has cleared the Stage-2-to-3 transition on the Legal Ops maturity model — past the spreadsheet-and-shared-drive era, into the operationally-disciplined era where contract velocity, outside-counsel governance, and AI adoption all matter at the same time.
How the pieces fit
- Ironclad is the CLM backbone. Every contract enters via Ironclad intake, gets routed by playbook, signed via Ironclad signing, and lives in the Ironclad repository post-signature. The contract review SOP is encoded in Ironclad workflow rules.
- Spellbook handles the day-to-day drafting and redlining. Lives where the lawyers already work — Microsoft Word — with the firm’s playbook as its native context. Pairs naturally with Ironclad: drafts in Spellbook, contracts route through Ironclad.
- Harvey is the high-bar attorney AI. Used for the matters where Spellbook’s per-seat AI isn’t enough: M&A diligence, complex regulatory questions, novel commercial structures. Reserved for senior attorneys.
- Thomson Reuters CoCounsel is the research backbone. Westlaw + Practical Law + AI in one stack — the legal-research layer Harvey and Spellbook don’t replace.
- Claude is the general-purpose AI surface. Matter summarization, outside-counsel invoice review, vendor diligence questionnaire response, matter status digests for the GC. The horizontal AI that connects everything.
Why this combination
The mid-market in-house team needs three things simultaneously: workflow infrastructure (Ironclad), specialist legal AI (Spellbook + Harvey + Thomson Reuters CoCounsel), and a general-purpose AI for the long tail (Claude). Most teams try to skip one of those layers — buy only specialist AI without the CLM, or buy the CLM without committing to AI — and end up with an incoherent stack that compounds technical debt rather than reducing legal cycle time.
This combination accepts the cost (six tools, ~$300K-$700K annual all-in for a 20-attorney team) in exchange for an operating model that scales to 2-3x the work volume per attorney. At maturity, this stack supports an in-house team handling everything except specialist regulatory matters and bet-the-company litigation, where outside counsel still wins.
Common variations
- Earlier-stage in-house team. Drop Harvey and Thomson Reuters CoCounsel; replace Ironclad with Concord or Juro. Spellbook + Claude + a lightweight CLM serves a 3-10 attorney team well.
- Heavy litigation profile. Add Relativity or Everlaw for eDiscovery; add a matter management platform (Onit or similar) on top of Ironclad.
- Heavy CLM customization needs. Replace Ironclad with Agiloft for organizations whose contract workflow is too non-standard for off-the-shelf CLM.
- Budget-constrained. Spellbook + Claude + Concord at one-third the cost; gives up the AmLaw-grade research layer but covers 80% of the value.
What this stack does NOT replace
- Outside counsel for specialist regulatory work, securities matters, and material litigation
- A privacy/DPO function for GDPR and EU AI Act compliance
- A dedicated legal spend management e-billing system if outside-counsel spend exceeds ~$5M/year (Brightflag, Onit, BusyLamp)
- Court-filing systems for active litigation