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, so the routing logic is the system of record — not a wiki page a paralegal has to remember.
- Spellbook handles the day-to-day drafting and redlining. It lives where the lawyers already work — Microsoft Word — with the firm’s playbook as its native context. This is the layer that touches the most matters, because most in-house work is commercial-agreement redlining, not litigation.
- Harvey is the reserved high-bar layer for the matters that exceed per-seat drafting AI. Its Workflow Agents run pre-built, no-code sequences over a document set — M&A diligence, credit agreements, lease portfolios — breaking the task into steps and pausing for attorney review. By mid-2026 Harvey passed $300M ARR with 100,000+ lawyers on the platform, and it now runs as both an MCP client and server, so a firm can surface its own tools inside Harvey or call Harvey’s vault review from another system. Seat economics (roughly $1,000-$2,000/attorney/month) mean you license it for senior attorneys and the deals that justify it, not the whole team.
- Thomson Reuters CoCounsel is the research backbone. Westlaw + Practical Law + AI in one stack — the legal-research layer with citation traceability that Harvey and Spellbook are not built to replace. This is the tool you reach for when the answer has to be defensible in front of the GC or a regulator, not merely plausible.
- Claude is the general-purpose AI surface for the long tail. Matter summarization, outside-counsel invoice review, vendor diligence questionnaire response, and matter status digests for the GC. It is the horizontal AI that absorbs the work that does not have a dedicated tool — and the one seat every legal-ops person gets, not just the attorneys.
The handoffs that make it a stack
The value is in the seams, not the individual tools:
- Draft in Spellbook → route through Ironclad. A commercial agreement is redlined against playbook in Word, then submitted to Ironclad intake, where it inherits the approval and signature workflow. Nobody re-keys terms between the two.
- Ironclad repository → Claude for reporting. Signed contracts and their metadata feed Claude-generated matter digests and status rollups for the GC, so the weekly report is a query, not a manual chase.
- Escalate from Spellbook → Harvey. When a matter outgrows per-seat drafting AI (an acquisition, a novel financing), the same document set moves to a Harvey Workflow Agent for structured extraction and multi-step review. Spellbook handles volume; Harvey handles depth.
- CoCounsel underneath both. Whenever a redline or a Harvey output raises a genuine research question, CoCounsel is the grounded-answer layer with Westlaw behind it.
Why this combination
The mid-market in-house team needs three things at once: workflow infrastructure (Ironclad), specialist legal AI (Spellbook + Harvey + Thomson Reuters CoCounsel), and a general-purpose AI for the long tail (Claude). Most teams skip one of those layers — buy specialist AI without the CLM, or buy the CLM without committing to AI — and end up with a stack that compounds process debt rather than cutting legal cycle time.
This combination accepts the cost of five tools in exchange for an operating model that scales to 2-3x the work volume per attorney. At maturity, it supports an in-house team handling everything except specialist regulatory matters and bet-the-company litigation, where outside counsel still wins.
What it costs
Budget ~$300K-$700K all-in annually for a 20-attorney team, and expect the spread to be driven almost entirely by how far you deploy the two custom-quote tools:
- Ironclad — custom, typically $50K-$150K/year at mid-market contract volume (higher with heavy feature use).
- Spellbook — flat, roughly $99-$179/user/month; ~$40K/year if the full team is licensed.
- Harvey — reserved for senior attorneys at ~$1,000-$2,000/seat/month; five to eight seats is where most mid-market teams land, so ~$70K-$150K/year.
- Thomson Reuters CoCounsel — custom, reported around $200-$500/attorney/month depending on bundle.
- Claude — $25/seat/month (Team) or Enterprise pricing; a rounding error against the rest, and the highest-return seat in the stack.
The lower band is a team that licenses Harvey narrowly and runs Ironclad at base volume; the upper band adds firm-wide Harvey and CoCounsel plus a heavier Ironclad footprint.
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. Swap rule: make this move when contract volume is under ~500/year and there is no live litigation exposure.
- Harvey rival on the high-bar layer. Swap Harvey for Legora — its chief rival after a 2026 mega-raise — when your team wants tighter in-document collaboration and European-origin drafting/review, or when Harvey’s price floor and procurement cycle do not pencil out. Run both in a paid pilot on your own matters before committing.
- Heavy litigation profile. Add Relativity or Everlaw for eDiscovery, and a matter-management platform (Onit or similar) on top of Ironclad. Swap rule: trigger this when you have more than a handful of active litigation matters at any given time.
- 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 roughly one-third the cost; gives up the AmLaw-grade research layer but covers most of the value.
When this stack is the right pick — and when it isn’t
Pick this stack when you have 10-50 attorneys in-house, mid-market contract volume, litigation that overflows to outside counsel rather than running in-house, and a mandate to raise throughput per attorney without adding headcount. It assumes you can commit to two custom-quote tools and run a real procurement cycle — if that is not true this quarter, start with the budget-constrained variation and grow into the rest.
Skip it when you are under ~10 attorneys with low contract volume (the budget-constrained variation is the honest answer), when outside-counsel spend dominates your legal budget (invest in legal spend management e-billing first — the stack does not address that), or when your work is litigation-heavy rather than transactional (the eDiscovery variation, not this default, is your starting point). If a single specialist AI would cover 80% of your pain, buy that one tool and revisit the full stack when the second and third pain points show up.
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