Skip to content
Harvey logo

Harvey

An AI platform for law firms and in-house legal teams that researches legal questions, reviews contracts against playbooks and extracts information from large document sets.

4.5

Benchmark results

Not benchmarked

This application has not been benchmarked yet.

Details

Use cases
  • Contract drafting and redlining
  • Legal research
  • Data extraction
Built for
  • In-house legal teams
  • Law firms
Founded
2022

Verified reviews

AI summary of reviews

Reviewers value faster due diligence, contract review, clear drafts and testing ideas, with reusable workflows and shared workspaces. They want easier draft navigation, shorter answers, stronger models and better links to company tools. One reports use of repealed laws and unwanted formatting changes.

4.5 / 54 verified reviews

Overall rating

Excellent
Good
Fair
Poor
Very poor

Uri Barak (opens in a new tab)

Herzog Fox & Neeman

Lawyer or legal adviser · Team size: More than 50 · Used for 1 to 2 years ·

5.0Excellent
Problems solved
Due-diligence - what used to be a tedious multi-day process now takes only hours with the Vault feature; Document benchmarking - reviewing and redlining documents against benchmarks. This isn't a unique feature or something that Claude or ChatGPT cannot do but Harvey is more cost-efficient for the heavy law firm user due to seat-based pricing, and they have a great interface; Quick work through multiple tasks, in parallel - both are edges. I run multiple workflows, projects and tasks concurrently. While human in the loop is still necessary for the final QA, it saves time and increases efficiency. Harvey also tends to be quite quick, even while working on complex tasks. Seat-based pricing - While using Claude with Opus 5.5 on a Team/Enterprise plan might get similar or better results (putting Vaults aside), you'd quickly run out of tokens while Harvey keeps going. It might change with a move to full or partial usage-based pricing. Playbooks - allows preserving knowledge and preferences and replicating them in repeatable workflows across the same document type or use case. It isn't a Harvey unique feature, but is highly useful for my needs as a daily user. Overall, it's a great product and it feels like having another, highly capable member on the team.
What could improve
Better agent/playbook/workflow builder - currently a bit rigid and not as intuitive as Claude Access to stronger models - for obvious cost saving reasons, the topmost models one can currently access on Harvey are Claude Opus 4.8 and GPT Sol 5.6. Since Harvey is in a way subsidizing tokens (and I've heard they'll move to usage-based pricing next year), this is understandable but still would be great to be able to access at least the previous generation of high-end models (Opus 5.0, Sol 6.0). Output too long and granular - out of the box, Harvey's outputs - whether when drafting or revising contract clauses or when replying to queries - are way too long and "legalese". When representing startups v. large enterprises, where every redline matters and less is more, and time is the most precious resource, a lot of time is spent on trimming down Harvey's proposed language or dropping suggested language which isn't critical. I know that the product itself already has features to deal with it, like Memory and writing styles, and this can also be addressed via workflows and playbooks, and not all clients are the same so better to be more conversative, but in future versions Harvey might consider going for shorter, more to the point style from the get-go.

Verified user

Lawyer or legal adviser · Team size: More than 50 · Used for more than 2 years ·

4.0Good
Problems solved
Excellent 'Assistant' and 'Vault' functionality - a game changer for BAU task completion and mass-insight extraction. Some of our in-house developed workflows are generating meaningful efficiencies (e.g. playbook-grounded issues list and redline creation, extraction of key attributes to generate contract summary forms required by various approval forums). The launch of 'Shared Spaces' has created the opportunity for us to collaborate - as a L&C function, with teams across dentsu (eg commercial, procurement), and with external counsel. The latter has been the most successful so far (we've co-created some workflows and Word-embedded playbooks) but there's so much more value to unlock (we just need the bandwidth!). Currently testing new (scheduled) 'Horizon Scanning' feature in the hope that this will generate some additional efficiencies for that aspect of our role - TBD if quality of analysis will exceed what we've managed to pull in via scheduled Claude/Copilot calls or what's generated via our existing 'Assistant' prompt on topic.
What could improve
A lot more in-house oriented features are required. Delighted to see "Intake" launch but it's well overdue!! Many more integrations with CLMs are required to truly move the needle - as absence undermines value of 'Vault'. No conversational functionality exits in Shared Spaces, reducing our ability to leverage it as a genuine collaboration (and deep work) zone - internally and with external counsel. While web sources can be leveraged as sources to support 'Assistant' queries, there's no ability to do scheduled data pulls - a real miss. No clause by clause benchmarking data available as an overlay to contract analysis - in contrast to likes of Ivo which will plot it on bell curve so that you know where, eg the liability clause in front of you, stacks up against the previous 100 contracts reviewed by your org in that client vertical. Insights like that are golden for in-house and far more impactful, IMO, than user-oriented metrics - in terms of safeguarding investment case.

Verified user

Legal operations, knowledge or innovation · Team size: 6 to 20 · Used for more than 2 years ·

5.0Excellent
Problems solved
Helps draft logically and well-structured content. I can red-team my own ideas and writings to prepare for discussions.
What could improve
When drafting and creating a back-and-forth with the tool, it man become very messy and difficult to switch between previous responses and version of drafts. Also, it never really settles a point and keeps suggesting redraft over redraft.
Add a review