Meeting of the Minds - The Legal AI Podcast

The episode delivers some genuinely useful operational nuggets—contract analytics being driven by sales/finance rather than legal, the governance vs. democratization tension, the case against defaulting to agents—but these are padded by significant filler, repeated affirmations, and general advice that any mid-level legal ops person would already know. The ratio of insight to throat-clearing is mediocre.

“not everything needs to be an agent. So I know that's like the buzzword that's going around, but some things might just be workflow, process improvements or writing a script”

“we're able to run analytics two days across 140,000 contracts”

There are a handful of genuinely interesting angles—business stakeholders (not legal) driving the contract analytics purchase, the prediction that prompt engineering is a bubble, Coinbase putting agent-building on performance reviews—but the bulk of the episode recycles familiar legal ops narratives about AI democratization, data hygiene, and change management that circulate widely at industry conferences.

“our contract analytics rollout actually was not driven by legal. We had our business stakeholders that were like, hey, we have a really big project we want to solve regarding, like, our financing contracts. And our previous vendor actually said they couldn't do it.”

“I think there's a whole economy building around prompt engineering. That could be a bit of a bubble because at a point we're going to be able to build our own tools to prompt on our behalf.”

Olivier Plummer is a genuine practitioner—four years implementing and scaling legal tech at Coinbase, a high-pressure crypto-finance environment—with real hands-on depth across CLM, contract analytics, MCPs, and APIs. He is not a career podcaster or pure thought leader, but he is a program manager rather than a senior decision-maker (GC, CLO, VP), which limits the strategic altitude of the perspective.

“I came on to implement our CLM and I've been here for seeing the whole evolution from like a very immature CLM to fully fledged integrating to the business.”

“Not a lot of people are going to get sued by the SEC and have to figure out how to flip that and win the next day.”

The episode has a handful of concrete anchors—5,000 contracts in a month with two lawyers, 140,000 contracts processed in two days, six months from POC to contract signing, a rough $100K big-law comparison—but these are scattered among long stretches of vague language ('super important,' 'big rocks,' 'a bunch of different insights') with no ROI figures, before/after productivity data, or named third-party evidence.

“we pretty much had a team of a couple lawyers scaling, sending out like 5,000 contracts in like a month”

“this would have probably been like an $100,000 invoice to, like, a big law firm”

The hosts ask some decent follow-up questions—probing how contract analytics spread beyond legal, the governance balance, and the historical pain of manual work—but the conversation is consistently warm and promotional, with overt flattery ('I'm pretty sure you're ahead of the curve') and no substantive pushback on vague or self-serving claims. The Evisort branded context visibly softens the questioning.

“So let me just double click on that if I could. What's changed in the last couple of years that you've seen in the relationship of Legal Ops and legal?”

“I'm wondering if you can like look back and it might be painful, but look back at some of those past manual projects”