AI storytelling

AI can build the model, but it can’t tell the story

AI may be getting closer to becoming a full-blown financial analyst, but it's a ways away from reaching the VP level.

Charlie Rhomberg

FP&A analyst turned content marketer

Share to

Link copied!

Table of contents

Series B/C do’s and don’ts

DO uplevel the finance team

Subscribe to the 10X Finance Blog

Get FP&A best practices, research reports, and more delivered to your inbox.

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.

Six months ago, AI models struggled to build a three-statement model.

Now, they can spin one up in seconds—something that would take a junior analyst a full day. The progress is real and genuinely impressive.

But for all the hype about AI’s execution prowess, it still struggles with something more human: turning raw numbers into narratives that land with stakeholders.

Chris Mossa, CEO of Graphite Financial, experiences this tension every day. His team uses AI to deliver full-stack finance support to hundreds of venture-backed companies.

During his recent appearance on the 10x Finance Podcast, he broke down exactly what AI can handle today, and where finance pros still earn their keep.

there's a lot of discussion around how AI is going to disrupt the finance field is that second and third iteration, that interaction with kind of the real world, the replacement for, you know, maybe a financial analyst, but not a VP of finance yet. You know, it's not a partner yet in, you know, in the leadership spaces in terms of how to tell a story. It can interpret results really well, but it's not great yet at telling a fully, you know, front to back story.

AI still falls short of finance-grade reliability

LLM hallucination rates are improving, but “mostly right” isn’t good enough when it comes to clients’ financials. Until AI outputs are near-perfect, they’ll need the same human review as any other client deliverable.

mental models that I always have, especially with AI and how fast things change is, it's like, it's very hard to have this balance between you want to build for where AI is going to be, but at the same time, especially in financial services and like the domain that we both operate in, you know, there's not a lot of room for errors, hallucinations. in our world, the penalty for being wrong is pretty steep. And so the checks and double checks and reviews that we've built around our application of AI and our customer work and purely disrupted the amount of time that we spend in a way that, you know, you see these sort of, you know, 10x time returns on people who have introduced AI workflows. I don't think we've quite seen that. I think we've probably seen more of like a three to one where things have gone, you know, lower level, automatable, repeatable tasks and the early building happen in a blink of an eye and much faster based on really smart prompting. But the additional services we're wrapping around kind of interpreting that, but also reviewing that work doesn't make it quite a ten to one yet. Right. It's, we're still seeing it at kind of like a three to one return because the penalty is so high.

A three-to-one return is nothing to sneeze at. Reconciliations, first-draft models, data pulls, and the like can all get done much faster.

As Chris notes, getting this kind of return hinges on really smart prompting. We asked real finance leaders what prompts they use most in their day-to-day, and consolidated the 15 best ones into a ready-to-use guide.

FINANCE RESOURCES Download the playbook A curated set of ready-to-use prompts to help finance teams get real value from AI.

But the ceiling is set by the work AI can't yet touch: the review layer, the interpretation, the "does this number actually make sense in context?" checks. That work still takes the same amount of time it always did, and it still requires someone who knows the business inside and out.

Expect great first drafts and shaky second iterations

AI tools are amazing brainstorming partners. Albert showed off this capability during our recent vibe coding webinar. You can jam on an idea by vibe coding a prototype in minutes—if it ends up being useful, build on it and share it with your team. If it doesn't, throw it away and move on.

But something like a financial model can’t be one-shotted in a vibe coding session.

Yeah, I would say the first drafts are really good. Now, everything is rooted in how good the prompt is. And if you're working with an agent, how good the kind of natural language and the dialogue is. but a financial model in our world is something that it's a living, breathing tool for our customers. And so what we find is that once you get kind of beyond that first draft, that experience starts to degrade a little bit as it requires kind of more, more human experience. It requires, you know, the ability to see what actually happened and interpret that in light of the model beyond, Hey, this is up and this is down. And it's because you spent more in this area.

AI can flag that legal expenses are up 40%. And with tools like Scan, it can even identify that a partner threatening litigation is what drove the variance.

But the color surrounding it—why it happened, what it means for next quarter, how to frame it for the board—is still outside its reach. That layer is exactly what separates a financial analyst from a VP of Finance. And it's where good finance storytelling starts.

What's one trend in finance and accounting you believe will shape the next five years? I think junior finance roles are going to become storytellers faster. I think mid and senior finance roles are going to become, you know, leadership storytellers faster because what, what technology and AI specifically is gonna, is gonna do is it's gonna unlock a tremendous amount of time that today gets spent doing repeatable updates and tasks that will, will completely go away. You're going to have to find a way to be able to interpret and tell a story and use that work to show real value to the business at every level.

The gap gets wider at scale

You might assume this gap closes over time as AI learns a company's context. And for a single company, that's partially true—feed it enough history and it gets smarter.

But for outsourced finance teams, fractional CFOs, and firms like Graphite that serve hundreds of clients? Every new engagement means starting from scratch. New board decks to ingest, new financial history to absorb, new business context to learn. The "what vs. why" gap doesn't shrink with scale—it multiplies.

This relates to the broader debate about what can be vibe-coded versus what needs a more robust structure surrounding it.

There's almost this experience today between what you're able to byte code or what you're able just like from your way into existence and what's an actual financial, like you know, what's an actual output that you can use repeatedly. And I think we've seen that in engineering and we've seen that in our domains and like it's kind of fine for, you know, prompting to be a way of getting a first draft where the objective is more learning than scaling. And then you might need to throw it away and then you might need to build again from the ground up in something that is scaled. Does that mindset resonate of like, you know, the objective of what you're prompting into existing is much more learning than scaling it? I think scaling it's actually very difficult because, you know, at least the work that we do so specific to the customer, right? Because we're a professional services environment, you know, we're not working on the same company all the time. So when we're trying to do this, the model doesn't always have all the historical context. We sort of have to build

The reframe matters: prompting something into existence is about learning, not production. Build the first draft, figure out what the client needs, then decide what's worth rebuilding into a repeatable system.

{callout}

For fractional CFOs and outsourced finance teams:

Each new client resets the AI's context—plan for that onboarding cost
Use AI-generated first drafts to learn what a client needs, then build repeatable workflows around it
The tools you choose need to work at scale. If it doesn't work for a thousand clients, it shouldn't be your solution for four

{/callout}

AI is getting smarter all the time. It will keep closing the distance between the what and the why. But for now—and likely for a while—the finance professionals who can bridge that gap themselves are the ones who will be impossible to replace.

Listen to the full conversation with Chris Mossa on the 10X Finance Podcast.

And if you want to see how Aleph helps finance teams automate the tactical work so they can focus on the strategic, book a demo.

Subscribe to the 10X Finance Blog

Get FP&A best practices, research reports, and more delivered to your inbox.

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.