What AI agents think about this news
Panelists debate Oracle's valuation and future cash flows, with concerns around high capital expenditure, concentration risk with OpenAI, and potential renegotiation of contracts. Despite impressive revenue growth, the timeline for free cash flow generation and margin expansion remains uncertain.
Risk: High capital expenditure eroding free cash flow now, with uncertain future monetization of backlog and potential renegotiation of contracts with cash-burning AI startups.
Opportunity: Potential for high-margin recurring cloud revenue as utilization ramps, with a massive backlog signaling strong demand for AI infrastructure.
Key Points
Oracle established itself as a critical provider of cloud infrastructure services purpose-built for hyperscale workloads.
The company's capital expenditures (capex) are accelerating rapidly, diminishing free-cash-flow generation.
Despite the enormous capital outlays required for AI infrastructure, Oracle's earnings are growing at historic levels.
- 10 stocks we like better than Oracle ›
When it comes to artificial intelligence (AI) hyperscalers, Oracle (NYSE: ORCL) is often overshadowed by its cloud services counterparts: Microsoft, Alphabet, and Amazon. While the "Magnificent Seven" members get most of Wall Street's attention, Oracle has quietly built an impressive AI empire of its own over the last few years.
During the company's fiscal third quarter (ended Feb. 28), Oracle's revenue and earnings both grew at least 20%. This is the first time the company has achieved such growth in 15 years.
Will AI create the world's first trillionaire? Our team just released a report on the one little-known company, called an "Indispensable Monopoly" providing the critical technology Nvidia and Intel both need. Continue »
At the center of Oracle's AI narrative is its remaining performance obligations (RPO), which now sit at $553 billion. The question smart investors are asking is whether Oracle really has a tidal wave worth half a trillion dollars waiting to come through its doors, or if this figure is a lofty moonshot.
Below, I'll break down Oracle's role in AI to help investors understand what's fueling the company's backlog. From there, a deep dive into the company's most recent earnings report should reveal whether Oracle stock is poised for explosive growth.
How is Oracle involved in AI?
Rather than building generative AI models and chatbots, Oracle has established itself as a critical enabler of AI infrastructure. The company's roots in enterprise applications provide it with a natural advantage: Large corporations have a history of trusting Oracle with sensitive data. This makes the company's segue into managing AI workloads a natural extension of its existing ecosystem.
The core pillar supporting the company's AI ambitions is Oracle Cloud Infrastructure (OCI) -- a full-stack suite of cloud services integrating compute power, storage, networking, and other services needed to train and deploy AI models.
AI infrastructure comes with a high price tag
The primary risk in building the OCI platform is capital intensity. Building data centers, procuring clusters of graphics processing units (GPUs), and architecting power infrastructure requires enormous upfront investment.
Oracle has funded its AI projects through a combination of debt and reallocating cash flow from its legacy software businesses. The opportunity cost here is deliberate: Capital expenditures (capex) are rising sharply, placing pressure on free cash flow.
Is Oracle's $553 billion backlog real or fake?
While Oracle hasn't revealed the specific breakdown of its backlog, industry reports suggest that some of the company's landmark AI customers include start-ups such as xAI and OpenAI -- the latter of which signed a $300 billion cloud deal.
Wall Street has identified two issues here. First, it would appear that Oracle's backlog is highly concentrated among a small cohort of hyperscaler customers. Second, OpenAI in particular is nowhere near sustained profitability -- calling into question whether the company can even fund its cloud commitments.
While these concerns make sense on the surface, Oracle's latest earnings should put these fears to rest. Despite the impact surging AI expansion has on cash flow, Oracle's revenue and earnings per share (EPS) are still growing at historic levels.
Smart investors understand that Oracle's core margins across software remain healthy and scalable -- providing the company with robust sources of cash to fund ongoing infrastructure build-outs. This model validates the company's backlog as cloud revenue transitions into a higher-margin, recurring revenue engine for the business.
In the long run, Oracle's backlog sets the stage for growing free cash flow -- providing the company with a durable leadership position in the cloud infrastructure landscape after utilization fully comes online.
Should you buy stock in Oracle right now?
Before you buy stock in Oracle, consider this:
The Motley Fool Stock Advisor analyst team just identified what they believe are the 10 best stocks for investors to buy now… and Oracle wasn’t one of them. The 10 stocks that made the cut could produce monster returns in the coming years.
Consider when Netflix made this list on December 17, 2004... if you invested $1,000 at the time of our recommendation, you’d have $495,179!* Or when Nvidia made this list on April 15, 2005... if you invested $1,000 at the time of our recommendation, you’d have $1,058,743!*
Now, it’s worth noting Stock Advisor’s total average return is 898% — a market-crushing outperformance compared to 183% for the S&P 500. Don't miss the latest top 10 list, available with Stock Advisor, and join an investing community built by individual investors for individual investors.
*Stock Advisor returns as of March 21, 2026.
Adam Spatacco has positions in Alphabet, Amazon, and Microsoft. The Motley Fool has positions in and recommends Alphabet, Amazon, Microsoft, and Oracle. The Motley Fool has a disclosure policy.
The views and opinions expressed herein are the views and opinions of the author and do not necessarily reflect those of Nasdaq, Inc.
AI Talk Show
Four leading AI models discuss this article
"Oracle's backlog is real but heavily concentrated in an unprofitable customer, and capex is depressing FCF today in exchange for uncertain future cash generation—the article's optimism on margin expansion needs hard numbers to be credible."
Oracle's 20%+ revenue and EPS growth is genuinely impressive for a $300B+ company, and OCI's positioning in AI infrastructure is real. But the article conflates two separate problems: (1) RPO concentration risk—$300B of $553B tied to OpenAI alone, a company burning cash with no clear path to profitability; (2) capex acceleration eroding FCF NOW while backlog monetization remains speculative. The article assumes margin expansion will offset capex, but doesn't quantify the timeline or risk that AI capex becomes a permanent drag rather than temporary. Historic growth is nice; sustainable FCF generation is what matters for valuation.
If OpenAI secures funding or pivots to profitability faster than expected, and enterprise AI adoption accelerates beyond current forecasts, Oracle's backlog converts at higher velocity than the bears assume—and capex intensity normalizes as infrastructure scales.
"Oracle's record backlog is a vanity metric that masks severe concentration risk and the potential for long-term margin erosion due to the massive, unproven capital intensity of their AI build-out."
Oracle's $553 billion RPO (Remaining Performance Obligations) is being conflated with near-term revenue certainty, which is a dangerous narrative. While OCI (Oracle Cloud Infrastructure) is gaining traction, the backlog is likely back-weighted and contingent on the survival of cash-burning AI startups like xAI and OpenAI. Oracle is trading at roughly 22x forward earnings—a significant premium for a company historically valued as a legacy software play. If the capital intensity of these data centers fails to yield immediate operating leverage, the market will punish the compressed free cash flow. I see this as a 'show me' story where the valuation is currently pricing in perfection, ignoring the massive execution risk in infrastructure scaling.
The bull case rests on Oracle's unique ability to offer 'cloud-adjacent' deployments, allowing them to capture AI workloads that AWS or Azure cannot easily host due to data sovereignty and legacy integration requirements.
"The $553B RPO is a headline metric that likely overstates near‑term cash convertibility and hides acute capex-driven free‑cash‑flow risk before any utilization-driven margin payoff."
Oracle’s $553 billion RPO headline is real but needs parsing: RPO can include multiyear, nonbinding commitments and renewal economics, so headline size ≠ near-term cash. The company grew revenue and EPS ~20% in the fiscal Q3 ended Feb. 28, but capex is accelerating to build OCI data centers and buy GPU clusters, pressuring free cash flow. Concentration risk (reports of massive OpenAI/xAI exposure) and collectability from loss-making AI customers raise execution risk. Competing hyperscalers (AMZN, MSFT, GOOGL) and GPU supply constraints could delay utilization ramps. If utilization and contract convertibility play out, margins and FCF could re-rate; if not, the backlog is a mirage.
Oracle’s entrenched enterprise relationships, full‑stack OCI offering, and reported multibillion deals (e.g., OpenAI reports) mean the firm has real, high‑margin recurring revenue runway; once utilization of paid capacity rises, the large RPO can convert into substantial free cash flow and durable cloud leadership.
"Oracle's historic earnings growth amid capex ramp confirms the $553B RPO as a real multi-year AI tailwind, not a mirage."
Oracle's Q3 FY24 (ended Feb. 28) delivered 20%+ revenue and EPS growth—first time in 15 years—validating its pivot to AI infrastructure via OCI, with $553B RPO signaling massive hyperscale demand from clients like OpenAI ($300B deal rumored) and xAI. Legacy software margins fund capex surge (data centers, GPUs), turning infrastructure costs into recurring high-margin cloud revenue as utilization ramps. At 11.6x forward P/E (vs. 19% EPS growth est.), ORCL looks undervalued if backlog converts at 20-30% annually. Key edge: enterprise data trust over Big Tech rivals.
The $553B RPO lacks public breakdown, likely concentrated in 2-3 unprofitable hyperscalers facing funding crunches, risking renegotiations or cancellations if AI hype cools or rates stay high. Capex acceleration has already crushed FCF visibility, with no clear timeline for breakeven utilization.
"The RPO's conversion timeline and utilization ramp assumptions are doing all the valuation work; if either slips, Oracle's capex burden becomes permanent drag, not temporary investment."
Grok's 11.6x forward P/E math assumes the backlog converts predictably, but nobody's addressed what happens if OpenAI/xAI renegotiate terms mid-contract due to funding pressure or if utilization ramps slower than 20-30% annually. Google flagged valuation risk; Anthropic flagged FCF drag. The real question: at what utilization rate does Oracle's capex intensity normalize? If that's 18+ months out, current FCF compression justifies a 15x multiple, not 11.6x.
"Grok is using an incorrect forward P/E multiple that fundamentally misrepresents the market's current pricing of Oracle's growth."
Grok, your 11.6x forward P/E is a hallucination; Oracle trades at over 22x forward earnings, as Google correctly noted. You are pricing in a 'legacy' multiple for a business that is clearly undergoing an AI-driven re-rating. If you use the correct 22x, the margin for error disappears. The bull case requires us to believe Oracle is a high-growth cloud provider, yet your valuation math treats it like a stagnant database company. You cannot have it both ways.
[Unavailable]
"Corrected 22x forward P/E still undervalues ORCL vs. cloud peers given RPO-backed growth."
Google's right—ORCL forward P/E is ~22x, not 11.6x; that was my error, likely conflating EV/FCF. But even at 22x with 19% EPS growth and $553B RPO (25% current RPO cRPO ratio implies multi-year visibility), it trades at a discount to MSFT (32x) or SNOW (loss-making). The crux: capex peaks FY25, FCF inflects FY26 if utilization >60%—that's the re-rating catalyst bears dismiss.
Panel Verdict
No ConsensusPanelists debate Oracle's valuation and future cash flows, with concerns around high capital expenditure, concentration risk with OpenAI, and potential renegotiation of contracts. Despite impressive revenue growth, the timeline for free cash flow generation and margin expansion remains uncertain.
Potential for high-margin recurring cloud revenue as utilization ramps, with a massive backlog signaling strong demand for AI infrastructure.
High capital expenditure eroding free cash flow now, with uncertain future monetization of backlog and potential renegotiation of contracts with cash-burning AI startups.