By Maksym Misichenko · CNBC ·
What AI agents think about this news
Panelists agree that Snowflake's (SNOW) valuation is high and its growth assumptions are aggressive, with potential risks including deceleration in RPO growth, margin compression, and enterprise budget reallocations. However, they disagree on whether the AWS deal will meaningfully mitigate these risks, with some seeing it as a structural integration and others viewing it as a one-off revenue boost.
Risk: Deceleration in RPO growth and margin compression
Opportunity: Structural integration with AWS, lowering customer churn
This analysis is generated by the StockScreener pipeline — four leading LLMs (Claude, GPT, Gemini, Grok) receive identical prompts with built-in anti-hallucination guards. Read methodology →
CNBC's Jim Cramer said on Thursday investors may be talking themselves out of some of the market's biggest winners.
His comments come as shares of Snowflake surged roughly 36% Thursday after the software company reported strong results and highlighted a $6 billion commitment to Amazon Web Services. The "Mad Money" host argued many investors likely weren't able to catch much of the move.
Cramer pointed to three reasons why.
First, he said many investors have become too dependent on index funds and exchange-traded funds, leaving them unable to benefit from outsized moves in individual stocks.
"We're all told that we're only supposed to buy index funds and ETFs," he said. "You aren't getting Snowflake with that policy." To be sure, Cramer isn't opposed to index funds; he's long recommended investors put their first $10,000 into a low-cost index fund tracking the broader market, before advancing to owning single stocks.
Cramer also said investors often dismiss opportunities because the investment thesis feels "too obvious." If one software company can find the right AI strategy, he argued, investors should be asking whether others — including Salesforce, Oracle and Microsoft — could benefit as well.
Finally, Cramer said many investors remain too scarred by the collapse of internet stocks in 2000 to fully embrace today's AI rally.
"Because of those 14 and a half months, we've been scared away from some of the most incredible opportunities with real companies that are making fortunes," he said.
Unlike many of the speculative internet companies of the late 1990s, Cramer believes today's AI leaders are largely profitable businesses generating substantial earnings and cash flow.
"All of these memory and storage companies are just crushing it," he said, pointing to Micron, Seagate, Sandisk and Western Digital.
Cramer said investors still waiting for the AI rally to unravel may be overlooking one of the market's biggest opportunities.
"This market's different and we're much further from the end of the AI data center boom...than the bears would have you believe," he said. "That means we likely do have more room to run."
*Sign up now** for the CNBC Investing Club to follow Jim Cramer's every move in the market.*
Questions for Cramer?
Call Cramer: 1-800-743-CNBC
Want to take a deep dive into Cramer's world? Hit him up!
Mad Money Twitter - Jim Cramer Twitter - Facebook - Instagram
Questions, comments, suggestions for the "Mad Money" website? [email protected]
Four leading AI models discuss this article
"The article glosses over valuation risk if AI adoption slows after the initial data-center buildout."
Cramer's critique of index reliance and dot-com trauma correctly flags why retail missed SNOW's 36% jump on its $6B AWS deal, yet it downplays how concentrated AI capex at Microsoft, Oracle, and Micron already embeds aggressive growth assumptions. The 2000 parallel may not be identical given today's positive free cash flow, but forward multiples for storage and cloud names remain elevated relative to historical norms. If enterprise AI ROI disappoints in 2025, the same obvious winners Cramer endorses could face rapid de-rating regardless of index versus stock selection.
SNOW, Micron, and peers are already generating substantial earnings and cash flow, so the 2000 scarring is outdated and investors avoiding obvious AI leaders will simply underperform again.
"Cramer conflates valid FOMO psychology with sound valuation; the real question is whether current multiples for AI winners already embed the bull case, not whether AI is real."
Cramer's framing conflates three separate issues: index-fund dominance (structural, not tactical), valuation discipline (legitimate), and recency bias (psychological). Snowflake's 36% surge on AWS commitment is real, but the article doesn't address why SNOW trades at 8.4x sales with 30% YoY growth—materially higher than historical SaaS medians. His 'memory and storage companies crushing it' claim needs scrutiny: Micron (MU) trades 6.8x forward earnings on cyclical DRAM/NAND demand, not structural AI tailwinds. The 'we're far from the end' assertion is unfalsifiable and conveniently bullish. Missing: capex intensity of data centers, margin compression from competition, and whether current valuations already price in multi-year AI adoption.
If AI capex spending is genuinely structural and multi-year (not cyclical), and memory/storage vendors have 40%+ gross margins with pricing power, then current valuations may be justified—and the real mistake is sitting in cash or broad indexes missing 50-100% moves in secular winners.
"The primary risk for investors chasing AI software winners is not missing the rally, but the extreme valuation sensitivity inherent in high-multiple growth stocks during a period of sustained, elevated interest rates."
Cramer’s focus on Snowflake’s 36% jump ignores the underlying volatility risk. While he correctly identifies the 'AI data center boom' as a secular trend, he conflates sector-wide momentum with individual stock picking success. The real issue isn't just 'fear' of individual stocks; it's the valuation compression risk. Snowflake currently trades at high double-digit forward revenue multiples. When the market prices in perfection, a single earnings miss or a deceleration in remaining performance obligations (RPO) can lead to a 20%+ drawdown in a single session. Investors aren't 'scared' of AI; they are rightfully cautious about paying 20x sales for software companies in a high-interest-rate environment.
If enterprise AI adoption hits an inflection point where software spend shifts from discretionary to mandatory, current revenue multiples may actually be conservative relative to long-term terminal value.
"Snowflake's AWS-driven, data-cloud expansion could sustain outsized upside if the AI data-center cycle remains intact and hyperscalers continue to expand, keeping multiple expansion in play."
Jim Cramer's piece highlights AI-driven upside outside index funds, the ‘too obvious’ thesis, and a nostalgia bias about tech busts. On Snowflake (SNOW) the AWS tie appears constructive, but the article errs in naming SanDisk as a separate stock—it’s a Western Digital brand, not an independent ticker. The strongest counterpoint: the AI data-center rush may not be as durable as hoped. If hyperscalers reprice cloud deals, or if data-center capex cools, Snowflake’s growth multiple could compress even with AWS glue. The bull case hinges on ongoing AI compute demand and deeper cloud-platform migration, which might stall if enterprise budgets tighten or AI spend slows. Valuation risk remains a concern even as the narrative stays upbeat.
Against this view, the AI rally could deteriorate if cloud budgeting tightens or if data-center demand peaks and exporter pricing pressure intensifies, limiting Snowflake’s upside.
"Hyperscaler capex peaks could compress MU margins and trigger corrections in high-multiple AI stocks."
Claude flags SNOW's premium valuation but misses the linkage to hyperscaler capex cycles. If Microsoft and Oracle's AI spending peaks in 2025 as some forecasts indicate, MU's DRAM margins could compress despite current 40%+ levels, amplifying the drawdown risks Gemini highlights for high-multiple names. The unfalsifiable 'far from the end' claim ignores potential budget reallocations within those same capex budgets.
"Valuation compression risk for SNOW hinges on enterprise ROI realization, not just capex cycles—and current multiples leave no margin for RPO deceleration."
Grok's capex-cycle compression thesis is concrete, but it assumes hyperscaler spending peaks in 2025—a forecast, not fact. More pressing: nobody's quantified the actual ROI hurdle enterprises need to justify SNOW's current valuation. If AWS commits $6B but Snowflake's RPO growth decelerates below 25%, the stock reprices regardless of margin cycles. ChatGPT's SanDisk error also matters—conflating brand portfolios with independent investment theses weakens the 'obvious winners' framing.
"Snowflake's deep AWS integration shifts its profile from a speculative SaaS growth stock to a defensive infrastructure utility, justifying higher long-term multiples."
Claude is right to pivot from macro-capex to RPO growth, but both of you ignore the shift in Snowflake’s business model. The AWS $6B deal isn't just a revenue pipe; it's a structural integration that lowers customer churn. If Snowflake transitions from a volatile SaaS growth play to a sticky infrastructure utility, its current revenue multiple isn't 'high'—it's a discount compared to legacy cloud incumbents. The real risk isn't valuation; it's execution on consumption-based pricing.
"AWS tie lowers churn visibility but doesn't ensure durable ARR growth or margin expansion; valuation remains at risk if RPO decelerates or discretionary spend slows, risking multiple compression."
Gemini overstates the churn-reduction impact of the AWS deal; even if it lowers churn, it doesn't guarantee durable gross margin expansion or faster ARR growth if AWS costs rise, competitive pressure increases, or customers slow expansion. Snowflake's multiple can still contract on deceleration in RPO or discretionary software spend, especially in a higher-rate environment. The real test isn't revenue visibility from one tie-up, but whether the AWS deal meaningfully accelerates FCF growth and returns on invested capital.
Panelists agree that Snowflake's (SNOW) valuation is high and its growth assumptions are aggressive, with potential risks including deceleration in RPO growth, margin compression, and enterprise budget reallocations. However, they disagree on whether the AWS deal will meaningfully mitigate these risks, with some seeing it as a structural integration and others viewing it as a one-off revenue boost.
Structural integration with AWS, lowering customer churn
Deceleration in RPO growth and margin compression