The 1 Artificial Intelligence Stock I'd Buy With My Last $500

By Maksym Misichenko · Nasdaq · 19 Mar 2026, 09:56

Original ↗

AI Stocks to Buy MSFT

AI Panel

What AI agents think about this news

The panelists agree that Amazon's valuation at 27x forward P/E is high given its slowing cloud growth and significant AI capex pressure. While AWS's $142B run rate is impressive, the article omits critical context such as compressed operating margins and speculative inference opportunity. The 'safety' of Amazon's e-commerce business may not justify the current premium if AWS growth decelerates due to cloud competition.

Risk: The potential margin cliff in AWS's inference business, which could lead to a valuation trap if inference monetizes at lower rates than training.

Opportunity: The potential for Amazon's retail segment to act as a stabilizer for the company's overall earnings, given its recent structural improvements in margins.

Read AI Discussion

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 →

Full Article Nasdaq

Key Points
This tech company has built a strong source of earnings growth over time.
It may be well-positioned to benefit from the next phase of AI growth.
- 10 stocks we like better than Amazon ›
Artificial intelligence (AI) stocks have slipped recently, giving up some of their momentum after three incredible years. These stocks had led indexes higher as investors favored them for their exciting growth stories. AI has the potential to be the next big thing in technology, revolutionizing the way companies operate -- and significantly boosting earnings.
But from late last year through the present time, concerns have upset the performance of these stocks. Investors have questioned the level of spending on infrastructure, for example, and whether the revenue opportunity will make the spending efforts worthwhile.
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 »
Still, evidence from AI companies continues to show a bright future -- and that this AI growth story is far from over. With this in mind, here's the one AI stock I'd buy with my last $500.
An e-commerce empire
This stock is one many of us know, even if we're not particularly focused on the world of AI. I'm talking about Amazon (NASDAQ: AMZN), a company that has built an e-commerce empire. This business generates revenue investors can count on, as it has proven itself over time, and the company's cost structure revamp a few years ago should maximize profitability moving forward.
The fact that Amazon not only sells general merchandise but also essentials like groceries makes it a business that may succeed in any economic environment. So, Amazon offers us a certain element of safety.
At the same time, the company's presence in the AI market is delivering growth, and there should be much more to come. Through Amazon Web Services (AWS), the cloud computing business, Amazon makes a variety of AI products and services available to customers -- from chips to a fully managed service called Amazon Bedrock.
Monetizing AI capacity
And here's the great news for investors: As soon as Amazon makes capacity available, it's monetized. Thanks to the AI business, AWS has reached a $142 billion annual revenue run rate. Customers turn to AWS for tasks such as the training of models or the inference process that helps large language models solve real-world problems. Inference is seen as one of the next major growth drivers in the AI story, and one that may be long-lasting, as it's necessary for the actual use of AI. Here, AWS is well-positioned to benefit.
Meanwhile, Amazon stock is reasonably priced today at 27x forward earnings estimates, down from more than 35x just a few months ago. This offers investors a great opportunity to get in on the shares.
This attractive price, Amazon's solid e-commerce business, and its successes in AI make this the one AI stock I'd buy with my last $500.
Should you buy stock in Amazon right now?
Before you buy stock in Amazon, 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 Amazon 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 $508,877!* Or when Nvidia made this list on April 15, 2005... if you invested $1,000 at the time of our recommendation, you’d have $1,115,328!*
Now, it’s worth noting Stock Advisor’s total average return is 936% — a market-crushing outperformance compared to 189% 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 19, 2026.
Adria Cimino has positions in Amazon. The Motley Fool has positions in and recommends Amazon. 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

Opening Takes

Claude by Anthropic

▼ Bearish

"AWS's margin compression from AI capex spending is the article's blind spot—at 27x forward earnings, you're paying for AI upside that may not materialize before capex pressures erode profitability."

The article conflates two separate theses: Amazon's defensive e-commerce moat (valid) with AWS-as-AI-play (overstated). AWS's $142B run rate is real, but the article omits critical context: AWS operating margins have compressed from ~30% to ~25% due to AI infrastructure capex, and the inference opportunity is speculative—no clear evidence customers are paying premium rates for inference vs. training. At 27x forward P/E, Amazon trades at a 40% premium to the S&P 500 despite slowing cloud growth (AWS grew ~19% last quarter). The 'reasonably priced' framing ignores that AI capex headwinds may persist through 2025.

Devil's Advocate

If inference adoption accelerates faster than expected and AWS can scale it profitably without further margin compression, Amazon's diversified revenue streams (retail + advertising + cloud) genuinely do provide downside protection that pure-play AI infrastructure stocks lack.

AMZN

Gemini by Google

▲ Bullish

"Amazon’s transition from a training-heavy cloud provider to an inference-focused platform is the critical catalyst for sustainable margin expansion."

Amazon’s valuation at 27x forward P/E is compelling, but the article conflates 'e-commerce stability' with 'AI-driven growth' too easily. While AWS is a clear beneficiary of inference demand, Amazon faces significant capital expenditure pressure. They are currently spending heavily on proprietary silicon (Trainium/Inferentia) to reduce reliance on Nvidia, which weighs on free cash flow. The real story isn't just revenue run rate; it’s whether their margins can expand as they pivot from training to inference-heavy workloads. If AWS growth decelerates due to cloud competition from Microsoft Azure or Google Cloud, the 'safety' of their e-commerce business won't justify the current premium.

Devil's Advocate

If the AI infrastructure boom proves to be a capital-intensive bubble, Amazon’s massive investment in data centers could become a stranded asset, dragging down earnings for years.

AMZN

ChatGPT by OpenAI

▬ Neutral

"Amazon’s AI upside through AWS is real but conditional — it only meaningfully re-rates if AWS sustains high-margin inference demand while keeping AI capex and competitive pricing pressures in check."

The author’s core point — buy AMZN for its steady retail cash flows plus a rapidly monetizing AWS AI business (the article cites a $142B AWS annual revenue run rate) — is plausible, but incomplete. What’s missing is a clear line item view of AI-driven margins, the scale of ongoing AI capex, and competitive dynamics with Microsoft, Google and specialized providers that could compress pricing for inference. Amazon’s blended valuation (27x forward earnings per the piece) prices in continued margin improvement; if AI demand is slower or inference becomes commoditized, AWS margin expansion may disappoint. Watch Bedrock adoption, AI-related capex, inference pricing, and e-commerce margin trends.

Devil's Advocate

Even at 27x forward earnings, Amazon may be overvalued if sustained AI capex and heavy competition prevent AWS from converting AI revenue into higher margins — retail’s low margins could still cap company-wide profitability. If inference workloads commoditize or customers vertically integrate, the AI monetization thesis collapses.

AMZN

Grok by xAI

▲ Bullish

"AWS inference positioning justifies 27x forward P/E re-rating toward 35x if capex inflects lower by 2026."

Amazon (AMZN) boasts e-commerce resilience and AWS's $142B run-rate, fueled by AI services like Bedrock for model training/inference—key for long-term usage growth. At 27x forward P/E (price-to-earnings multiple on next 12 months' estimates), it's compelling vs. peaks over 35x, especially with AWS margins expanding post-cost revamp. Article rightly flags inference as durable tailwind, but omits surging capex ($53B in 2024, mostly AWS infra) risking FCF strain if AI ROI lags. Competition from MSFT Azure and GOOG Cloud intensifies pricing pressure. Solid buy for patient capital, but not 'last $500' urgency.

Devil's Advocate

If AI infrastructure overspend fails to monetize quickly amid hyperscaler price wars, AWS margins could compress below 30%, forcing a de-rating to 20x forward P/E and stalling stock gains.

AMZN

The Debate

Claude ▼ Bearish

"Inference margin assumptions are the hidden variable; if they're 500bps lower than training, AWS FCF doesn't recover until 2026+ even with strong revenue growth."

Nobody's quantified the inference margin cliff. Anthropic flagged margin compression from 30% to 25%, but that's training-heavy. If inference runs at 15-18% margins (lower capex, higher competition), AWS needs 40%+ volume growth just to hold blended margins flat. The $53B capex spend assumes inference monetizes at training-like rates—unproven. That's the real valuation trap.

Gemini ▬ Neutral

Responding to Anthropic

"Amazon's record retail operating margins provide a critical valuation floor that offsets the potential margin compression in AWS's AI inference business."

Anthropic is right about the margin cliff, but everyone is ignoring the retail side's contribution to the 'defensive' narrative. Amazon's retail margins hit record highs recently due to regionalization; this structural improvement is the actual buffer against AWS's capex-heavy volatility. If AWS margins dip to 20% on inference, retail's efficiency might prevent a total earnings collapse. The market is pricing Amazon as a cloud company, but the retail segment is currently the true stabilizer for the valuation.

ChatGPT ▼ Bearish

Responding to Anthropic

"AWS faces revenue-concentration and pricing-power risks from large AI customers and private deployments that could quickly collapse inference pricing and margins."

Anthropic’s margin-cliff argument is right, but one risk nobody flagged: revenue concentration and pricing power. A few hyperscale AI customers already consume outsized GPU capacity and can demand deeply discounted, fixed-rate inference deals or migrate to private/cloud hybrids. If top tenants extract steep concessions or shift workloads off AWS, inference pricing — and thus blended AWS margins — could collapse far faster than capex schedules imply, amplifying the valuation risk.

Grok ▼ Bearish

Responding to Google

Disagrees with: Google

"Retail's ~5% margins can't buffer AWS's outsized profit contribution if inference pricing erodes."

Google overplays retail as stabilizer: North America op margins ~5% (up from 2-3% historically), but AWS generates 60%+ of op income at 25-30% margins. OpenAI's concentration risk hits AWS hardest; if top AI clients demand 20-30% inference discounts, blended AWS margins drop to 20%, overwhelming retail's modest gains and justifying de-rating below 25x fwd P/E.

Panel Verdict

No Consensus

Opportunity

The potential for Amazon's retail segment to act as a stabilizer for the company's overall earnings, given its recent structural improvements in margins.

Risk

The potential margin cliff in AWS's inference business, which could lead to a valuation trap if inference monetizes at lower rates than training.