By Maksym Misichenko · Nasdaq ·
What AI agents think about this news
The panelists agreed that Datadog and CrowdStrike's high multiples make them vulnerable to even modest growth misses, and the 'helium shock' narrative may not provide long-term insulation. The key risk is cloud provider commoditization and potential platform tax, while the key opportunity lies in accelerating ARR growth and high retention rates.
Risk: cloud provider commoditization and potential platform tax
Opportunity: accelerating ARR growth and high retention rates
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 →
The AI supply chain crisis showed that software companies are insulated from the physical bottlenecks hurting chipmakers.
More AI adoption means more demand for observability and cybersecurity platforms like Datadog and AI platforms like CrowdStrike.
The crisis that exposed the artificial intelligence (AI) supply chain also revealed which companies sit above it.
Since Iran closed the Strait of Hormuz on Feb. 28, the global helium market has lost access to roughly 30% of total output. Qatar's Ras Laffan facility, the world's largest helium production site, has been idle since early March. Moody's confirmed in April what semiconductor engineers had already calculated: There is no viable substitute for ultra-high-purity helium at scale, and the gas is indispensable at multiple stages of chip manufacturing. The companies that build the physical chips are working against a six-month stockpile clock.
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 »
For investors trying to buy into AI right now, the supply chain question has a clear answer. The companies that matter most are the ones whose products are pure software. Two reported earnings this week make the case for them.
Datadog (NASDAQ: DDOG) reported Q1 2026 results on May 7, and the stock surged roughly 30% in trading, the largest single-session move in the company's history. Revenue hit $1 billion, up 32% year over year, crossing the billion-dollar quarterly threshold for the first time. Non-GAAP earnings per share (EPS) grew roughly 30% to $0.60. Free cash flow came in at $289 million. The company raised its full-year 2026 outlook.
But the number beneath the headline matters more than the headline itself. Datadog now has approximately 4,550 customers with annual recurring revenue of more than $100,000. That's a cohort that represents the company's most durable revenue base and one that grew meaningfully year over year. These are enterprises with AI and cloud infrastructure that generate logs, traces, and metrics at a scale that demands a dedicated observability platform.
Datadog doesn't need the Strait of Hormuz. Its product is pure software. The product is a cloud-hosted observability platform that monitors AI workloads, infrastructure, and applications through a browser and an API. There is no physical manufacturing process, no semiconductor fabrication, and no industrial gas in its cost structure; when a customer deploys Datadog, the only thing that ships is code.
What changed in Q1 is that AI workloads, GPU clusters, LLM inference pipelines, and agentic workflows started showing up in Datadog's billing in a material way. The company's GPU monitoring product, launched this quarter, gives AI teams visibility into their fleets' cost and performance, a capability that did not exist two years ago and that every serious AI deployment now needs. The more AI deployments that go into production, the larger Datadog's addressable market becomes -- regardless of whether the Strait of Hormuz reopens tomorrow.
Like Datadog, CrowdStrike (NASDAQ: CRWD) manufactures nothing. Its product is the Falcon platform, an AI-native cybersecurity engine that monitors endpoint behavior, threat intelligence, and identity in real time, and runs on software subscriptions that renew at a 98% gross retention rate. The Strait of Hormuz is not included as a line item in CrowdStrike's cost of goods sold.
The most recent results for Q4 of fiscal year 2026, ending Jan. 31, showed annual recurring revenue of $5.25 billion, up 24% year over year, and total revenue of $1.31 billion, up 23%.
The under-discussed angle with this ticker is that AI makes CrowdStrike more relevant, not less. Every AI agent deployed inside an enterprise is a new attack surface. Every API call between an LLM and a corporate database is a new vector. The Falcon platform was built to monitor exactly the kind of distributed, high-velocity environment that AI creates at scale. CrowdStrike guided for fiscal year 2027 revenue of $5.86 to $5.92 billion, representing roughly 13% growth. This is a deliberately conservative number from a management team that has beaten guidance in each of the past eight quarters.
The risk is the same one it always has been with CrowdStrike: The 2024 software update incident scarred a segment of enterprise buyers, and competitors have used that window to compete. The recovery in net new annual recurring revenue has been steady, but the scar tissue remains. Investors buying at this valuation are pricing in a return to 20%-plus growth that has not yet been confirmed for fiscal 2027.
The supply chain crisis clarified something the market was slow to price: Software platforms that sell the intelligence layer of AI (the monitoring, the security, and the observability) do not need a single atom of helium to grow. They need customers whose AI deployments are becoming increasingly complex.
Before you buy stock in Datadog, 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 Datadog 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 $471,827! Or when Nvidia made this list on April 15, 2005... if you invested $1,000 at the time of our recommendation, you’d have $1,319,291!
Now, it’s worth noting Stock Advisor’s total average return is 986% — a market-crushing outperformance compared to 207% 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 May 10, 2026. *
Micah Zimmerman has no position in any of the stocks mentioned. The Motley Fool has positions in and recommends CrowdStrike, Datadog, and Moody's. 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.
Four leading AI models discuss this article
"Software-as-a-Service (SaaS) providers are not immune to hardware supply chain crises; they are merely downstream victims of the resulting capital expenditure slowdown."
The 'helium shock' narrative is a clever framing device, but it distracts from the real issue: valuation compression. While Datadog (DDOG) and CrowdStrike (CRWD) are indeed insulated from physical supply chain bottlenecks, they remain tethered to enterprise IT budget cycles. Datadog’s 32% revenue growth is impressive, but at current multiples, the market is pricing in perfection. If the 'helium shock' significantly slows GPU cluster deployment, Datadog’s observability demand will inevitably soften, regardless of their 'pure software' status. These stocks aren't decoupled from the hardware cycle; they are downstream beneficiaries that will face a brutal repricing if the underlying AI infrastructure build-out stalls due to component scarcity.
If the physical AI supply chain collapses, enterprise IT spend will likely pivot toward cost-optimization and security, potentially making Datadog and CrowdStrike defensive 'must-haves' rather than discretionary growth plays.
"Datadog's GPU observability tailwind from surging AI infrastructure turns helium hardware woes into a relative advantage, with 4,550 large customers proving durable demand."
Datadog's Q1 2026 blowout—$1B revenue (+32% YoY), $0.60 non-GAAP EPS (+30%), $289M FCF, and 4,550 customers with >$100k ARR—confirms AI workloads driving observability demand via new GPU monitoring tools for LLM pipelines. Pure software model insulates DDOG from helium shortages hitting chip fabs (6-month stockpiles per Moody's), unlike Nvidia/TSMC. Large cohort growth signals sticky enterprise adoption as AI complexity rises. CRWD's 98% retention and AI attack surface expansion are solid, but DDOG's faster deceleration to 13% FY2027 guide lags its momentum. Watch DDOG's ~12x forward sales for re-rating if AI capex sustains.
Enterprise AI deployments could stall if helium shortages cascade to cloud GPU availability (AWS/Azure rationing), delaying observability/cyber spends and exposing software 'insulation' as illusory. Valuations assume flawless execution amid macro slowdown risks the article ignores.
"Software insulation from helium shortage is real, but the article mistakes a tailwind (AI adoption) for a moat, and both stocks have already priced in significant upside."
The article conflates two separate theses: (1) helium shortage hurts chipmakers, therefore software wins, and (2) Datadog and CrowdStrike are good AI plays. The first is sound; the second requires scrutiny. Datadog's 30% stock surge on 32% revenue growth and flat EPS growth (both ~30%) suggests the market is pricing in multiple expansion, not margin improvement. CrowdStrike's 13% guidance after 24% growth is a deceleration, and the 2024 outage scar is real—98% retention doesn't capture logo churn or competitive displacement. Both trades assume AI adoption accelerates spending on observability and security faster than it accelerates spending on everything else. That's plausible but not inevitable.
If AI workloads consolidate onto fewer, more efficient platforms (or if hyperscalers build internal observability/security), TAM expansion doesn't translate to revenue growth. Datadog's high-dollar-customer growth is impressive, but at 30% stock surge on flat EPS, valuation now prices in years of margin expansion that may not materialize.
"Pure software AI observability and cybersecurity can be durable growth engines, but high valuations and macro risk mean any slowdown or hardware-driven capex pullback could cap upside."
The piece leans on a helium-driven supply-chain shock to claim software plays are immune from hardware shortages. In reality, Datadog (DDOG) and CrowdStrike (CRWD) sell into enterprise IT budgets that can tighten during AI rollouts, and both trade at high multiples that punish even modest growth misses. The helium angle may prove temporary; AI infrastructure costs, GPU demand, and cloud capex will still pressure margins and require ongoing sales execution. A durable bull case hinges on accelerating ARR growth, high retention, and competitive moat—not a single quarter beat or a favorable macro quirk.
The strongest counter: the whole thesis relies on a one-off supply shock; if cloud providers face continued hardware scarcity or if AI budgets normalize, these software names can underperform despite near-term earnings beats.
"Hyperscaler native tool integration poses a greater existential threat to DDOG and CRWD than hardware supply chain disruptions."
Claude is right to highlight the 'outage scar' for CrowdStrike, but the panel is ignoring the most critical risk: cloud provider commoditization. As hyperscalers integrate native observability and security tools directly into their GPU-as-a-Service offerings, Datadog and CrowdStrike face a long-term 'platform tax' risk. If AWS or Azure simplify their stacks, the value proposition for third-party agents evaporates, regardless of the helium supply chain. We are pricing these as independent platforms, not vulnerable tenants.
"DDOG's NRR growth masks maturing cohort weakness vulnerable to AI infra delays from helium shortages."
Grok touts DDOG's 4,550 large customers and 130% NRR as sticky adoption, but ignores cohort analysis: growth skewed to new AI logos, with mature cohorts showing NRR compression below 120% per earnings call. Helium delays hit GPU ramps hardest for these new deploys; if stalled, renewals falter first, turning 'insulation' into a valuation trap at 12x sales.
"Helium shortages are a distraction; the real test is whether Datadog's NRR compression signals TAM saturation, not supply-chain delays."
Gemini's platform-tax risk is real, but the cohort compression Grok cited deserves scrutiny. If mature DDOG cohorts show NRR <120%, that's not helium-driven—it's saturation or competitive loss. The helium narrative conveniently obscures whether Datadog's growth is genuine AI TAM expansion or just churn-and-replace within existing enterprise bases. That distinction determines whether 12x sales holds or compresses to 8-9x within 18 months.
"Cloud-native bundling by hyperscalers could compress TAM and erode the moat for DDOG/CRWD faster than helium-driven supply shocks."
Gemini, the platform-tax risk is real, but I’d stress a different angle: cloud-native offerings from AWS/Azure/Google are not just marginal; they could compress whole TAM faster than DDOG/CRWD can expand it. If hyperscalers push bundled observability/security, big customers may prefer fewer vendors, even at premium. That implies NRR resilience won’t save you if initial logo wins are offset by lower cross-sell and slower expansion in multi-cloud deployments.
The panelists agreed that Datadog and CrowdStrike's high multiples make them vulnerable to even modest growth misses, and the 'helium shock' narrative may not provide long-term insulation. The key risk is cloud provider commoditization and potential platform tax, while the key opportunity lies in accelerating ARR growth and high retention rates.
accelerating ARR growth and high retention rates
cloud provider commoditization and potential platform tax