UAE/GCC
The right answer to "should we use HubSpot Breeze or an external LLM for data enrichment?" is both — but for entirely different signals. Teams that try to force one approach to cover everything end up with either bloated third-party tooling costs for data HubSpot could have surfaced itself, or thin enrichment outputs that miss the qualitative signals sitting in their own CRM activity. The split is clean once you understand what each approach can and cannot actually see.
This framework comes directly from Gareth Jones, Managing Partner at Oxygen Strategic Partners, who presented on intent signals at a recent HubSpot User Group session. The short version: use HubSpot Breeze for anything that already lives in HubSpot, and use external LLMs for signals that require reaching out to the open web. Everything below explains why that split holds, where it gets more nuanced, and how to implement it without wasting credits or engineering time.
What Breeze Actually Does Well: First-Party Data Enrichment
Breeze's real advantage is access. No external vendor — no matter how large their database — can read your meeting transcripts, call recordings, email threads, deal notes, or CRM activity history. Breeze can. Launched at INBOUND 2024, Breeze Intelligence draws on a database of over 200 million buyer and company profiles for standard enrichment, but the more interesting capability is what it can infer from your own first-party conversation data — buying role, preferred communication style, primary interest topic, hesitation signals, and qualitative contact-level context that no third-party source could reconstruct.
This makes Breeze genuinely strong for teams running active sales cycles where the CRM contains real conversation history. If a contact has been through three discovery calls, two demos, and a handful of email exchanges, Breeze can synthesise that into structured properties. That synthesis is not something you can approximate by pointing an external LLM at a LinkedIn profile. As Gareth put it: "Anything that lives in HubSpot, I would say just use Breeze."
One technical limitation worth flagging: Breeze currently processes transcript text, not audio. It is not fully multimodal. That means it can detect tone through word choice — hedging language, enthusiasm, reluctance — but it cannot pick up on how something was said, which matters for heavily context-dependent signals. WhatsApp conversations are also not yet a supported data source, though that is expected to change. For teams in APAC and the GCC who rely heavily on WhatsApp for client communication, this is a real gap in the current implementation. For more on why messaging platform integration is commercially important in this region, see our piece on why businesses need to be using WhatsApp Business.
Smart Properties: The Underused Capability Most Teams Miss
Beyond the standard enrichment fields, Breeze supports AI-generated custom properties — called smart properties — that can pull from any activity on a HubSpot object. This is where the real depth lives. Most teams use Breeze for contact and company summaries and stop there. Smart properties let you go much further: close and loss reasons pulled from deal activity, qualitative consultant performance signals from delivery call transcripts, preferred channel analysis, hesitation patterns across a buying cycle.
Each smart property costs 10 HubSpot credits to populate — roughly one cent on Pro, where you get 5,000 credits included, or 10,000 on Enterprise. That is cheap enough that selective deployment across your highest-value segments is essentially a rounding error in most CRM budgets. The practical constraint is workflow: smart properties currently have to be created through the AI prompt interface rather than the standard property builder, which means your CRM admin needs to know they exist and where to find them. They are not prominently surfaced, and that is probably why adoption is low even among experienced HubSpot users.
The use cases extend beyond sales. If you are running post-implementation reviews or delivery calls with clients, Breeze can surface qualitative performance signals from those transcripts at the consultant or account level. For professional services firms or agencies managing complex multi-stakeholder engagements, that kind of structured qualitative data is otherwise entirely invisible in the CRM.
Where External LLMs Outperform Breeze
Breeze cannot search the web in any reliable way. Its native web research capability exists but is, as one HUG attendee described it, "a bit finicky" — a characterisation Gareth confirmed, which is why Oxygen routes all web-search enrichment tasks through Gemini externally. For horizontal signals (firmographic data that applies across industries) and vertical signals (sector-specific intelligence), external LLMs are clearly the better tool.
The signals that fall into this category include hiring intent derived from job postings, M&A activity, regulatory certifications, export capacity, technology stack changes, and content freshness on a company's digital presence. None of this lives in your CRM. All of it requires open-web access and, often, synthesis across multiple sources. An LLM with web search enabled — Gemini, GPT-4o with browsing, Claude with appropriate tooling — can pull and structure this faster and more cost-effectively than a human researcher, and at the scale needed for meaningful segmentation.
On cost: API token pricing across Claude, GPT, and Gemini is roughly equivalent on current-generation models. LLM selection for external enrichment should therefore be driven by output quality for the specific signal type you are targeting, not by cost optimisation. Test with a sample of 20 to 50 records before committing to a prompt design or a specific model for a given signal type. Gareth's current approach: "Right now we're 100% on horizontal and vertical signals using LLMs, and 100% HubSpot Breeze on the proprietary data."
The APAC and GCC Data Quality Reality
If your contacts are primarily based in the US or Western Europe, the Breeze free enrichment tier — which covers approximately 13 standard properties — will return useful data at a 95%+ match rate. For APAC-based contacts, expect around 50%. That is a significant improvement from the 15% match rate Gareth observed roughly a year ago, which reflects how quickly HubSpot is expanding its underlying data coverage, but it still means half your APAC contacts will come back empty on standard enrichment fields.
This has a practical implication for how you structure the enrichment workflow. For APAC and GCC contact bases, the free Breeze enrichment pass is still worth running — at zero marginal cost, even a 50% match rate delivers value. But you should not treat it as a complete solution and you need a parallel process for the contacts it cannot cover. That parallel process is where external LLMs and specialist data vendors earn their place. For European contacts, the gap between Breeze and external alternatives is much smaller — Breeze likely covers most of what you need without supplementary tooling.
This regional variation also affects how you should think about CRM strategy more broadly. A global HubSpot deployment that performs well in London or Chicago will behave differently when the contact base shifts to Hong Kong, Shenzhen, or Dubai — not just on enrichment match rates, but on data structure, communication channels, and localisation requirements. Our guide to thinking locally within a global CRM strategy covers that broader challenge in detail.
How to Structure the Decision in Practice
The simplest way to operationalise this is to run two separate enrichment passes with clear ownership for each. The first pass uses Breeze — run the free enrichment across all contacts and companies, then deploy smart properties on the segments where first-party conversation data is richest. The second pass uses external LLMs for signals that require web research, structured as batch API calls against your CRM export or directly via HubSpot's workflow integrations.
Before choosing which external LLM to use for the second pass, test against a representative sample of your actual contact data. Pull 30 to 50 records that reflect your typical customer profile — industry, company size, geography — and run the same prompt across Gemini and GPT-4o. Evaluate the outputs on accuracy, parsability, and relevance to the specific signal you are trying to extract. Gareth's recommendation: "Compare it to your data source or the result you get from something like Gemini and just have a look using your sample data." That test takes a few hours and will tell you more than any vendor benchmark.
One thing to deprioritise in that evaluation: cost. At current API pricing, the difference between models is negligible for most enrichment volumes. Optimise for output quality, not token economics.
Constellation Research's analysis of Breeze Intelligence frames the core value proposition as reducing the complexity and cost of managing disconnected enrichment point solutions. That framing holds — but it only fully applies to the first-party data use case. The practical reality for most enterprise teams operating in APAC or GCC markets is that Breeze and external LLMs are complements, not substitutes. The teams that treat them as competing options will under-invest in one or the other. The teams that treat them as a structured two-pass system will get more signal coverage, better data quality, and a cleaner implementation than either approach alone could deliver.
