HubSpot Diamond partner

HubSpot AI set up properly,
and custom Claude for the rest

HubSpot's own AI (now Agent Hub, previously Breeze) does more than most teams realise, and much of it sits switched off or running against messy data. We configure it properly, then build custom Claude agents for the work it was never designed to do.

Abbott Laboratories logoCIPD logoLivaNova logoHealix LogoGunnebo LogoUniversity of West LondonCloserStill Media LogoMention Me logoFeefo logoEcommpay LogoSuperior Press logoThought Leaders 4WayPoint PartnersTussell LogoUnily LogoUtilize LogoArdmacCauseway logoSadel GroupTrue Student LivingStudent FM logoLeaders Romans GroupSpriftIncome AnalyticsConnect Vending LogoRoar B2BSIGOS logoTentbox logoZeroAviaproAlpha logoIcon Solutions logoVantagePoint Consulting logoConway ConsultingPetExec LogoBuyaPowa LogoVableStakeholderzAbbott Laboratories logoCIPD logoLivaNova logoHealix LogoGunnebo LogoUniversity of West LondonCloserStill Media LogoMention Me logoFeefo logoEcommpay LogoSuperior Press logoThought Leaders 4WayPoint PartnersTussell LogoUnily LogoUtilize LogoArdmacCauseway logoSadel GroupTrue Student LivingStudent FM logoLeaders Romans GroupSpriftIncome AnalyticsConnect Vending LogoRoar B2BSIGOS logoTentbox logoZeroAviaproAlpha logoIcon Solutions logoVantagePoint Consulting logoConway ConsultingPetExec LogoBuyaPowa LogoVableStakeholderz

Where HubSpot's AI succeeds, and where it stalls

Agent Hub and Breeze are genuinely good at the work they were designed for. They stall when a job needs your own logic, a system outside HubSpot, or data the CRM does not hold. Knowing which is which saves a great deal of money.

Without SpotDev

Switched on and left alone

With SpotDev

Engineered to do real work

Agents answering from thin data.

HubSpot's agents draft from whatever is in the CRM. Where records are patchy, the output is confidently wrong.

Grounded in records you trust.

We fix the data foundations first, so the agents answer from records that are complete, deduplicated and current.

Credits burning with nothing to show.

Usage-based AI bills by the unit of work. Without governance you pay for drafts and answers nobody uses.

Governed, measured usage.

We scope which agents run where, set the guardrails, and report on what the spend actually returns.

Stops at the edge of the platform.

The moment a process needs your pricing rules, an ERP lookup or a system HubSpot does not reach, the built-in agents stop.

Custom Claude picks it up.

We build a Claude agent for that step, wired into HubSpot and the systems around it, so the process completes end to end.

Nobody trusts the output.

Teams quietly stop using AI suggestions after the first few misses, and the subscription keeps renewing.

Adoption you can prove.

Role-based rollout, clear guardrails on what to check, and before-and-after measurement of real usage.

Without SpotDev

Agents answering from thin data.

HubSpot's agents draft from whatever is in the CRM. Where records are patchy, the output is confidently wrong.

With SpotDev

Grounded in records you trust.

We fix the data foundations first, so the agents answer from records that are complete, deduplicated and current.

Without SpotDev

Credits burning with nothing to show.

Usage-based AI bills by the unit of work. Without governance you pay for drafts and answers nobody uses.

With SpotDev

Governed, measured usage.

We scope which agents run where, set the guardrails, and report on what the spend actually returns.

Without SpotDev

Stops at the edge of the platform.

The moment a process needs your pricing rules, an ERP lookup or a system HubSpot does not reach, the built-in agents stop.

With SpotDev

Custom Claude picks it up.

We build a Claude agent for that step, wired into HubSpot and the systems around it, so the process completes end to end.

Without SpotDev

Nobody trusts the output.

Teams quietly stop using AI suggestions after the first few misses, and the subscription keeps renewing.

With SpotDev

Adoption you can prove.

Role-based rollout, clear guardrails on what to check, and before-and-after measurement of real usage.

Swipe to explore

HubSpot AI implementation services

We are a HubSpot Diamond partner and a software engineering firm, so we can configure HubSpot's own AI properly and write real software where it runs out of road. We work with UK companies running HubSpot, typically from around £3m in revenue upwards.

Agent Hub setup and configuration.

The agents HubSpot gives you, configured against your real pipelines, properties and playbooks rather than left on defaults.

Data foundations first.

Deduplication, property hygiene and structure, so the AI answers from records worth trusting. Usually the highest-return work on the list.

Custom agents in Agent Builder.

Where HubSpot's no-code agent builder can do the job, we build it there and hand it over, rather than selling you engineering you do not need.

Custom Claude agents.

For the work HubSpot's AI was not designed to do: your own business logic, systems outside HubSpot, and long multi-step processes.

Credit and cost governance.

HubSpot bills its AI by units of work. We scope where agents run, cut the waste and report on what the spend returns.

Rollout, training and adoption.

Role-based training and clear guardrails, so your team actually uses what you are paying for.

How we work

Scroll to explore all four phases
1

Audit and use cases.

We review your portal, your data quality and the AI you already pay for, and pin down which jobs are worth automating.

2

Data and configuration.

We fix the data foundations and configure HubSpot's agents against your real pipelines and processes.

3

Build what HubSpot cannot.

Where the platform stops, our engineers build a custom Claude agent and integrate it properly.

4

Adoption and cost control.

We train the team role by role, monitor usage and keep the spend honest.

Where HubSpot's AI stops and custom Claude starts

HubSpot's agents are good at CRM-shaped work. These are the jobs where a custom Claude agent earns its keep.

Processes that leave HubSpot.

Order entry, quoting against ERP stock, contract checks: anything needing a system HubSpot does not natively reach. We built an AI order-entry agent for a UK builders' merchant that reads incoming orders and writes them into the system.

Judgement against your own rules.

Pricing logic, eligibility, risk scoring and approval rules that are specific to your business and will not come out of a generic model.

Long-running, multi-step work.

Research, reconciliation and document workflows that need to run for minutes and complete a job, rather than return a single suggestion.

Training and adoption

Getting your team to actually use it

The most common reason HubSpot AI disappoints is that nobody trusts it enough to use it. We fix that the same way we run HubSpot training: structured, role by role, and measured.

Spaced learning that sticks.

Short, hands-on sessions with practice gaps between them, so habits embed instead of fading after a one-off workshop.

Role by role, not one big session.

What a salesperson should hand to an agent is not what a service lead should. We train against the real jobs people do.

Clear guardrails.

People learn what to check and where the limits sit, so adoption is safe as well as fast.

Adoption you can prove.

A before-and-after competence survey plus usage reporting, so you can see whether the spend moved anything.

START HERE

Start with an audit of what you already have

Most clients start here, with a fixed-scope diagnostic, before committing to a delivery project.

HubSpot AI and Data Readiness Assessment

A fixed-scope diagnostic of your portal: data quality, which AI features you are already paying for, what is worth switching on, and what genuinely needs custom engineering.

  • Fixed scope and fixed price
  • A costed, prioritised roadmap of what to build
  • Starts at £5,000 with 20% credited to an implementation project

Start with a free scoping call.

Tell us what you want HubSpot's AI to do. A senior engineer will call you back to talk through what the platform can already do, what needs building, and a realistic investment.
300+HubSpot implementations, firm-wide

Implementation expertise that drives adoption

We've delivered 300+ HubSpot implementations as a firm, and we specialise in Anthropic's Claude for AI work. Technology only delivers value when people use it, so adoption is built into everything we ship.

In-house engineering team.

Agents and integrations designed, tested and shipped by our own engineers. Nothing is subcontracted.

300+ HubSpot implementations, as a firm.

Transformation projects shipped for B2B teams across the UK and beyond.

Claude specialists.

We've gone deep on Anthropic's Claude rather than dabbling across every model, so you get engineers who know it inside out.

AI with security in mind

No training on your data
Cyber Essentials Plus
Built on your infrastructure
In-house engineers

Common questions about HubSpot AI

SpotDev is a HubSpot Diamond Solutions Partner. SpotDev is an independent consultancy and is not affiliated with or endorsed by Anthropic. Claude is a trademark of Anthropic, PBC. HubSpot and Breeze are trademarks of HubSpot, Inc.