GenAI PMHubSpot
A CRM and software company whose APIs were rated highly in a product API access grading exercise. The newsletter highlights its documentation and UI as useful for prototyping workflows.
Key Highlights
- HubSpot was repeatedly highlighted as an agent-ready CRM with strong APIs, MCP support, and emerging agentic product experiences.
- Its remote and developer MCP servers make HubSpot especially relevant for teams building AI agents that need CRM and CMS access.
- HubSpot earned an A in an API access grading exercise, with documentation and UI praised for enabling rapid workflow prototyping.
- The company’s Agent Hub, Agent Builder, and Agent CLI show how incumbent SaaS vendors can evolve toward agent-native platforms.
- Breeze AI and AEO Grader illustrate HubSpot’s broader push to productize AI across support, growth, and operational workflows.
HubSpot
Overview
HubSpot is a CRM and go-to-market software company that increasingly appears in discussions about agent-ready SaaS, not just traditional business software. In the newsletter, HubSpot stands out for combining a widely used CRM with strong developer infrastructure: well-documented APIs, MCP support, AI tooling, and workflows that can be accessed both through a human-friendly UI and through agentic interfaces. For AI Product Managers, that makes HubSpot notable as a platform where product, growth, sales, support, and automation strategies can converge.Why it matters is practical: HubSpot is being positioned as a system that works for both humans and AI agents. Newsletter references highlight its highly rated API access, public and private agent tooling, MCP servers for CRM and developer workflows, and experiments in agentic UX. That makes HubSpot relevant to AI PMs who need to evaluate whether a software platform can support copilots, autonomous workflows, internal agents, CRM automation, and rapid prototyping without excessive integration friction.
Key Developments
- 2026-04-06 — HubSpot was described as the first leading CRM to launch a public MCP beta about ten months earlier, with thousands of customers reportedly connecting it to AI apps such as Claude and ChatGPT.
- 2026-04-07 — HubSpot’s Breeze AI pricing shifted from $1 per conversation to $0.50 per resolved conversation, signaling a move toward outcome-based AI pricing for support use cases.
- 2026-04-19 — HubSpot was cited alongside Salesforce as a likely backend for a new wave of agent-first startups, where autonomous agents may sit on top of existing SaaS systems and sell outcomes rather than seats or services.
- 2026-05-18 — HubSpot was highlighted as topping an agent readiness list, reinforcing the idea that modern software needs strong agentic experiences in addition to strong human UX.
- 2026-05-19 — Dharmesh Shah said HubSpot was launching an agentic experience (AX) so AI agents could configure the platform, create dashboards, and manage CRM workflows directly rather than depending on a human interface.
- 2026-05-28 — HubSpot launched a private-beta Agent CLI, described as a next-generation command-line tool built for agentic workflows.
- 2026-06-03 — HubSpot’s free AEO Grader was referenced as part of proactive AI workflows for optimizing SEO and ad campaigns, showing HubSpot’s reach beyond CRM into AI-assisted growth tooling.
- 2026-07-24 — HubSpot publicly launched Agent Hub and Agent Builder in beta, enabling teams to build custom chat-style agents or agentic workflows by combining data, tools, and prompts.
- 2026-08-22 — HubSpot was reported to have two MCP servers: a local Developer MCP server for CMS/app development and a remote MCP server for CRM data access. The remote server supported reading, creating, and editing CRM objects like contacts and deals, but not deletion.
- 2026-08-24 — In an API access grading exercise covering 1,331 software products, HubSpot earned an A. Its rich, well-documented APIs were cited as a reason Divvy Homes chose it as a CRM, and its UI was noted as useful for rapidly prototyping and testing workflows.
Relevance to AI PMs
1. A strong test case for agent-ready enterprise software HubSpot is useful for AI PMs evaluating what “agent readiness” actually looks like in practice: APIs that are accessible, MCP support, usable auth flows, operational CRM actions, and product surfaces that can be controlled by both users and agents.2. A practical platform for workflow automation and prototyping
The newsletter specifically highlights HubSpot’s UI as a fast way to prototype workflows and its APIs as robust enough for production integrations. For AI PMs, that combination is valuable when testing human-in-the-loop flows before automating them.
3. A live example of productizing AI across pricing, tooling, and UX
Breeze AI pricing, Agent Hub, Agent Builder, Agent CLI, MCP support, and AX initiatives show multiple layers of AI product strategy: monetization, developer tools, runtime access, and autonomous operation. AI PMs can study HubSpot as an example of how an incumbent SaaS company evolves toward agent-native product design.
Related
- Dharmesh Shah / dharmesh — HubSpot co-founder and a central voice in the newsletter’s discussion of MCP, AX, Agent CLI, and Agent Hub.
- Claude and ChatGPT — Referenced as AI apps customers connect to HubSpot through MCP and related integrations.
- MCP / model-context-protocol / mcp-beta / mcp-auth-app — Core to HubSpot’s agent connectivity story, especially for CRM access and developer workflows.
- Agent Hub / Agent Builder / Agent CLI / agent-hub / agent-builder / agent-cli — HubSpot’s emerging toolkit for building and operating custom agents and agentic workflows.
- Breeze AI / Breeze AI Assistant / breeze-assistant — HubSpot’s AI layer for customer-facing and workflow use cases, including pricing experimentation around resolved outcomes.
- Salesforce — Frequently mentioned as a comparable CRM and as another major SaaS backend in the emerging agent-first stack.
- Divvy Homes — Cited as an example of a company that chose HubSpot partly because of its API quality and documentation.
- HubSpot Academy — Relevant as part of the broader HubSpot ecosystem for onboarding, enablement, and operational adoption.
- AEO Grader — HubSpot’s free tool referenced in autonomous SEO and growth workflows.
- AWS and Microsoft — Related as major infrastructure/platform players often adjacent to enterprise AI and SaaS ecosystems, though not central in these HubSpot-specific mentions.
Newsletter Mentions (24)
“He said HubSpot’s rich, well-documented APIs influenced Divvy Homes’ decision to use it as its CRM, and that its sales team used HubSpot’s UI to rapidly prototype and test new workflows.”
#8 in Alex Klarfeld shared results from grading 1,331 software products on API access, reporting that 57% scored a D or worse while HubSpot earned an A. He said HubSpot’s rich, well-documented APIs influenced Divvy Homes’ decision to use it as its CRM, and that its sales team used HubSpot’s UI to rapidly prototype and test new workflows.
“HubSpot has two MCP servers: the local Developer MCP server for HubSpot CMS and app development, and the remote HubSpot MCP server for CRM data access.”
#5 ▶️ I Tested HubSpot's New MCP Server SyntaxGTM HubSpot’s remote MCP server at mcp.hubspot.com was connected through an MCP Auth App to list, create, and update CRM contacts, while deletion remained unavailable. HubSpot has two MCP servers: the local Developer MCP server for HubSpot CMS and app development, and the remote HubSpot MCP server for CRM data access. The remote MCP added the manage CRM objects tool, enabling creation and updates for CRM objects such as contacts and deals; it supports read, create, and edit operations but not deletion. An MCP Auth App requires an app ID, client ID, and redirect URL; after authorization, Claude used the HubSpot connector’s get contacts / search CRM objects capability to return contacts in roughly 5–6 seconds, including when using Claude Haiku.
“Dharmesh Shah celebrates HubSpot’s public beta launch of Agent Hub and Agent Builder, a toolkit that lets you build custom chat-style AI agents or agentic workflows by mixing your data, tools, and prompts.”
#9 𝕏 Dharmesh Shah celebrates HubSpot’s public beta launch of Agent Hub and Agent Builder, a toolkit that lets you build custom chat-style AI agents or agentic workflows by mixing your data, tools, and prompts. #10 𝕏 Philipp Schmid : LangChain now lets you trace GoogleDeepMind Gemini Live speech-to-speech loops in real time—featuring speaker callback hooks, a color-coded live timeline (user in blue, Gemini in orange, tools in custom colors), and separate audio vs.
“#15 ▶️ How to build proactive agents & self-improving company (Fully explained) AI Jason Explains how to build closed-loop, proactive AI workflows using Loopany’s open-source agent skills, a custom memory layer with cron-job orchestration, and HubSpot’s free AEO Grader to autonomously optimize SEO and ad campaigns.”
#15 ▶️ How to build proactive agents & self-improving company (Fully explained) AI Jason Explains how to build closed-loop, proactive AI workflows using Loopany’s open-source agent skills, a custom memory layer with cron-job orchestration, and HubSpot’s free AEO Grader to autonomously optimize SEO and ad campaigns. HubSpot’s free AEO Grader takes only a company name, analyzes metrics like perplexity and Gemini brand characterization, and returns scores across multiple dimensions plus growth areas for AI answer-engine optimization. Loopany’s SEO loop combines a two-part memory layer—daily/weekly temporal logs and a continuously updated keyword strategy—with cron-driven skills that perform SEO audits, draft and publish content, and pull performance data from Google Analytics and Ahrefs. My friend Gio’s autonomous ad-optimization loop tested 10 ad formats (whiteboard sketch, notebook page, cardboard science, tweet screenshot, etc.) in week one, discovered that “ugly” whiteboard-style assets performed best, and generated 243 leads within months on a $1,500 budget.
“in Dharmesh Shah launched HubSpot’s private-beta Agent CLI, a next-gen command-line tool built for agentic workflows.”
#21 𝕏 in Dharmesh Shah launched HubSpot’s private-beta Agent CLI, a next-gen command-line tool built for agentic workflows. He argues the future of software lies in humans (for context, judgment, creativity) and AI agents (for speed, scale, patience) collaborating.
“Dharmesh Shah says HubSpot is launching an agentic experience (AX) so AI agents can natively configure the platform, create dashboards, and fully manage the CRM instead of relying on a human UX.”
#19 𝕏 Dharmesh Shah says HubSpot is launching an agentic experience (AX) so AI agents can natively configure the platform, create dashboards, and fully manage the CRM instead of relying on a human UX.
“#8 𝕏 Dharmesh Shah applauds HubSpot for topping @jasonlk’s “agent readiness” list, underscoring that software must deliver not only stellar human UX but also robust agentic experiences (AX).”
#8 𝕏 Dharmesh Shah applauds HubSpot for topping @jasonlk’s “agent readiness” list, underscoring that software must deliver not only stellar human UX but also robust agentic experiences (AX).
“in Greg Isenberg predicts a $1T+ market for agent-first startups that treat Salesforce, HubSpot and other SaaS as dumb backends, replace professional services with autonomous agents, and shift to outcome-based pricing.”
#8 in Greg Isenberg predicts a $1T+ market for agent-first startups that treat Salesforce, HubSpot and other SaaS as dumb backends, replace professional services with autonomous agents, and shift to outcome-based pricing.
“#13 in Gohar Ghukasyan 🐘 Starting April 14, HubSpot’s Breeze AI shifts from $1 per conversation to $0.50 per resolved conversation, so you only pay when the AI actually fixes the issue.”
#13 in Gohar Ghukasyan 🐘 Starting April 14, HubSpot’s Breeze AI shifts from $1 per conversation to $0.50 per resolved conversation, so you only pay when the AI actually fixes the issue.
“He says HubSpot was the first leading CRM to launch a public MCP beta ten months ago, and now thousands of customers connect it to AI apps like Claude and ChatGPT.”
#11 in Dharmesh Shah says HubSpot was the first leading CRM to launch a public MCP beta ten months ago, and now thousands of customers connect it to AI apps like Claude and ChatGPT. He asks whether opening the platform in this way makes HubSpot more valuable.
Related
Anthropic’s assistant, discussed here for shared memory across chat and Cowork. The feature is relevant to PMs because it enables cross-task context reuse and user-controlled memory.
An AI coding tool referenced as providing data used to evaluate Grok 4.6. It is also named later as a target environment for running AI eval skills.
OpenAI’s conversational AI product used by the design team to prototype ideas and test interface decisions. Here it is also part of a rapid experimentation workflow.
Co-founder associated here with advocating an 'open brain' approach to machine- and human-readable organizational information. Important for PMs thinking about internal systems, APIs, and organizational memory.
An interoperability protocol for connecting AI systems and tools. Here it is described through a public roadmap covering long-running workloads, local-server HTTP, discovery, identities, permissions, and generated SDKs.
A large technology company building AI products and models. Here it appears in connection with MAI-Image-2.6 and Microsoft’s chat playground.
A collaborative design platform referenced as an example of broad enterprise SaaS that may remain resilient in the AI era. It is contrasted with niche single-purpose products.
Amazon’s cloud platform, referenced in a story about a training pipeline running on a 4-GPU instance. The anecdote highlights GPU utilization monitoring and infrastructure waste.
Product and software entrepreneur referenced for two ideas: voting on nonexistent API endpoints and robot-like agent behavior in human UIs. The newsletter attributes both framework ideas to him.
Enterprise software company mentioned as a customer in a Claude Code migration story. The newsletter highlights a major reduction in migration time and high test coverage.
A protocol for connecting AI models to external tools and servers. The newsletter references discovery of MCP servers and reducing MCP token usage.
Venture firm whose spend data is cited as evidence of AI reshaping SaaS buying patterns. It serves here as a source of market intelligence for PMs.
HubSpot’s low-code AI agent platform for designing and deploying internal agents. The newsletter uses it as an example of practical AI in RevOps.
AI/SaaS commentator cited for interpreting a16z spend data. He is used here to support the thesis that AI is stratifying SaaS rather than killing it.
Stay updated on HubSpot
Get curated AI PM insights delivered daily — covering this and 1,000+ other sources.
Subscribe Free