Person profile
Co-founder & CTO at HubSpot.
Tools Dharmesh Shah has publicly discussed or demonstrated using. Curated by Magpie's editorial team from podcasts, posts, and public stacks.
Dharmesh Shah is co-founder and CTO of HubSpot and builder of agent.ai. Operator focus on AI tools for small business; runs an active X presence and builder community. Names specific tools weekly.
Dharmesh Shah names Cursor as his daily driver for code assistance. He uses it in two modes: autocomplete inside VS Code and full agent/chat mode. In his Latent Space interview he frames vibe-coding with Cursor as the way he ships features to Agent.ai, citing the example of asking it to add an autosave feature. He's also publicly praised Cursor's $200/mo Max tier as great pricing strategy that speaks to power users.
Dharmesh Shah uses Claude for writing-heavy workflows specifically, switching between frontier models based on the task. He runs Claude Desktop with Model Context Protocol connected to his agent.ai agents, HubSpot CRM, local filesystem, Slack, Google Calendar and Gmail. He frequently creates Claude Projects loaded with company style guides to speed up branded content creation.
for this particular thing involves writing. So maybe I want to use Claude for this particular thing.
I can have the LLM use agents on Agent.ai..., access CRM data in HubSpot, read/write to a specified directory..., access my Google Calendar and Gmail. The possibilities are endless.
Dharmesh Shah uses ChatGPT for document summarization and as one of the three frontier models he recommends operators standardize on (alongside Claude and Gemini). His agent.ai blog specifically frames ChatGPT as the easy entry point: 'hop into ChatGPT to summarize a long document' as a daily-use habit founders should build. His earlier project ChatSpot was a HubSpot-native natural language interface that grew out of his fascination with ChatGPT.
Dharmesh Shah designed and ships HubSpot Breeze, the AI layer inside HubSpot CRM. He launched 18 new Breeze agents at INBOUND 2025 across marketing, sales and customer service. Breeze is the bridge between his agent.ai builder community and enterprise CRM workflows, so when Shah talks about how operators should use AI in their go-to-market motion, Breeze is the surface he points them to.
Dharmesh Shah surfaces DeepSeek as one of the model options inside Agent.ai (alongside o3-mini, Claude 3.5 Sonnet, Flux and Ideogram). He's been deliberate about exposing open-weights models like DeepSeek to agent builders rather than locking them into a single frontier vendor, which signals his read on where the open-source model layer is heading.
Last researched May 14, 2026
Editorial note
These tools have been mentioned by the people featured in podcasts, interviews, posts, and other public media. Source links and citations are included wherever possible. Magpie AI has no direct relationship with the people on these pages. Spot a missing tool or a wrong attribution? Suggest a correction →