Hoshang Mehta

Hoshang Mehta

PylarPylar
Co-founder at Pylar
631 points

Forums

Architecture design to keep AI Agents from compromising customer data

Most AI agents need access to structured data (CRMs, databases, warehouses), but giving them database access is a security nightmare. Having worked with companies on deploying agents in production environments, I'm sharing an architecture overview of what's been most useful- hope this helps!

Now Live on Pylar : Agent Data Connectors

One of the biggest blockers to building agents is getting the data 'agent-ready'. Teams spend months building pipelines, wiring up sources, cleaning data, and centralizing it - before an agent can even ask its first question.
Pylar now does this out of the box.
We re source-agnostic. Whether your data lives across multiple databases and warehouses (Supabase, Snowflake, MySQL, etc.), you can connect one or many instantly, no re-architecture required.
If you don't have a warehouse yet, we ve got you covered. Pylar ships with 100+ built-in integrations across marketing tools, CRMs, support platforms, product databases, and billing systems. Data comes in cleaned, transformed, and centralized, ready for agents to work with.
Next up is agent views - once you've connected to your sources, you can write SQL across or within to create precise, sanitized, sandboxed views purpose built for specific agents.
Agents don t roam your databases arbitrarily. You deterministically scope exactly what fields they can access, so they do their job well, without hallucinating or giving you different answers for the same/similar questions.
Give it a try and let me know what you think!

Launching Airbook AI - Cursor for Analytics

Today, we re excited to launch Airbook AI - an AI-native workspace to do all your analytics in one place.

Airbook automatically syncs, cleans, and centralizes data from HubSpot, Amplitude, GA4, Zendesk, Stripe, Postgres, Snowflake & more.

Our AI is schema-aware - it understands your question and maps it to the fields that exist in your database, auto-builds queries across sources, and lets you edit everything it generates too- so you're always in control. From there, turn results into dashboards via a prompt or trigger workflows to push data into other growth tools.

Three ways to work:

A very big thank you to our awesome PH community! 🙏🏼

Folks - I'm Hoshang, CEO at Airbook.
Ever since we started building Airbook, we've always wanted to first launch on Product Hunt. We'd been speaking to other founders and 10/10 founders always mentioned that launching on PH was the best way to get feedback.
We've had 4 launches so far and you guys got us to the #1 Product of the Day, twice! It gave us incredible visibility and more importantly, we got some tremendously helpful feedback from the community. It's pretty hard to otherwise get your initial users to get on the product and give it a good try and take the time to share feedback. If it was not this community, we wouldn't have come so far.
This week has been incredibly exciting for us. We launched the biggest release of Airbook. Once again, got some super helpful feedback. Every vote, comment, signup means a lot and we as a team go through each and everyone's feedback and make notes on what we can offer next!

Your requests become our roadmap and that's how we build and iterate, together!
This community is a part of our team and we're all very grateful to have your support!
I'd love to take this opportunity to just say a very big Thank you!

We will be here to share about what we're going to be building next - show you previews (before launch, before anyone else gets to see it ;) get your feedback, answer your questions, share honest stories about what we learn and unlearn, as we keep building!
Stay tuned!
Best,
Team Airbook

A very big thank you to our awesome PH community! 🙏🏼

Folks - I'm Hoshang, CEO at Airbook.
Ever since we started building Airbook, we've always wanted to first launch on Product Hunt. We'd been speaking to other founders and 10/10 founders always mentioned that launching on PH was the best way to get feedback.
We've had 4 launches so far and you guys got us to the #1 Product of the Day, twice! It gave us incredible visibility and more importantly, we got some tremendously helpful feedback from the community. It's pretty hard to otherwise get your initial users to get on the product and give it a good try and take the time to share feedback. If it was not this community, we wouldn't have come so far.
This week has been incredibly exciting for us. We launched the biggest release of Airbook. Once again, got some super helpful feedback. Every vote, comment, signup means a lot and we as a team go through each and everyone's feedback and make notes on what we can offer next!

Your requests become our roadmap and that's how we build and iterate, together!
This community is a part of our team and we're all very grateful to have your support!
I'd love to take this opportunity to just say a very big Thank you!

We will be here to share about what we're going to be building next - show you previews (before launch, before anyone else gets to see it ;) get your feedback, answer your questions, share honest stories about what we learn and unlearn, as we keep building!
Stay tuned!
Best,
Team Airbook

Hoshang Mehta

11mo ago

Airbook - The all-in-one data platform to scale your startup

Airbook lets you sync clean data from any source, analyze it, create dashboards, and activate growth campaigns. Set up in minutes without the complexity and costs.
Hoshang Mehta

2yr ago

Airbook's Plug & Play Data Templates - 50+ actionable data templates with interactive SQL queries

We cover 5 critical categories- Product Analytics, Customer Analytics, Sales Analytics, Marketing Analytics and Finance Analytics. Our data templates are a step-by-step walkthrough for 50+ use-cases with pre-baked, interactive SQL queries.
Hoshang Mehta

2yr ago

Airbook - The fastest way to build and share your data work

Airbook is the only data notebook with native connectors to business apps, databases & warehouses where data and business teams can collaboratively generate insights across sources using SQL and/or no-code. Together & Confidently.
Hoshang Mehta

1yr ago

Airbook 2.0 - Think Notion, but for analytics

Airbook eliminates the complexity of pulling data from multiple sources and juggling fragmented tools for cross-functional teams to build insights across 150+ sources with or without code.