Oct 7, 2026 · 29 min · 13 segments
Proudly brought to you by Ignition who we both love and use in our businesses to automate proposals and streamline invoicing. In this episode, Nat…
Diya JollyGuest
We saw, as we said on stage yesterday, we've seen like a 4x increase in the builders we have.

People come to, I hear requests for so many things which are specific to like 10 firms.

I'm like, if we build that into the product, the other firms are going to go, why did you build that into the product? What do we want to enable you? So then the next question was, do you really have to talk to our APIs and write code to our APIs? No.

Do you do it in Cloud Core or OpenAI Codex, but they don't have the guardrails? Because to build AI, you have to give it all the context.

This new technology now allows us to put something inside those guardrails that can actually allow you to do the stuff that you couldn't do before.

And again, going back to the conversation you and I were having, the goal is to take away the work that you guys do Never really wanted to do.
So should accountants and bookkeepers be putting private and sensitive information directly into an LLM?

Look, when you work with our connectors, we have a deal with them that they cannot use the data.

We saw, as we said on stage yesterday, we've seen like a 4x increase in the builders we have.

People come to, I hear requests for so many things which are specific to like 10 firms.

I'm like, if we build that into the product, the other firms are going to go, why did you build that into the product? What do we want to enable you? So then the next question was, do you really have to talk to our APIs and write code to our APIs? No.

Do you do it in Cloud Core or OpenAI Codex, but they don't have the guardrails? Because to build AI, you have to give it all the context.

This new technology now allows us to put something inside those guardrails that can actually allow you to do the stuff that you couldn't do before.

And again, going back to the conversation you and I were having, the goal is to take away the work that you guys do Never really wanted to do.
So should accountants and bookkeepers be putting private and sensitive information directly into an LLM?

Look, when you work with our connectors, we have a deal with them that they cannot use the data.
The rest of this transcript — segmented and speaker-labeled, so you land on the exact moment something was said
Search every transcript — by keyword, by phrase, or by meaning, across every show Radar indexes
Trends — what is surging across podcasts, measured against its own baseline
Alerts — when a name you follow appears in a newly indexed episode
No account is needed to search Radar.