Intel / video

Agents in Production: How OpenGov Built and Scaled OG Assist - Gabe De Mesa, OpenGov

Source: youtube.com
Author: AI Engineer
Date: Published Jun 26, 2026

Context

OpenGov, which supplies government software for functions such as budgeting and permitting, describes an explicit approval step in its OG Assist . According to its engineering presentation, the pauses when a proposed tool call requires human approval, and the interface lets the user accept or reject it.

That places the decision inside the execution flow, where it can prevent a configured action from proceeding. It is more specific than asking the model to behave cautiously in a prompt: the application determines which calls require approval and waits for the user's decision. The mechanism's coverage therefore depends on which operations the application marks for review.

Terms in this piece · Glossary

AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
agentic loop — The cycle an agent runs in: decide, call a tool, read the result, decide again — repeating until the goal is met or a stop condition fires.
eval — A repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.

Key quotes

“we decided to move over to our own kind of Effect Native Agent Loop to have full regency over this uh Agent Loop”
Gabe De Mesa

“always always always making sure that, um, humans are in the driver's seat”
Gabe De Mesa

“we found that having some sort of um rolling summarization was more effective than you know always stuffing in the latest and most recent uh messages”
Gabe De Mesa

“we believe that tools and skills are really all you need”
Gabe De Mesa

“we're building tools and skills for customer-facing uh agents and and that has been great, but we're also building them internally as well to help accelerate our development workflows”
Gabe De Mesa

Read the source www.youtube.com