Markdown source

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

Source Video

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

Relationship To World's Fair 2026

These slides are extracted from a public AI Engineer YouTube video connected to World's Fair 2026. Speaker-matched clips are supporting context unless later confirmed as exact session recordings; official livestream recordings are day-level/event-level source material.

Related Scheduled Sessions

• No individual scheduled session mapping has been assigned yet; treat this as an event livestream deck.

Extracted Slides

• Recreated text/layout view: open HTML recreation
• AI slide classifier: content_slide confidence 0.99
• Text source: agent_vision.

Slide text:

Agenda

1. Meet OG Assist

2. The Origin Story

3. Betting on Effect

4. The Core Agent Loop

5. A2A, Evals & Sandboxing

6. Long Context Handling

7. Monitoring & Observability

8. Tools, Skills & Dev Workflows

• Recreated text/layout view: open HTML recreation
• AI slide classifier: content_slide confidence 0.86
• Text source: advanced OCR rapidocr-live/right-72/contrast reconciled by agent.
• OCR decision: ready — two-column slide with smaller paragraph text and embedded video area

Slide text:

About OpenGov

Software for

more effective,

accountable

government.

Founded over 14 years ago, OpenGov builds ERP, budgeting,

asset management, and permitting software for state and local

government and OG Assist now connects across all of it.

• Recreated text/layout view: open HTML recreation
• AI slide classifier: content_slide confidence 0.95
• Text source: advanced OCR rapidocr-live/bright-screen/opencv-adaptive reconciled by agent.
• OCR decision: ready — product UI screenshot with small internal text plus surrounding slide copy

Slide text:

About OpenGov

Software for

more effective,

accountable

government.

Founded over 14 years ago, OpenGov builds ERP, budgeting, asset management, and permitting software for state and local government and OG Assist now connects across all of it.

• Recreated text/layout view: open HTML recreation
• AI slide classifier: content_slide confidence 0.94
• Text source: agent_vision.

Slide text:

Origin Story

One bet on agents, one immediate yes.

• Recreated text/layout view: open HTML recreation
• AI slide classifier: content_slide confidence 0.99
• Text source: advanced OCR rapidocr-live/full reconciled by agent.
• OCR decision: ready — Dense code block plus readable title.

Slide text:

Agent-to-Agent Protocol

Built Off The A2A Protocol

The A2A protocol allows OG Assist to build off a supported spec, rather than from the ground up.

• Recreated text/layout view: open HTML recreation
• AI slide classifier: content_slide confidence 0.98
• Text source: agent_vision.

Slide text:

Sandboxing

Room to act, safely.

• Recreated text/layout view: open HTML recreation
• AI slide classifier: content_slide confidence 0.98
• Text source: agent_vision.

Slide text:

Tools & Skills

UI, on the Fly

• Recreated text/layout view: open HTML recreation
• AI slide classifier: content_slide confidence 0.98
• Text source: advanced OCR rapidocr-live/full reconciled by agent.
• OCR decision: ready — Dense trace screenshot is OCR-suitable.

Slide text:

Observability

You can't scale

what you can't

see.

Source: https://effect.website/docs/observability/tracing/

Every agent run is traced end to end, giving us the visibility to debug, measure, and tune behavior at production scale.

• Recreated text/layout view: open HTML recreation
• AI slide classifier: content_slide confidence 0.98
• Text source: advanced OCR rapidocr-live/bright-screen/contrast reconciled by agent.
• OCR decision: ready — Code/editor screenshot with small text is OCR-suitable.

Slide text:

Developer Velocity

Building agents

with agents.

Claude Code, Cursor, and cloud agents accelerate how the team writes, reviews, and ships building OG Assist with the same kind of tools we ship.

Hidden Non-Slide Evidence

• `slide-001.jpg` — title_card confidence 0.97; title card
• `slide-006.jpg` — sponsor_logo confidence 0.98; logo-only partnership slide

Classification audit: raw/sources/slide-ai-classification/slides/4uFVSLgD2Q4/audit.json

Slide-Derived Subjects To Review

Subject extraction uses video title, related session titles/descriptions, transcript context, and OCR text when available. OCR is best-effort and should be reviewed against the embedded slide images.