--- schema: 1 type: video title: >- Agents in Production: How OpenGov Built and Scaled OG Assist - Gabe De Mesa, OpenGov description: >- Come and learn about building AI Agents in production. Learn hands-on directly with the AI Agents team from OpenGov which powers AI workflows across thousands of state and local governments. This session will cover: * The core agent loop/harness * A2A protocol * Building with Effect-TS and Typescript * Feedback and evals * Long context handling * Monitoring and observability * Building out tools and skills * Enterprise contribution model * Accelerating workflows with Claude and Cursor Speakers: - Gabe De Mesa (OpenGov): Gabe works on the flagship AI Agent product offering at OpenGov which serves thousands of state and local governments across the country. Gabe was one of the first engineers to join the newly formed AI Agents team. He wanted to share the features he's built, experience he's gained building and running agents in production, battle scars gained from running with real production workloads and customers, architecture, and some best practices to help other engineers run agentic workloads at their companies. X/Twitter: https://x.com/jamesjellow LinkedIn: https://www.linkedin.com/in/gabedemesa GitHub: https://github.com/gabedemesa canonical: >- https://liquidgold.cc/channel/aidotengineer/explore/video/agents-in-production-how-opengov-built-and-scaled-o-b24ddaf37398 markdown: >- https://liquidgold.cc/channel/aidotengineer/video/agents-in-production-how-opengov-built-and-scaled-o-b24ddaf37398.md llms: null parent: 'https://liquidgold.cc/channel/aidotengineer.md' channel: aidotengineer updated: '2026-10-24T09:25:13.529Z' language: null children: [] videoId: 4uFVSLgD2Q4 durationSeconds: 1110 publishedAt: '2026-06-26T07:00:38.000Z' searchChunks: - ordinal: 0 text: null startSeconds: 102 endSeconds: 195 watch: 'https://liquidgold.cc/watch/4uFVSLgD2Q4?t=102' heldReason: rights - ordinal: 1 text: null startSeconds: 207 endSeconds: 295 watch: 'https://liquidgold.cc/watch/4uFVSLgD2Q4?t=207' heldReason: rights - ordinal: 2 text: null startSeconds: 305 endSeconds: 420 watch: 'https://liquidgold.cc/watch/4uFVSLgD2Q4?t=305' heldReason: rights - ordinal: 3 text: null startSeconds: 420 endSeconds: 432 watch: 'https://liquidgold.cc/watch/4uFVSLgD2Q4?t=420' heldReason: rights - ordinal: 4 text: null startSeconds: 432 endSeconds: 525 watch: 'https://liquidgold.cc/watch/4uFVSLgD2Q4?t=432' heldReason: rights - ordinal: 5 text: null startSeconds: 536 endSeconds: 615 watch: 'https://liquidgold.cc/watch/4uFVSLgD2Q4?t=536' heldReason: rights - ordinal: 6 text: null startSeconds: 536 endSeconds: 615 watch: 'https://liquidgold.cc/watch/4uFVSLgD2Q4?t=536' heldReason: rights - ordinal: 7 text: null startSeconds: 626 endSeconds: 727 watch: 'https://liquidgold.cc/watch/4uFVSLgD2Q4?t=626' heldReason: rights - ordinal: 8 text: null startSeconds: 626 endSeconds: 727 watch: 'https://liquidgold.cc/watch/4uFVSLgD2Q4?t=626' heldReason: rights - ordinal: 9 text: null startSeconds: 739 endSeconds: 822 watch: 'https://liquidgold.cc/watch/4uFVSLgD2Q4?t=739' heldReason: rights - ordinal: 10 text: null startSeconds: 822 endSeconds: 834 watch: 'https://liquidgold.cc/watch/4uFVSLgD2Q4?t=822' heldReason: rights - ordinal: 11 text: null startSeconds: 834 endSeconds: 933 watch: 'https://liquidgold.cc/watch/4uFVSLgD2Q4?t=834' heldReason: rights - ordinal: 12 text: null startSeconds: 933 endSeconds: 944 watch: 'https://liquidgold.cc/watch/4uFVSLgD2Q4?t=933' heldReason: rights - ordinal: 13 text: null startSeconds: 944 endSeconds: 1035 watch: 'https://liquidgold.cc/watch/4uFVSLgD2Q4?t=944' heldReason: rights - ordinal: 14 text: null startSeconds: 1046 endSeconds: 1110 watch: 'https://liquidgold.cc/watch/4uFVSLgD2Q4?t=1046' heldReason: rights --- # Agents in Production: How OpenGov Built and Scaled OG Assist - Gabe De Mesa, OpenGov Come and learn about building AI Agents in production. Learn hands-on directly with the AI Agents team from OpenGov which powers AI workflows across thousands of state and local governments. This session will cover: \* The core agent loop/harness \* A2A protocol \* Building with Effect-TS and Typescript \* Feedback and evals \* Long context handling \* Monitoring and observability \* Building out tools and skills \* Enterprise contribution model \* Accelerating workflows with Claude and Cursor Speakers: - Gabe De Mesa (OpenGov): Gabe works on the flagship AI Agent product offering at OpenGov which serves thousands of state and local governments across the country. Gabe was one of the first engineers to join the newly formed AI Agents team. He wanted to share the features he's built, experience he's gained building and running agents in production, battle scars gained from running with real production workloads and customers, architecture, and some best practices to help other engineers run agentic workloads at their companies. X/Twitter: https://x.com/jamesjellow LinkedIn: https://www.linkedin.com/in/gabedemesa GitHub: https://github.com/gabedemesa Canonical: https://liquidgold.cc/channel/aidotengineer/explore/video/agents-in-production-how-opengov-built-and-scaled-o-b24ddaf37398 ยท Channel: [AI Engineer](https://liquidgold.cc/channel/aidotengineer.md) > Search chunk text is held until public-source provenance is verified. ## Document chunks --- #### Chunk 0: Document excerpt (0:01 to 1:31) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 1: Document excerpt (1:31 to 3:15) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 2: Document excerpt (3:15 to 4:55) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 3: Document excerpt (4:55 to 7:00) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 4: Document excerpt (7:00 to 8:45) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 5: Document excerpt (8:45 to 10:15) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 6: Document excerpt (10:15 to 12:19) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 7: Document excerpt (12:19 to 13:54) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 8: Document excerpt (13:54 to 15:44) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 9: Document excerpt (15:44 to 17:26) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 10: Document excerpt (17:26 to 18:30) > Held: transcript rights do not permit this chunk's text.