Claude Dispatch Update and Building Local AI Agents with Gemma 4

In this episode, the hosts share a hands-on update on using Claude Dispatch. They discuss how it works as a separate synced chat that can trigger and check on jobs remotely, create tickets from analysis results, and request new agents. They also reference the current friction around permissions and repository selection. The conversation then shifts to exploring local and lower-cost agentic AI workflows due to usage limits and subscription costs, including experimenting with Google’s Gemma 4 as a local “brain” via LM Studio and using Kimi in Windsurf to build a new local agent app (code-named “Loki”) with chat, tools, memory, and research capabilities.

Sponsor
Fireside
Powerful podcast hosting & analytics
By podcasters, for podcasters. Since 2016

Sign up for our newsletter
Check out our Website

00:00 Dispatch Update Kickoff
01:10 What Dispatch Can Do
03:04 Poolside Rollbar Workflow
05:37 Dispatch Integration Questions
08:35 Rethinking Work With Agents
13:50 Claude Limits Spark Local Shift
15:26 Gemma 4 Local Agent App
18:32 Building The Framework Fast
22:52 Tauri Local First Architecture
27:43 Model Switching And Cost Hacks
30:58 Loki Next Steps Wrap Up