@abshekha: Had a great time talking about ๐๐ ๐๐ด๐ฒ๐ป๐ ๐๐ฎ๐ฟ๐ป๐ฒ๐๐ ๐๐ป๐ด๐ถ๐ป๐ฒ๐ฒ๐ฟ๐ถ๐ป๐ด at Large Scale Production Engineerโฆ
Summary
The author gave a talk at Google on AI Agent Harness Engineering, demonstrating a Financial Agent using Gemma 4 local LLMs that ran under 15 GB RAM and performed on par with frontier models.
View Cached Full Text
Cached at: 06/28/26, 10:05 AM
Had a great time talking about AI Agent Harness Engineering at Large Scale Production Engineering, Google.
I gave an example of building a Financial Agent to analyse my credit card spends using Gemma 4 family of Local LLMs.
Everything running under 15 GB RAM on my laptop!
The agent was performing quite well & in some cases, at par with the frontier models.
This was a clear testimony for the importance of Harness Engineering to build effecting Agents.
Linking the YouTube talk in the following Tweet. Will link the repo soon.
Similar Articles
@analogalok: I just got Gemma 4 26B A4B MoE model running fully locally with Hermes agent on an 8GB RTX 4060 and it's now backtestinโฆ
A developer demonstrates running Gemma 4 26B MoE model locally on an 8GB RTX 4060 with Hermes agent to fully automate backtesting of trading strategies, highlighting the growing capability of local LLMs as autonomous agents.
@KanikaBK: Google just dropped an AI bomb! A BILLION DOLLARS Game is on. Gemma 4 12 B runs on your laptop. 16 GB of RAM, that is aโฆ
Google released Gemma 4 12B, an open-source multimodal AI model under Apache 2.0 that runs locally on laptops with 16GB RAM, targeting enterprise edge deployment.
@rachpradhan: holy shit @ivanleomk i used @GoogleDeepMind's gemma4(with codegraff) on the flight to Japan to read through a few paperโฆ
A user shares their positive experience using Google DeepMind's Gemma 4 model with the open-source tool codegraff to read and analyze papers during a flight. Codegraff is a lightweight AI agent that runs code, automates tasks, and supports multiple models, claiming significant cost and performance advantages over Claude Code and Codex.
@LyalinDotCom: Back at work after dinner with my colleague, getting some learning time in... Trying to get more familiar with how our โฆ
Google launched Managed Agents in the Gemini API, allowing developers to create AI agents with reasoning, tool use, and code execution in isolated Linux environments via a single API call.
@googledevs: Most agent demos are stateless. Ask โ answer โ context gone. Production agents need to run for days โ pausing, resumingโฆ
Google Devs introduces Agent Factory series with ADK 2.0 and Gemini 3.5 Flash, demonstrating how to build production-grade stateful agents that can run for days, featuring insights on skills, MCP, and code review strategies from engineers like Rohde Davis.