
π From Napkin Sketch to data-driven real-estate advisor Agent in Under 40 Minutes? π Can a...
{% embed https://youtu.be/US8lAtHja_s %}
π From Napkin Sketch to data-driven real-estate advisor Agent in Under 40 Minutes? π
Can a coding agent really work autonomously on complicated problems without human intervention? I decided to put Googleβs new Antigravity 2.0 and Gemini 3.5 to the test: The Napkin Challenge. π
The goal: Build and deploy a real estate investment advisor - based on real-world data, starting with nothing but a rough sketch on a napkin.
The Result? With the right context, yes!
I used: Antigravity 2.0 & Gemini 3.5: Architect and execute the plan Agent CLI Skills: Scaffold, build, test and evaluate the agent using ADK.3 Developer Knowledge MCP: Provided necessary context to connect to BigQuery MCP and integrate the census dataset for grounded investment advice. Parallelized Workflow using sub-agents: While the system ran the evaluation suite, it simultaneously deployed the agent to Cloud Run.
The Outcome:
The "Napkin Challenge" proves that when you combine the right context with powerful models, the barrier between an idea and a deployed product has virtually disappeared.
I challenge you: What is your "napkin" project? Try it with Antigravity 2.0 and Gemini 3.5. π
π How to join the challenge -
gemmaI ported the whole Gemma-4 family β E2B, E4B, 12B, 31B, and the 26B-A4B MoE β to run on...
communityHey DEV, I'm Tobore. Let's actually connect. I've been on here for a while now, mostly writing and...
ai(yep, kinda clickbait, just for the funsies π) At the beginning of the year, I relaunched my...
aiMy laptop was sitting idle with the fan at full tilt. Nothing was running that I knew of. The culprit...
githubactionsI Built a Thing! TL;DR β Google Gemini-based Pull Request reviews and Issue Triaging for...
aiI've been hearing the word "harness" thrown around a lot lately. I assumed it just meant "the IDE" or...
Workflows from the Neura Market marketplace related to this CoPilot resource