By Sagar Shankaran, Founder of CallSphere
NotebookLM Pro adds custom research agents, Audio Overviews v2, and a 5M-token corpus per notebook — here is what changed. Practical context for teams in San Francisco, CA.
Key takeaways
NotebookLM Pro is the consumer surface for Gemini 3 Pro — a notebook with a real research agent inside it.
This briefing is written with builders in San Francisco, CA in mind — local procurement, latency from regional Google Cloud / AWS / Azure regions, and time-zone-friendly support windows shape the practical recommendations.
Google's April 2026 cadence around the Gemini 3 family, Antigravity, and the AgentSpace surface is the most coherent product narrative the company has put together in years. The pieces fit: a frontier model (Gemini 3 Pro), a fast variant (Gemini 3 Flash), an on-device tier (Gemini Nano), an IDE (Antigravity), an agent runtime (Vertex Reasoning Engine), an agent catalog (Agent Garden), an enterprise hub (AgentSpace), and a consumer notebook (NotebookLM Pro). For builders, the practical impact is that you can pick a Google story for almost any agent shape and have a credible delivery path from prototype to production.
On SWE-bench Verified, Gemini 3 Pro scores 71.8% — within striking distance of Claude Opus 4.7's 72.9% and ahead of GPT-5.5's 69.4%. On tau-bench retail, the new model lands at 95.1%, a meaningful jump from Gemini 2.5's 88.6%. MMMU sits at 84.0%. The numbers matter less than the spread: for the first time, the three frontier labs are within 3 percentage points of each other on most benchmarks that builders cite.
For San Francisco, CA teams, the practical near-term move is to set up an evaluation harness against your top 3 production prompts before committing to a model swap.
Gemini 3 Pro is priced at $1.25 / $10.00 per million input/output tokens up to 200K context; long-context (>200K) tier kicks in at $2.50 / $15.00. With prompt caching at a 75% discount and a 50% Batch API discount on async workloads, the realized cost for many production agents lands closer to $0.80 per million blended tokens. Compared to Claude Opus 4.7 ($15/$75) and GPT-5.5 ($10/$30), Gemini 3 Pro is positioned as the price-aggressive frontier option.
The recommended path is prototype in AI Studio, then promote to Vertex AI for production. Vertex provides regional availability (12 regions globally, including europe-west4 and asia-southeast1), VPC-SC, CMEK, audit logging, and the new Reasoning Engine managed runtime. AI Studio's prompt IDE got a major refresh — versioned prompts, side-by-side eval, and one-click deployment to Vertex are now first-class.
Hear it before you finish reading
Talk to a live CallSphere AI voice agent in your browser — 60 seconds, no signup.
This is the short version; the full vendor documentation has more nuance, particularly on rate limits and regional availability.
If you are evaluating this release for a 2026 deployment, work through the following checklist before signing a contract:
Q: Is Gemini 3 Pro available in my region?
A: Gemini 3 Pro is generally available in 12 Vertex AI regions as of May 2026, including us-central1, europe-west4, asia-southeast1, and asia-northeast1. Check the Vertex AI region availability docs for the latest list.
Q: How does Gemini 3 Pro pricing compare on a real workload?
A: Headline price is $1.25 / $10.00 per million tokens up to 200K context. With 75% prompt cache discount and 50% Batch API discount, realized blended cost on long-running agent workloads typically lands at $0.80-$1.20 per million tokens.
Q: Can I use Antigravity with Claude or GPT-5.5?
A: Yes. Antigravity is unusually open — Claude Opus 4.7, GPT-5.5, and Gemini 3 Pro are all first-class providers in the IDE settings.
Q: What is the difference between A2A and MCP?
A: MCP is the agent-to-tool protocol; A2A is the agent-to-agent protocol. They are complementary, not competitive — most production agent stacks will use both.
Still reading? Stop comparing — try CallSphere live.
CallSphere ships complete AI voice agents per industry — 14 tools for healthcare, 10 agents for real estate, 4 specialists for salons. See how it actually handles a call before you book a demo.
Last reviewed 2026-05-05. Pricing and benchmarks change frequently — check primary sources before relying on numbers in this article.
Reading NotebookLM Pro Launches With Custom Agents and Audio Overviews v2 as an operator, the question isn't 'is this exciting?' — it's 'does this change anything in my agent loop, my prompt cache, or my cost per session?' For an SMB call-automation operator the cost of chasing every new release is real — re-baselining evals, re-pricing per-session economics, retraining the on-call team. The ones that ship adopt slowly and on purpose.
Google's AI position spans three layers worth keeping straight: the Gemini family (general-purpose multimodal models), Vertex AI (the managed runtime, MLOps tooling, and enterprise-grade governance around them), and a growing set of vertical plays (Med-PaLM-class healthcare models, retail-specific search, document-AI for ops). For SMB call automation, the realistic Gemini fit today is post-call analytics, multimodal document handling (insurance card photos, ID verification, receipts), and longer-context summarization — not the realtime audio inner loop, where streaming stability and tool-call latency still favor incumbent realtime APIs. Vertex AI is where the enterprise governance story lives: VPC service controls, regional pinning, audit logging, and IAM that maps cleanly onto an existing GCP estate. CallSphere's evaluation pattern for Google AI: keep Gemini in the analytics evals queue, lean on Vertex when a customer's compliance posture requires GCP-native data residency, and re-evaluate the realtime story on every major release. Google's vertical-AI plays are worth tracking because they signal where the specialist-model market is headed.
Q: Why isn't notebookLM Pro Launches With Custom Agents and Audio Overviews v2 an automatic upgrade for a live call agent?
A: Most of the time it doesn't, and that's the right starting assumption. The relevant test is whether it improves at least one of: p95 first-token latency, tool-call argument accuracy on noisy inputs, multi-turn handoff stability, or per-session cost. Real Estate deployments run 10 specialist agents with 30 tools, including vision-on-photos for listing intake and follow-up.
Q: How do you sanity-check notebookLM Pro Launches With Custom Agents and Audio Overviews v2 before pinning the model version?
A: The eval gate is unsentimental — a regression suite that simulates real call traffic (noisy ASR, partial inputs, tool-call timeouts) measures four numbers, and a candidate has to win on three of four without losing badly on the fourth. Anything else is treated as a blog post, not a stack change.
Q: Where does notebookLM Pro Launches With Custom Agents and Audio Overviews v2 fit in CallSphere's 37-agent setup?
A: In a CallSphere deployment, new model and API capabilities land first in the post-call analytics pipeline (lower stakes, async, easy to roll back) and only later in the live realtime path. Today the verticals most likely to absorb new capability first are Real Estate and Sales, which already run the largest share of production traffic.
Want to see salon agents handle real traffic? Walk through https://salon.callsphere.tech or grab 20 minutes with the founder: https://calendly.com/sagar-callsphere/new-meeting.
Written by
Sagar Shankaran· Founder, CallSphere
Sagar Shankaran is the founder of CallSphere, where he builds production AI voice and chat agents deployed across healthcare, hospitality, real estate, and home services. He writes about agentic AI, LLM engineering, and shipping voice agents that handle real calls in production.
See how AI voice agents work for your industry. Live demo available -- no signup required.
Anthropic's May 2026 push positions Claude as a vertical platform for financial services. The strategic positioning versus OpenAI and Google.
Workspace Studio puts a Gemini-powered AI agent builder inside Google Workspace. A walkthrough of what it does, who it is for, and where it fits in 2026.
At Cloud Next 2026 Google renamed Vertex AI to Gemini Enterprise Agent Platform and absorbed Agentspace. What actually changed and why a rebrand made sense.
Google donated the Agent-to-Agent (A2A) protocol to the Linux Foundation at Cloud Next 2026. What this means for vendor neutrality and your agent stack.
Jules's GitHub integration takes an issue, writes a fix, runs tests, and opens a PR — here is the architecture and pricing. Practical context for teams in North Carolina.
How Llama Guard 4 compares to OpenAI's Moderation API on accuracy, latency, and cost — for both open and closed model deployments. Practical context for teams in Seattle, WA.
© 2026 CallSphere LLC. All rights reserved.
Watch how CallSphere handles real customer calls, schedules appointments, and processes payments — live.