Assertion Supported AI assessment confidence: 90% certainty 4/5 debate potential 2/5

Basu Mallick: Google was first to introduce tool chaining for live APIs

Shrestha Basu Mallick · [AIEWF Preview] Gemini in 2025 and Realtime Voice AI · Jun 2, 2025 · at 8:33

Shrestha Basu Mallick highlights Google's feature releases around tool chaining and function calling for the Gemini Live API.

0:00 / 0:08exact quote · 8.3s

▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark

“Again, we were very proud because we introduced tool chaining first, so you could change search and code execution to all kinds of analysis.”

quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →

The claim, plainly

Google was the first AI provider to introduce tool chaining combining search and code execution for multimodal live models.

a quote alone can be ambiguous, so this restates it with the references and context of the conversation around it resolved. AI-written; the tape below the player is the source.

Assessment

Public product release records confirm that Google was the first AI provider to introduce built-in tool chaining combining search and code execution in a real-time multimodal model. With the announcement of Gemini 2.0 Flash and the experimental Multimodal Live API on December 11–12, 2024, Google introduced native server-side tool execution combining Grounding with Google Search and Python code execution within bidirectional streaming sessions. In contrast, OpenAI's Realtime API (launched October 2024) supported only client-executed function calling without built-in server-side tool chaining for search and code execution, and Anthropic had not launched a real-time multimodal streaming API as of June 2025.

Google announced Gemini 2.0 Flash and the Multimodal Live API on December 11–12, 2024, featuring built-in multi-tool chaining combining Grounding with Google Search and server-side Code Execution in live streaming sessions.
OpenAI's Realtime API (launched October 1, 2024) relied on client-side function dispatching rather than server-side built-in web search and code execution chaining.
No other major provider (including Anthropic) had deployed built-in search and code execution tool chaining in a live bidirectional multimodal API prior to Google's release.

Checked against

[1] mamezou-tech.com [2] inworld.ai [3] stackademic.com [4] openai.com [5] llmgateway.io [6] youtube.com [7] blog.google [8] googleblog.com

"Multimodal Live API" "code execution" "Google Search" Gemini "OpenAI" "Realtime API" "built-in" "search" OR "code execution" OpenAI Realtime API tool calling code execution search "OpenAI" "Realtime API" "code interpreter" OR "web search" "Multimodal Live API" "Google Search" "Code Execution"

assessed as of 2026-09-02

This assessment is an AI reading of a public statement, made against the cited references with the confidence shown. It can be wrong. The quote, the tape and the references are all on this page; if something is off, use report an error below. full disclaimer →

Mentioned

Google tool chaining

⚑ Spot an error? Report it

More from Shrestha Basu Mallick

Prediction Not checkable as stated

Basu Mallick: Most voice use cases will transition to audio-to-audio models

“I do think perhaps eventually For most use cases, as these audio to audio architecture models get better, a lot of use cases will probably transition to that.”

Shrestha Basu Mallick Jun 2, 2025 ▶ 11:29 [AIEWF Preview] Gemini in 2025 and Realtime Voice AI

Assertion Contradicted

Mallick: Gemini recognizes distinct voices as an unsupported emergent behavior

“This is not officially supported yet. The model just does it.”

Shrestha Basu Mallick Jun 2, 2025 ▶ 21:31 [AIEWF Preview] Gemini in 2025 and Realtime Voice AI

Assertion Supported

Mallick: Google was first to market with live video API input

“So we were actually the first to market with also video input”

Shrestha Basu Mallick Jun 2, 2025 ▶ 7:53 [AIEWF Preview] Gemini in 2025 and Realtime Voice AI

Prediction Not checkable as stated

Mallick: Google's URL Context tool will enable developer research agents

“And I think that this will unlock new use cases. Like if people want to build their own version of a research agent, which is something developers ask us for a lot.”

Shrestha Basu Mallick Jun 2, 2025 ▶ 3:43 [AIEWF Preview] Gemini in 2025 and Realtime Voice AI

Assertion Not checkable as stated

Basu Mallick: Transcription was one of Gemini Live API's biggest early use cases

“Transcription actually, even before we released native audio, now of course you get text and audio interleaved in the output, but transcription used to be one of the biggest use cases we had on the live API.”

Shrestha Basu Mallick Jun 2, 2025 ▶ 7:25 [AIEWF Preview] Gemini in 2025 and Realtime Voice AI

Assertion Partly supported

Basu Mallick: Early Gemini Live sessions were capped at 20m audio, 5m video

“Like when we started, you could do like 15 to 20 minutes of audio, I'm sorry, and about five minutes of video.”

Shrestha Basu Mallick Jun 2, 2025 ▶ 8:05 [AIEWF Preview] Gemini in 2025 and Realtime Voice AI

Basu Mallick: Google was first to introduce tool chaining for live APIs

More from Shrestha Basu Mallick

Turn any episode into a week of clips.