Hey y’all I would love to build a system with Claude or some AI that can understand my ICP and what I sell, get trained on a sequence, researvh prospects, get high quality leads, personalize the message and send an email to these people through maybe GoHighLevel or something else. I want to be able to automate the process and have Claude handle it all and book me in for a sales call. I also wanna train Claude on a method of adjusting stimuli called “the scientific method” so that Claude can use the method and adjust stimuli according to the feedback it gets, OR submitt the dailt inputs it has done and let me give it feedback instead. Is it possible to build such a system with Claude?

Hey you all. I am wondering if trillet or retell is better if I am making an Ai receptionist in a different language? I am making a swedish receptionist and it has to sound natural but I don't know how to choose a plattform that can handle a native language in the way it is supposed to be spoken given instructions on behavior. Is trillet or retell or any other plattform better at handling in Swedish and other languages? Can trillet be used for other languages like swedish?

Hi All, Has anyone set up both inbound and outbound calling for a voice AI agent? If so, how did you handle it? Through prompting? Seems inefficient to use a multi purpose prompt (would be very long and eat up tokens on every call). Use case: inbound calls classify caller as prospect, current client, vendor/supplier, field technician or urgent caller and then routes call to proper workflow (get info, take message, schedule appt., forward call, etc.), updates crm records etc. If field technician, records info on job status, updates job and creates task list. Outbound: calls suppliers back, makes call based on tasks created by field technician such as calls supplier to place order, calls sub contractor to schedule work, etc.

Google just dropped Gemini 3.5 Transcribe, and it's their most accurate speech-to-text model yet, built to handle real conversations instead of just clean studio audio. - Word error rate down to 4.0% for streaming and 2.6% for pre-recorded audio, measured by Artificial Analysis - That's a big jump from their old model, Chirp 3. Time to final transcription is 70% faster - Handles up to 85 languages and picks up on accents and dialects automatically - Cleans up your speech as you talk. Cuts filler words like "um" and "ah" and fixes self-corrections like "let's meet Tuesday, no wait, Wednesday" - Can identify up to 3 speakers in recorded audio with timestamps, which is huge for meeting notes and call analytics - It can also call other Gemini models to do stuff like generate images or analyze files, all triggered by voice - Already live in things like Rambler on Android and the Gemini app on macOS, and rolling into Chrome soon - Developers can plug it into their own apps now through the Gemini API and Google AI Studio If you're building any kind of voice agent, meeting notes tool, or automation that starts with "listen to this audio," this is worth testing against whatever you're using now. I still use Deepgram Nova 3 or Flux for my voice agents. But I might start using Gemini 3.5 Transcribe if I like the results. Will ultimately come down to latency. https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-5-transcribe

Google just dropped another Flash model, and it's only been three weeks since the last one. Gemini 3.7 Flash is out, and the headline is that it beats 3.6 Flash across coding, document work, and agent tasks while launching at half the price per million tokens. - Intro pricing sits at $0.75 per 1M input tokens and $3.75 per 1M output - That intro rate ends Dec 31, 2026, then it jumps to $1.50 and $7.50 - AutomationBench score went from 17.0% to 30.4%, so real business workflows nearly doubled - Coding jumped too: DeepSWE v1.1 hit 65.3% vs 49.0% on the old model - FrontierCode 1.1 came in at 43.6% vs 34.4% - WebDev Arena Elo moved from 1538 to 1588 for front end builds - PDF comprehension climbed from 22.0% to 34.0% on the GDP.pdf benchmark - Google says it plans better, calls tools more carefully, and needs fewer retries - Gemini Spark, the 24/7 personal agent, switched to 3.7 Flash today in 160+ countries - Live in AI Studio, Antigravity, and Gemini Enterprise right now The release cadence is what gets me here. Three weeks between models means the cheap tier is now moving faster than most of us can rebuild our workflows around it. Are you guys rebuilding for every new model drop, or waiting for things to settle down? haha https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-3-7-flash/