AI · Official
Stretto Builds AI Voice Agent Tara on Amazon Nova 2 Sonic for Bankruptcy Intake
Amazon AWS Machine Learning blog ·

At a glance
Stretto, a company that runs the Bankruptcy.com site, built a phone-based AI voice agent named Tara. Tara talks with callers who are considering bankruptcy and collects detailed financial information in conversation. The agent is built on Amazon Nova 2 Sonic, a speech model that handles voice input and output in one system.
Key points
- Tara replaces a short web form that many visitors left before finishing.
- Tara asks callers a full bankruptcy questionnaire and collects financial details in real time.
- After each call, the system sorts the lead as qualified, disqualified, or needing more information, based on rules set by attorneys.
- Nova 2 Sonic handles speech directly in one model, which aims to lower delay and sound more natural.
Why it matters
Phone intake can collect richer lead data for attorneys, and the post shows how a company built a voice agent for a sensitive financial use case.
Original source
How Stretto built an AI voice agent with Amazon Nova 2 Sonic
Amazon AWS Machine Learning blog · Nov 19, 03:58 KST
Read on Amazon AWS Machine Learning blog ↗AI summarized the original article. Check the original for accuracy. Copyright belongs to Amazon AWS Machine Learning blog.
More from this field
- AWS Guide Shows How AgentCore Gateway Reaches Private APIs Through a Central Firewall
AWS published a guide for connecting Amazon Bedrock AgentCore Gateway to private APIs and MCP servers in a network where all traffic must pass a central firewall. The network team keeps control of every subnet, and the Gateway's requests and replies go through the inspection VPC in both directions. The setup places a VPC Lattice resource gateway in the network account and routes it through a transit gateway. The guide was tested in a lab in the us-east-1 region.
Amazon AWS Machine Learning blog · Nov 19, 04:05 KST - AWS Quick User Group DC Meetup Shows How Companies Prepare Data for AI Agents
AWS held an inaugural AWS Quick User Group meetup in Arlington, Virginia, on October 7, 2026. Data leaders and developers talked about how to prepare company data so AI agents can use it. One firm, Financial Independence Group (FIG), shared how it is using AWS Quick for its analytics.
Amazon AWS Machine Learning blog · Nov 19, 03:54 KST - Why Fine-Tuning Jobs Run Longer Than FLOP Estimates Predict on Shared GPUs
A team tested how well the usual FLOP-based estimate predicts how long a fine-tuning job takes on shared GPUs. Using 272 real runs on H200 GPUs, the simple estimate explained little, while a learned model using pre-dispatch information did far better. The gap comes from overheads like setup, evaluations, and checkpoint saves that the formula misses.
Hugging Face blog · Nov 19, 03:53 KST - Microsoft Launches Seven Cheaper In-House AI Models to Replace Outside Ones
Microsoft AI has released seven new in-house models for coding, security, images, speech, and routing, all at once at its Ignite conference. The company says they match rival models at a much lower cost, and it is aiming them at AI agents that run around the clock.
The Decoder · Nov 19, 03:47 KST