
Callstack is a visual regression and testing platform for voice AI agents built on AssemblyAI. It enables developers to create, run, and compare conversational test cases against different versions of their voice agents before changes reach production. Developers define test cases using real or scripted audio conversations, expected agent behavior, assertions, and configuration. Each test streams audio through AssemblyAI’s real-time speech-to-text infrastructure while Callstack captures the complete execution: transcripts, speaker turns, timestamps, tool calls, agent responses, latency, and other runtime events. The platform turns these executions into visual conversation traces, making it easy to inspect exactly how an agent behaved. Developers can run the same test against two agent versions and view them side-by-side to identify regressions such as incorrect transcription, missed entities, failed tool calls, unexpected responses, increased latency, or premature interruptions. Callstack also provides configurable assertions for validating intent detection, entity extraction, tool usage, response quality, latency thresholds, and expected conversational behavior. Failed assertions are surfaced alongside the relevant section of the conversation, making debugging significantly faster. The pipeline integrates with CI/CD so voice-agent tests can automatically run whenever a prompt, model, tool, orchestration layer, or configuration changes. Teams can establish a baseline, execute a regression suite, compare results, and block deployments when critical conversational behavior degrades. Callstack brings the workflow of Postman and visual regression testing to voice AI: define conversations, execute them, inspect what happened, compare versions, and catch regressions before users do.
30 Sep 2026
.png&w=828&q=75)
A dead-simple CRM with AI lead sourcing designed to help startups and small businesses manage customers, track sales pipelines, and discover new leads automatically. The platform uses AI to identify high-potential prospects from public business data and organize them into a clean, easy-to-use dashboard. Users can store contacts, manage conversations, schedule follow-ups, and track deal progress without the complexity of traditional enterprise CRMs. Built-in AI tools assist with lead scoring, personalized outreach suggestions, and automated interaction summaries to improve sales efficiency. The system focuses on speed, simplicity, and minimal setup so teams can start managing relationships and generating leads immediately. Additional features include email integration, activity tracking, reminder notifications, and searchable customer histories. The goal of the project is to create an affordable, lightweight sales management solution that combines CRM functionality with intelligent lead generation automation.
17 May 2026
.png&w=828&q=75)
Briefly is an ultra-fast learning tool that delivers personalized microlessons in the format users learn best—text, audio, or visuals. Instead of long courses, it breaks any topic into bite-sized, swipeable lessons generated instantly with AI. Users set their preferred learning style once, and every lesson adapts to that mode automatically. Behind the scenes, structured metadata lives in Postgres for analytics, while rich lesson content is stored in Mongo for flexibility and speed. The result is a lightweight, high-impact learning experience that feels as easy as scrolling TikTok but far more purposeful. Briefly makes rapid, personalized learning accessible to anyone, anytime, in just seconds.
19 Nov 2025
.png&w=828&q=75)
summit is an AI-powered networking assistant that helps event attendees discover and connect with the most relevant people based on shared interests, goals, behavior, and interaction styles. Attendees receive a personalized list of top 5–10 matches, complete with compatibility scores, reasons for the match, meeting suggestions, and icebreakers. With real-time feedback, explainable matches, and mutual interest detection, MatchMySummit transforms large-scale events into curated, meaningful networking experiences. Utilizing FastAPI and Groq for rapid LLM inference, we have built a platform for heightened connecting!
8 Jul 2025

Pulse is an AI-powered radiology assistant is a tool designed to enhance efficiency in medical imaging analysis by automatically generating structured diagnostic reports. It leverages AI to detect and highlight abnormalities in scans, such as fractures, tumors, or organ anomalies, and translates these findings into concise, professional summaries. The system aims to assist radiologists by reducing reporting time, providing decision support, and offering interactive feedback for refining results. This tool can streamline workflows, improve diagnostic accuracy, and ultimately enhance patient care.
11 Dec 2024