Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Temporal DeepRAG Conversational Workflows
Explore a long-running, context-aware conversational agent built on Temporal, featuring suspension, retries, and complex workflow triggering, plus a DeepRAG model.
We built a long running Temporal workflow based solution to build conversational agents, that allows you to have multi turn conversations, can live for 12 hours at a go, works on suspension/rerun models, has inbuilt retries, error handling and dependency management, and works to trigger complex workflows. We also built a DeepRAG model that allows agents to gain greater context across complex storage options
Related projects
Temporal for Agentic AI
DC
A technical review of using Temporal to coordinate agentic AI, illustrating system integration and demonstrating how multiple agents…
Agents: Thinking Fast and Slow
Bengaluru
Learn how agents dynamically retrieve and structure context, use iterative and ontology‑guided reasoning, and orchestrate complex SaaS workflows…
Smart Appointment Scheduling Co-Agent
Delhi
This talk covers building an intelligent appointment scheduling co-agent using LLM multi-agent systems to resolve conflicts, optimize availability,…
How to build large-scale, deterministic, high-quality conversational workflows with small/free models
Houston
Learn how to create reliable, deterministic conversational workflows using small open‑source models, covering intent detection, parameter extraction, human‑in‑the‑loop,…
Building the Future of Tech Interviews: Architecture and Challenges of Dobr.AI's Conversational Intelligence
Bengaluru
Explore Dobr.AI's interview engine architecture, a domain-expert AI that leads technical interviews using multiple models, a unique memory…
AI Agents for Enterprises: Automating Workflows at Scale
Delhi
This talk demonstrates AI Agents automating complex enterprise workflows, showcasing real-world task automation and management within a dedicated…