Chat Simulation V1, Agent Prompt Optimiser, and Reliability Upgrades
Simulation for text chat agents, a six-strategy automated prompt optimiser, selective optimisation against specific calls, and resilience on restarts.
135 stories
Simulation for text chat agents, a six-strategy automated prompt optimiser, selective optimisation against specific calls, and resilience on restarts.
Context-aware debugging that explains why a simulation failed and how to fix it, full lifecycle for personas, structured JSON sessions, Optimiser backend.
Scenarios that branch into multiple conversation paths, ambient noise profiles that push simulations closer to production, and a critical-issue feed.
Logs, latency, cost on every simulation call. Retell agents, outbound calling, tool-level verification in Simulate. Plus editable personas and Run Prompt.
Workspace credit attribution, a 3-step guided agent builder with multi-language, rebuilt Prompt Workbench with commit history, and 4 new TTS providers.
ai-evaluation SDK launches with 50+ templates. Pre-built and custom personas come to simulation, with dataset-derived personas from real call transcripts.
As we draw closer to the end of another year, we're back with our penultimate quarterly update for this year so we can share some exciting updates across the board. We'll give you a quick rundown of these updates so you can start using them to improve and optimize your business operations.
Observability ships for three voice platforms at once. Evaluation groups integrate with experiments and optimization. Call Simulation now SDK-triggerable.
Upload an SOP or call transcript to auto-generate test scenarios with edge cases. Commit-style version control for agents. Session observability per span.
Zero-config performance insights on agent traces, statistical dashboards for annotator agreement, and multi-workspace isolation with audit logging.
Redesigned summary dashboards with new chart types and side-by-side compare, a rebuilt alerts system, Prompt SDK upgrades, and RBAC workspace access.
Upload documents into datasets with built-in OCR, write deterministic function evals for objective checks, and run evaluations async from the SDK.
The Explorer Agent redefines how MinusX works. Unlike earlier agents that needed hand-selected tables or models, Explorer digs deep across your entire Metab...
AI-conducted phone calls test voice agents end-to-end. Plus an interactive sandbox for evaluations in real time, with inline scoring on any trace span.
Infrastructure metrics alongside agent traces in Observe, image tracing for AWS Bedrock, and standalone mode + feedback loops in the Eval Playground.
At the halfway mark of an extraordinarily special year for all of us in the Zoho CRM team, we come to you with another update post to bring you all up to speed on everything new and powerful in Zoho CRM.As usual, since our last announcement, our team has been at the top of their game, working hard…
MinusX works by determining the "right context" for the surface you're in - be it a SQL query page, question builder page or a dashboard page. This works we...
Real-time alerts with Slack and email, gRPC trace transport with 60% less latency, and a visual graph of agent execution inside Observe.
Showing 126 of 135 stories
Load more storiesGet the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts