Week 47
Telli has introduced role-based access control, allowing for custom permissions and predefined roles. Additionally, organizations can now enable single sign-on via Microsoft Entra or Okta, and manage multiple API keys per workspace.
Also shipped Nov 18, 2026telli in November 2026 →
Genie Code CLI is now generally available
Databricks has made the Genie Code CLI generally available, aligning its management with workspace Genie Code. Administrators can oversee a single Genie Code budget across both the CLI and workspace, while users can apply free monthly usage in the CLI.
Smart Routing now supports external models for coding agents (Beta)
Databricks added support for routing coding-agent subagents to external model providers in the Unity Gateway Managed Configuration beta.
V3 progress control | CodeRabbit Cloud, V3 review settings preview
CodeRabbit updated progress controls in the V3 review settings preview, allowing progress_updates configuration to control review-progress reporting format.
Hyperdrive, Workers VPC - Custom CA and client certificates (mTLS) for Workers VPC
Cloudflare Workers VPC now supports custom certificate authority (CA) verification and mutual TLS (mTLS) authentication for private VPC Services.
Spark Monitoring UI (General availability)
Snowflake announced the general availability of the Spark Monitoring UI in Snowsight for tracking and troubleshooting Snowpark Connect for Spark jobs and sessions.
Amazon OpenSearch Memory is now generally available
Amazon OpenSearch Memory is now generally available as a serverless capability in Amazon OpenSearch Service to store, extract, and retrieve persistent memory for AI agents.
More from telliEvery telli release →
Week 46
Knowledge base updates Agents can now use up to five knowledge bases at once. The system searches all of them in parallel, so answers stay fast no matter how many you add. You can also add websites as sources, and they refresh automatically daily, weekly, or monthly. This way, your agent always has the latest information.
Week 45
Charlie tasks Give Charlie work to run once or on a recurring schedule, such as reviewing calls or preparing a weekly report. Manage tasks directly from Home , create them with Charlie or set them up manually, and open a task to review its instructions and recent runs. Pause, resume, or run a task when you need it.
Week 44
Telli now supports custom code execution within agents and workflows, allowing users to run code as a workflow step.
Week 43
Analytics Analytics is now publicly available in telli. Create dashboards from scratch, start with a template, or ask Charlie to build one. Edit chart titles and descriptions directly, filter dashboards by agent and time range, and export selected dashboards as a self-contained HTML report that works offline.
Week 42
Simulations Test agents before they speak with real callers from the new Simulations page. Create reusable scenarios, choose the agent, version, and number of conversations, then inspect every run and conversation side by side.
Week 41
Browser test calls You can now test an agent directly in your browser. Choose Browser Call in the test-call dialog to test your agent without placing a phone call. Account-level call outcomes Call outcomes are now available across your account. Define an outcome once instead of repeating it for every agent.
Week 40
Webhook trigger Workflows can now start when your systems send an incoming POST request. Choose Webhook received as the trigger, copy the stable endpoint, and allow anonymous requests or protect the endpoint with a Bearer credential. You can also run the published workflow manually before enabling external requests.
Week 39
Duo agents Duo agents are now available to every account and are the default when you create an agent. Duo separates thinking from speaking for more precise conversations. You can preview speaking styles with live samples, let callers schedule a callback, handle iOS Call Screening, and ask for consent before recording.