# Changelog > Every Entelligence release, newest first: Code Review, Agent Insights, Model Router, the World Model, Ask Ellie and the Ellie CLI, one page per release. Source: https://entelligence.ai/changelog Updated: 2026-11-03 ## [World Model nodes grow their connections in place](https://entelligence.ai/changelog/2026-11-03-world-model-connected-globe.md) Nov 3, 2026 · World Model The World Model now opens on every category together, and clicking a node grows its connections on the same globe while the view zooms in on it. Anyone tracing a product area to the tasks and sessions behind it sees the whole neighbourhood without leaving the globe. ## [Review replies check the fix in current code](https://entelligence.ai/changelog/2026-11-03-review-replies-check-current-code.md) Nov 3, 2026 · Code Review When an author replies "Fixed in ", Code Review now reads the commented file at the head of the pull request before it answers. A thread resolves on code the reviewer has read, so a resolved finding can be trusted. ## [Turn any Ellie answer into an automation](https://entelligence.ai/changelog/2026-10-31-ask-ellie-automations.md) Oct 31, 2026 · Ask Ellie Automations now live in Ask Ellie. When a question is worth asking every week, one click under the answer schedules it, and Ellie suggests it for you once you have asked the same thing three times in seven days. ## [Ask Ellie inside the World Model](https://entelligence.ai/changelog/2026-10-28-ask-ellie-on-the-world-model.md) Oct 28, 2026 · World Model The World Model has a side panel where you can ask Ellie about whatever you are looking at. As it searches, the globe lights up the nodes it visits, so you watch the answer being found. ## [Route each API request with model auto](https://entelligence.ai/changelog/2026-10-16-model-auto.md) Oct 16, 2026 · Model Router The Model Router now serves plain API traffic as well as coding agents. Set the model to "auto" on an OpenAI or Anthropic shaped request and the router picks the cheapest model that can handle that one request. ## [agentplay: replay any coding agent session](https://entelligence.ai/changelog/2026-10-14-agentplay-open-source.md) Oct 14, 2026 · agentplay agentplay replays your coding agent sessions as a map and a timeline: what the agent read, what it edited, what failed and what it shipped. It runs locally with one command, and it is open source under Apache 2.0. ## [Replay any agent session, step by step](https://entelligence.ai/changelog/2026-09-24-session-explorer.md) Sep 24, 2026 · Agent Insights Agent Insights now has a Session Explorer: pick a session and step through what the agent read, edited, spent and retried, in order. The map lights each branch as the agent reaches it, and the timeline lanes show errors, cost and context at every step. ## [The World Model opens to every org](https://entelligence.ai/changelog/2026-09-23-world-model-for-every-org.md) Sep 23, 2026 · World Model Every org can now open the World Model: one globe of the issues that keep recurring across your repos. Pick a pattern and it explains itself in a few bullets, such as how often it fires and what fixed it. ## [Model Router: your keys, every provider](https://entelligence.ai/changelog/2026-08-24-model-router-keys-for-every-provider.md) Aug 24, 2026 · Model Router Bring a key for each provider your organization already pays, and Model Router routes through it. When none of your keys serves the model it picks, the turn runs on your Entelligence credits. A model policy keeps blocked models out of every route. ## [Review Scorecard: code quality and blast radius](https://entelligence.ai/changelog/2026-08-03-review-scorecard-and-blast-radius.md) Aug 3, 2026 · Code Review Every review now scores two things separately: the quality of the code, and how much of the system it can break. The Review Scorecard combines them into a merge confidence you can trace back to its cause. ## [Model Quality, measured on your own PRs](https://entelligence.ai/changelog/2026-07-24-model-quality-on-your-own-prs.md) Jul 24, 2026 · Agent Insights Model Quality compares the models your team codes with on the pull requests they actually produced. Each rate shows the sample behind it, so a small sample can never pass for a verdict. ## [Agent Insights: agent spend against project budgets](https://entelligence.ai/changelog/2026-07-06-agent-insights-spend-budgets-and-skills.md) Jul 6, 2026 · Agent Insights Agent Insights shows what your coding agents cost in dollars, project by project against each budget. Open a project and its spend is charted week by week against the budget, so an overrun shows up before the month ends. ## [The CLI signs in from your browser](https://entelligence.ai/changelog/2026-06-01-cli-browser-sign-in-and-skills.md) Jun 1, 2026 · Ellie CLI Getting the CLI working is now one command and one click in the browser. Signing in wires its skills into the coding agents it finds, such as Claude Code and Cursor, and the CLI updates itself, so the whole team stays on the same version. ## [Tickets and Fix Now for production incidents](https://entelligence.ai/changelog/2026-05-11-tickets-and-fix-now-for-incidents.md) May 11, 2026 · Incident Knowledge Every production pattern in Incident Knowledge can now become a Linear or Jira ticket, with a team and an owner, from its own row. The ticket then sits on that row beside Fix, which runs Fix Now and opens a fix pull request.