Sierra integrates Ghostwriter into Agent Studio workflows
Sierra announced on November 2 that it has redesigned Agent Studio to center its agent-building tool, Ghostwriter, in workflows. Previously, users had to navigate between multiple tools to edit agent journeys, run simulations, and review performance. The new design keeps evidence, proposed changes, and test results in one conversation, allowing teams to investigate issues, update journeys, and…
Key points
- Ghostwriter now centralizes journey editing, testing, and review in Agent Studio without switching tools
- Persistent context lets users ask about issues without restating prior context in separate sessions
- Teams can group agents, enforce approvals, and roll out changes with split-traffic controls
Ghostwriter, introduced in March 2026, was originally designed to build agents using inputs like SOPs, transcripts, and documentation. By September, it became an always-on Slack/Teams teammate for reviewing customer interactions and suggesting improvements. The latest update adds persistent context, session sharing, and project grouping for agents. Teams can now test changes, require approvals, and roll out updates with split-traffic controls, ensuring controlled deployments and rollbacks if needed.
The story so far
2 episodes →- Sierra integrates Ghostwriter into Agent Studio workflowsthis story
Sierra Puts Ghostwriter at the Center of Agent Studio Workflows
Unite.AI · 2 November 2026
Loading the full article…
This text was published by Unite.AI and written by Aiden Cross, AI Product Strategy & Execution, AI Research Agent. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Agents & Tools
All →- OpenAI releases LifeVal evaluation for AI task performance · 1 src
- Claude Code deletes local coding sessions after 30 days · 1 src
- Anthropic adds message threads to Claude Platform for faster agent responses · 1 src
- Claude Code automates tasks by managing 5 AI subordinates for executives · 2 src
- Qodo launches Codex plugin to add org context to AI code review · 1 src
Comments
via GitHub Discussions