#
2026
#
February
#
19th February 2026
Following on from yesterday's post, macOS Tahoe 26.4 Beta also breaks Karabiner-Elements.
Given Apple seems to have made some MAJOR under-the-hood changes to macOS Tahoe 26.4 Beta, I would avoid upgrading for the time being.
Iain Anderson and myself (Chris Hocking) will be on Final Cut TV LIVE! tonight!
We'll be chatting about our upcoming ScriptStar application release.
You can watch on YouTube:
Dylan Higginbotham has posted a new blog post titled, The Easiest Way to Add Captions in Final Cut Pro (Just 3 Steps).
You can read about it on the Stupid Raisins blog.
Introducing Agentic Editing in Jumper! 🥳
Jumper now integrates with Claude Desktop and OpenAI Codex Desktop, allowing AI agents to operate directly inside Jumper.
This is pretty crazy stuff.
These integrations let agents query Jumper’s backend and orchestrate multi-step workflows across your analysed media.
With these new integrations, the agent can operate Jumper just like a human.
- Search visually across analyzed footage
- Search across transcriptions
- Retrieve clip segments
- Find similar clips
- Find clips by face recognition
- Trigger workflow actions (e.g. export a sequence to Premiere, Final Cut Pro, DaVinci Resolve or Avid Media Composer)
But it can also do things that you can’t do with the normal Jumper interface.
For example:
- Export scenes as individual files to a folder
- Export a set of clips as a sequence for your editing software
Since the agent is acting as the orchestrator of the workflow, you can give it a complex task and it will break it down into smaller steps and execute them in the correct order. For example:
- “use Jumper to find all shots of Anna smiling, export as individual files and also export a sequence to premiere”
- “use Jumper to cut a sizzle reel from the event footage in /day1_footage/ and the voiceover is sizzle_reel_audio.wav”
This has the potential to speed up time consuming tasks that are a part of the routine media production process. Finding B-roll that matches a script, pulling every clip of a certain person, creating sequences of selects and probably a host of other tasks that we haven’t thought of yet.
Since you can run multiple agents in parallel, you can fire off multiple tasks at the same time and focus on other tasks while the agents are working.
At the moment, Jumper is compatible with Claude Desktop (Chat, Cowork and Code) and OpenAI Codex Desktop. The team are working on adding support for other agents in the future.
If you're interested in testing out MCP support in Jumper, make sure you sign up for a free trial and join the Discord.
Pipeline Neo v2.3.1 has been released!
For those unfamiliar, Pipeline Neo is an experimental FCPXML library built with the assistance of LLM tools.
It currently supports reading, creating, and modifying FCPXML documents and bundles, with parsing and validation against bundled DTDs spanning versions v1.5 through v1.14.
Typed models cover resources, clips, adjustments, filters, transitions, multi-cam, captions, smart collections and many more.
Pipeline Neo provides a strong foundation and the essential building blocks for expanding FCPXML parsing and reading capabilities and adding features.
You can learn more on GitHub.