My approach is looking for things that need a level of fuzzy logic. It can be as basic as do any of the subject lines in an inbox have some variation of ‘looks important’. I’m less sold on them doing much of anything reliably at the moment though.

I set up an MCP for jira, to hopefully avoid me from ever opening jira again.

i will just talk to the LLm, and ask it to set a task to in progress, tell me what to work on next, add tasks to sprints, tag tickets with labels / link them to epics, search for issues, create bugs / tasks etc

seems mildly helpful, with some slack mcp etc it could be useful for teams i think

i really don't want to just buy an agentic workflow from a website, so its important that i can just replace the model with whatever and that i have control of the mcp server

I once set up Jira automations and integrations so well that a developer could move a ticket all the way to ready for final PO review without actually opening up Jira, and I told my manager about this and a product manager asked in a horrified tone: "you mean they can do their work without actually reading the tickets?"

Well I have a very specific use case. Me an my team made like this shared memory for LLMs: So an llm makes an mcp call to our api with a general question. An ai agent on our side determines which tools to call (search, graph exploration, etc) to find memory "fragments" based on tags and semantic search. and then the ai agent determines if the content of the "memory fragment" is relevant to the initial question and then it returns it.

Sounds very interesting. At you releasing your api commercial?

No

Hard same. None at all, ever, in anything. And I disable any I can in all the apps I use, and I try to find apps that do not embed any kind of LLM.

Currently, I am giving serious consideration to junking Firefox, or reverting to the ESR version or something. I am heartily sick of mindless "AI" bots everywhere.

Have you checked out Waterfox?

https://www.waterfox.net/

Yep. It's been my default browser since Firefox Quantum came out, so circa 2017.

I did switch back to Firefox (but only on my Macs) since Waterfox was forced to drop XUL support, but I am reconsidering that too now.

I'm implementing a personal AI agent that is fully local inference with external memory that has access to my meetings, notes, Slack and Google Docs. Initially, it replaces Fireflies to capture notes from meetings and Slack.

Mind sharing some details? How is it implemented, models used, how is it triggered?

No.

Personal AI agents are for laymen who do not know how to code. It is overkill for most ppl here

helps a lot in social marketing efforts for me

Pair programming with an agent is so powerful and underrated.