How do I give my LLM workflow persistent context across independent client connections?

·5 views

You build a support workflow in two steps. At 06:00 a scheduled job connects to your MCP server, reads the night's tickets and works out that 4127 and 4133 are the same bug. At 10:00 you open a chat client and ask the agent which tickets can be closed. That is a new client connection, perhaps to a different server instance, and the agent starts from nothing. What the first step worked out lived with the first connection, and that connection closed four hours ago.

Read the full story at DEV Community

This is an AI-generated summary. ShortSingh links to the original source for the complete article.

Discussion (0)

20+ Years of Friendship. One Weekend to Build His Marketing Department.

This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend Built for Nathan: best friend of 20+ years, musician behind Flies Like Robots, not a marketing guy. Self-hosted Gemma 4 watches and listens to his video, then drafts the YouTube metadata and Bandcamp copy in his voice, and picks a hook for a vertical Short. He edits or approves. Soundboard remembers the edit, uploads as private, and reads it back from YouTube before calling it verified. Code • 60 s demo • Deployed site What I Built Nathan makes the music and the videos.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

The time I screwed up a conference talk (And the talk on Pydantic I would have given)

Hi there -- I know it's been a while. A lot of things have changed and a lot of things have remained the same. I felt inspired to write today for a couple of reasons: I want to talk about screwing up because I screwed up yesterday and rather than let the shame beat me up, I want to transform these feelings into humility and maybe a lesson you can learn from or relate to I want to find a way to share my talk because it's a good talk and I am proud of it and you might find some of it useful PyBay is one of my favorite conferences. I've spoken at PyBay three times, and each time, I've grown close

0 comments Read more at DEV Community

ProgrammingDEV Community ·

Why vul.cve Returns Zero for CVE-2026-96365: Reading Exposure Data Honestly

Why vul.cve Returns Zero for CVE-2026-96365: Reading Exposure Data Honestly Vulnerability overview CVE-2026-96365 is one of 36 identifiers in CERT-BUND advisory WID-SEC-2026-3554, published 23 September 2026 and rated high risk. The advisory covers 16 contributed Drupal projects, with identifiers running from CVE-2026-96355 to CVE-2026-96398. Interpretation starts with the two ZoomEye results collected for this article. The public record describes remote exploitation in five outcome classes: arbitrary code execution, extended privileges, bypass of security measures, data manipulation or disclo

0 comments Read more at DEV Community

ProgrammingDEV Community ·

QueerCade: Both Sanity Challenge Paths, One Arcade

I built QueerCade — a curated arcade of LGBTQ+ video games — through both paths of the Sanity challenge. One dataset powers all of it. QueerCade (Part 1): Ship an Agent That Queries Real Content Sanity Challenge Path One Submission Mike “Demo” Demopoulos Sep 21 #devchallenge #sanitychallenge #sanity #ai comment The QueerCade Discovery Guide is an AI agent that recommends games, characters, developers, and studios — answering only from the Sanity dataset (3,500+ documents). It never invents a game; if something isn't in the data, it says so. QueerCade (Part 2): Vibe-Code Something Strange — an

0 comments Read more at DEV Community