On Apr. 19th, 2025, we had the fifth meeting of scicloj-ai-meetups, a new Clojure dev group focusing on AI, continuing the earlier scicloj-llm-meetups group.
11 people attended the meeting.
Brief summary
-
@pragyansden - Reliable Extraction of Structured Data from LLM Responses
This was an extended and updated discussion following also Pragyan’s recent blog post, Taming LLM Responses with Instaparse. -
@vedang - Writing MCP servers in Clojure, for fun and profit
This was a discussion of MCP, the new mcp-clojure-sdk, and related practices. -
@siavash_mohammady - Agentic-Driven Data-science
The talk discussed a detailed method that composes an LLM, a couple of DSLs, clara-rules, a database, and Tablecloth in one automated data-science workflow… -
After a short discussion, @vedang shared the screen again, and we had a dive into the code.
-
In the unrecorded part, we discussed, among other things, possibly projects we can study/research at this group, in the sessions and in between the sessions. A few ideas were proposed in a discussion with @Michael_Cole, @siavash_mohammady, and others. Here are a couple of concrete ideas for upcoming meetings:
- Basic NLP with packages like SpaCy – how to make it convenient from Clojure
- Neuro-symbolic combinations, e.g., a concrete practice of the ideas from the talk of @siavash_mohammady.
Public recording
The talks by @pragyansden and @siavash_mohammady are shared publicly here. The full recording is shared in the group chat as an unlisted video.
Chat
See #scicloj-ai-meetups > meeting 5 at the Clojurians Zulip Chat for the full recording and a followup discussion.
Links shared in the meeting
The Scicloj-AI-meetups group
The scicloj-ai-meetups group is a new developer community focused on AI models, their underlying principles, and practical applications.
The group is organized by @stoica94 and @daslu, emerging from community discussions about the need for more open collaboration and experimentation in AI. It builds upon our previous initiatives like the scicloj-llm-meetups, but with an expanded scope that explores diverse types of AI models beyond just LLMs.
While some content will be specific to the Clojure ecosystem, much of the material will be valuable and relevant to the broader AI and programming communities.
Next events
Follow our events on the Clojure Events Calendar Feed.