Skip to content

Update TF2 rolling notes: 13 July agenda #33

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
gperu merged 3 commits into from
Jul 13, 2026
Merged

Update TF2 rolling notes: 13 July agenda #33

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
61f4135
Expand June 22 agenda with review status and actions update
gperu Jun 16, 2026
f7f3cf7
Add July 13 agenda; trim June 22 entry to reflect no-show
gperu Jul 13, 2026
7dd2c4f
Add links to Michael Sparks document in July 13 agenda
gperu Jul 13, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
73 changes: 65 additions & 8 deletions meetings/tf2-rolling-notes.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,51 @@

Repository: <https://github.com/EVERSE-ResearchSoftware/reference-framework>

# TF2 Meeting Agenda — 13 July 2026

**Date:** Monday, 13 July 2026 **Time:** 11:00 UK / 12:00 CET **Location:** <https://us02web.zoom.us/j/83181471617>

**Attending:** Fotis, Carlos (from 11:15)

**Apologies:**

## A. AI position

No agreed EVERSE position on AI. Feeds Fotis's policy brief, due February 2027.

## B. Michael Sparks document

"How do you use AI to develop quality research software" — Spectrum of AI Intensity framework. RSQKit split targeted for today.

Google Doc: <https://docs.google.com/document/d/1FrI7I1yaQORtEi7BmFY34CvMAFcz2hskT4cUdlYpZa4/edit>
Local copy: `~/Desktop/Desktop2026_07_07/task_How_do_you_use_AI_to_develop_quality_research_software.docx`

## C. HSF/ESCAPE collaboration

Caterina Doglioni: HSF/ESCAPE AI-assisted-coding guidelines, lighter-weight than RSQKit, proposed co-organised with EVERSE.

## D. What do we build

No model training. Guidance and skills/prompts. MCPs undecided.

Hugo's prototypes (TeSS metadata agent, RSQKit chatbot) — blocked on compute and authorisation, no change since April.

## E. AI webinar

Joint with ReSA (Michelle Barker), target October/November. Contact not yet made.

## F. RF section reviews

PR #26 (sustainability) and PR #30 (Three-Tiers View) open, unreviewed. #12–#15 unowned. Status only — tracked on GitHub.

## G. AOB

Mattermost → CERN migration. Helmholtz read-only 15 July.

## Key actions

---

# TF2 Meeting Minutes — 22 June 2026

**Date:** Monday, 22 June 2026 **Time:** 11:00 UK / 12:00 CET **Location:** <https://us02web.zoom.us/j/83181471617>
Expand All @@ -10,23 +55,35 @@ Repository: <https://github.com/EVERSE-ResearchSoftware/reference-framework>

**Apologies:**

## Pre-meeting note — 1:1 Giacomo / Hugo Bacard, 16 June 2026
No one joined — meeting rescheduled without checking availability. Rescheduled to 13 July. Agenda below kept for reference; superseded where relevant by the 13 July agenda above.

Pre-meeting note (Hugo, 16 June): TeSS agent and RSQKit chatbot prototypes both still blocked on compute and formal AI authorisation — no change since.

## A. Actions from 18 May — update

Hugo's AI work within EVERSE covers two streams: a RAG-based RSQKit chatbot (prototype exists, repo unmaintained) and a TeSS metadata extractor agent (working prototype with Kenneth Rioja). Both are blocked on compute (EOSC/AI4EOSC insufficient for agentic workflows) and on formal authorisation to use AI within the project.
Done ahead of this meeting:
- GitHub issues assigned to agreed owners: Daniel (#6, #7, #8, #18), Shoaib (#4, #5, #20), Thomas (#10, #11)
- Neil nudged on community dimension references (#18)
- Shoaib nudged on audience statement (#20)
- Thomas nudged on views chapters (#10, #11)
- AI and openness issue published to ai-everse (#1)
- 3 new ai-everse issues filed from 1:1 with Hugo (#2, #3, #4)

Key question raised: is a custom chatbot worthwhile given that general LLMs already handle RSQKit content adequately? The case rests on privacy (self-hosted model, no third-party data exposure) and deeper integration (following links within RSQKit pages). Hugo proposes a modular architecture — static RAG first, web search activatable via config flag later. Three issues filed in ai-everse: #2 (use case), #3 (compute), #4 (authorisation).
Still outstanding: Fotis check on AI scope; Senem issue; Patrick Rein email to Faruk.

## A. Actions from 18 May
## B. Reference Framework review status

## B. Hugo: AI tools update
18 open issues. Owners now assigned across all framework and views chapters. Only active PR: #26 (Thomas's sustainability rewrite — Giacomo reviewing before this meeting). #12–#15 remain unowned (raised on Mattermost). Daniel working on community indicators (#18), waiting on Neil's references.

TeSS agent and RSQKit chatbot/assistant — update and discussion. See pre-meeting note and ai-everse issues [#2](https://github.com/EVERSE-ResearchSoftware/ai-everse/issues/2), [#3](https://github.com/EVERSE-ResearchSoftware/ai-everse/issues/3), [#4](https://github.com/EVERSE-ResearchSoftware/ai-everse/issues/4).
## C. Hugo: AI tools update

## C. Section ownership: #12–#15
Did not happen — see pre-meeting note above.

## D. Section ownership: #12–#15

Lifecycle, personas, science clusters, conclusions — still unowned. Raised on Mattermost; volunteers needed.

## D. AOB
## E. AOB

- RSQKit contentathon — 30 June
- Mattermost archiving in July — move to Matrix
Expand Down
Loading