tags:: #todoist-task, [[PROJECTS/MOSAICO]] , [[meeting]] 
date:: [[01-07-2025]] - 09:25
progress:: {{renderer :todomaster}}

	- ### Tasks
		- {{query (and [[TODO]] [[Missione ROMA Mosaico]] )}}
		  query-sort-by:: block
		  query-table:: true
		  query-sort-desc:: false
		  query-properties:: [:block]
	- ### Notes
		- Agenda: ![MOSAICO Consortium meeting Rome_proposed agenda_202506165408279409830273888.pdf](../assets/MOSAICO_Consortium_meeting_Rome_proposed_agenda_202506165408279409830273888_1751381413979_0.pdf)
		- Participants: ![MOSAICO 2nd Consortium meeting_Rome_list of participants_202506238683233499270025632.pdf](../assets/MOSAICO_2nd_Consortium_meeting_Rome_list_of_participants_202506238683233499270025632_1751381740630_0.pdf)
		-
		- **First day of meeting [[01-07-2025]]**
		  query-table:: true
		  query-properties:: [:block]
			- ### Overview
			  collapsed:: true
				- ![image.png](../assets/image_1751354765576_0.png)
			- ### WP1 Presentation
			  collapsed:: true
				- ![image.png](../assets/image_1751355881307_0.png)
				- ![image.png](../assets/image_1751356317096_0.png)
					- Where is the consensus agent?
					- The shown workflow is an initial simplification. The idea is having more complex workflows where consensus agents are part of the workflow.
				- ![image.png](../assets/image_1751356391471_0.png)
				- ![image.png](../assets/image_1751356495836_0.png)
					- This is the API of the server that is executing agents
				- ![image.png](../assets/image_1751357021426_0.png){:height 480, :width 951}
					- TODO Look at Phoenix technology
					- TODO [[p2]] WP2 and WP3 need to decide where to put the telemetry function
				- ![image.png](../assets/image_1751358801620_0.png)
				- ![image.png](../assets/image_1751359025611_0.png)
				- ![image.png](../assets/image_1751359581584_0.png)
				- ![image.png](../assets/image_1751359775463_0.png){:height 561, :width 951}
				- ![image.png](../assets/image_1751359960093_0.png)
				- TODO Vedere LangFuse for observability.
					- ![image.png](../assets/image_1751360262806_0.png)
						- You can see different calls / tools used
					- Compare to Phoenix, the license is more friendly and you can use this completely locally.
					- Opentelemetry is a communication protocol and LangFuse supports this protocol.
				- ![image.png](../assets/image_1751360448322_0.png)
				- ![image.png](../assets/image_1751360766405_0.png)
					- TODO [[p1]] Da guardare A2A agent card per la tassonomia relativa al repository
				- ![image.png](../assets/image_1751361032317_0.png)
				- ![image.png](../assets/image_1751361131943_0.png)
				- ![image.png](../assets/image_1751361170015_0.png)
					- TODO [[p2]] The agent discovery mechanism is very much related to that of MOSAICO. Have a look at them especially to see what is the taxonomy underpinning them
				- ![image.png](../assets/image_1751361461752_0.png)
				- ![image.png](../assets/image_1751361630543_0.png)
				- ![image.png](../assets/image_1751361681318_0.png)
					- TODO This is an idea related to the WP2 taxonomy
				- ![image.png](../assets/image_1751361765405_0.png)
			- ### WP2 Presentation
				- ![image.png](../assets/image_1751363781466_0.png)
					- TODO Developer Interface is not the right naming. THis needs to be changed
				- ![image.png](../assets/image_1751364615575_0.png)
					- TODO LiteLLM can be seen as a possible alternative for the telemetry
				- ![image.png](../assets/image_1751364754080_0.png)
					- TODO How do they implement guard rails?
						- This is for security but also **reliability**
					- TODO How scalable are they in terms of agents?
					- TODO Do they support agents in different technologies?
					- TODO What about parallel executions?
					- TODO Improve the relation vs existing model repositories
					- TODO [[p1]] Have a look at the different repositories shared by Antonio
						- https://beeai.dev/agents
						- https://www.agentlocker.ai/
						- https://aiagentslist.com/
						- [Taxonomy of AI Agent Skills - Agntcy](https://docs.agntcy.org/oasf/taxonomy/)
					- TODO Look at Traces and Metrics (OpenTelemetry with Spring)
						- Our application should be ready to gather telemetry
							- It is related to LangFuse
							- Traces to LangFuse
							- Metrics go to Graphana
							- OpenTelemetry does both
						- We talk metrics but we should also talk about the evaluator
					- TODO Check alternative technologies than MongoDB
						- https://docs.spring.io/spring-ai/reference/api/vectordbs.html#_vectorstore_implementations
					- TODO [[p2]] Link the taxonomy with the SEBOK
					- TODO Investigate also the support of "contracts".
						- We are talking about different and disgributed systems, we should have some contracts capabilities among them
						- How do you agree on them?
						- This also involves the concepts of monitoring. What about if agents to not respect the contracts.
					- TODO [[p1]] Make available to all partners the initial version of the repository metamdoel [[PROJECTS/MOSAICO/WP2]]
			- ### WP3 Presentation
			  collapsed:: true
				- ![image.png](../assets/image_1751373339095_0.png)
				- ![image.png](../assets/image_1751373489739_0.png)
					- Tipically used for developing agents in a rule-based manner
					- How people thinks!
				- ![image.png](../assets/image_1751373575932_0.png)
				- ![image.png](../assets/image_1751373666549_0.png)
					- How to make BDI more pervasive in MOSAICO
						- (last point and see next slide)
					- WE can select an agent with respect to "desires" typically writte in natural language
						- Believes for selecting agents
						- Agent will expose intentions while it's adoption (e.g. in vscode you can accept or not what agent is going to do)
					- WP3 is kind of requiremnt for WP1 !?
				- ![image.png](../assets/image_1751373946026_0.png)
				- ![image.png](../assets/image_1751374070429_0.png)
				- ![image.png](../assets/image_1751374209613_0.png)
				- ![image.png](../assets/image_1751374443438_0.png)
				- ![image.png](../assets/image_1751374491508_0.png)
					- This scenario comes from the interaction with Collins
				-
			- ### WP4 Presentation
			  collapsed:: true
				- ![image.png](../assets/image_1751380184004_0.png)
				- ![image.png](../assets/image_1751380295091_0.png)
					- ... different profiles (from WP2)
				- ![image.png](../assets/image_1751380541463_0.png)
				- ![image.png](../assets/image_1751380591305_0.png)
				- ![image.png](../assets/image_1751381052161_0.png)
				- ![image.png](../assets/image_1751381117177_0.png){:height 532, :width 921}
				- ![image.png](../assets/image_1751381195013_0.png)
				- ![image.png](../assets/image_1751381211852_0.png)
				- ![image.png](../assets/image_1751381248184_0.png)
				-
				- ![image.png](../assets/image_1751381592398_0.png)
					- Attributes of the Agent class are related to the repository. For instance, the confidence of each agent should be available from the repo.
					- The list of attributes of the Agent class should be refined by considering also who is going to value/compute them.
				- ![image.png](../assets/image_1751382098076_0.png)
				- ![image.png](../assets/image_1751382272258_0.png)
				- ![image.png](../assets/image_1751382349242_0.png)
		- **Second day of the meeting [[02-07-2025]]**
		  collapsed:: true
			- ### WP10 Presentation
			  collapsed:: true
				- [Florence Bonnet | CEPR](https://cepr.org/about/people/florence-bonnet)
				- ![image.png](../assets/image_1751440517352_0.png)
				- ![image.png](../assets/image_1751440535841_0.png)
				- ![image.png](../assets/image_1751440629503_0.png)
				- ![image.png](../assets/image_1751440694430_0.png)
					- IMM can be classified as controller under the terminology of GDPR. This needs to be clarified.
				- ![image.png](../assets/image_1751440798166_0.png)
					- Also in this case there are potential issues violating GDPR
						- Are we profiling users?
				- ![image.png](../assets/image_1751440931236_0.png)
					- In this case there might be some AI Act concerns.
				- ![image.png](../assets/image_1751441078039_0.png)
				- ![image.png](../assets/image_1751441112844_0.png)
					- More detailed technical assessment at use case level
					- The system is considered as high risk! not only for its functionalities but also for the use cases
				- ![image.png](../assets/image_1751441225496_0.png)
					- GPAI - General Purpose AI systems
				- ![image.png](../assets/image_1751441352198_0.png)
				- ![image.png](../assets/image_1751442011801_0.png)
				- ![image.png](../assets/image_1751442158052_0.png)
				- ![image.png](../assets/image_1751442353687_0.png){:height 572, :width 980}
				- ![image.png](../assets/image_1751442656482_0.png)
				- ![image.png](../assets/image_1751442712933_0.png)
				- ![image.png](../assets/image_1751442865593_0.png)
				- ![image.png](../assets/image_1751443063827_0.png)
				- ![image.png](../assets/image_1751443159003_0.png)
				- ![image.png](../assets/image_1751443304718_0.png)
				- ![image.png](../assets/image_1751443910337_0.png)
				- ![image.png](../assets/image_1751444025592_0.png)
					- This table is meant for the controller.
				- ![image.png](../assets/image_1751444237541_0.png)
					- This would be only for use case providers that will implement their solution. This needs to be done only if we will play the role of "Controller".
					- She mentioned also *Global DPIA*
					- Risk assessment
					- Risky use of data
			- ### WP6 Presentation
			  collapsed:: true
				- ![image.png](../assets/image_1751446623202_0.png)
				- ![image.png](../assets/image_1751446649205_0.png)
				- ![image.png](../assets/image_1751446666984_0.png)
				- ![image.png](../assets/image_1751446747609_0.png)
				- ![image.png](../assets/image_1751446857632_0.png)
				- ![image.png](../assets/image_1751446886734_0.png)
				- ![image.png](../assets/image_1751446922978_0.png)
					- This is related to Task 6.1
				- ![image.png](../assets/image_1751447087276_0.png)
					- Not yet contents on YouTube (real project video will be released later)
					- We removed X from our socialmedia. We should decide what to do. It makes sense to increase the Linkedin KPI
					- So far no visits to schools or alike
				- ![image.png](../assets/image_1751448051487_0.png){:height 582, :width 980}
					- TODO [[p1]] Aggiungere presentazione MOSAICO a FSE
				- ![image.png](../assets/image_1751448218239_0.png)
				- ![image.png](../assets/image_1751448299956_0.png)
				- Concerning T6.1 and T6.3 (from Eclipse)
					- ![image.png](../assets/image_1751448528799_0.png){:height 512, :width 921}
						- We are at the preparation phase
					- ![image.png](../assets/image_1751448583649_0.png)
					- ![image.png](../assets/image_1751448655067_0.png)
					- ![image.png](../assets/image_1751448767246_0.png)
						- TODO In september we will a first internal development workshop. Who is going there?
					- ![image.png](../assets/image_1751448826727_0.png)
						- We expect to have a panel on AI and someone from MOSAICO is expected to go there!
				- Concerning Task 6.4 (Netcompany)
					- ![image.png](../assets/image_1751449067733_0.png)
					- ![image.png](../assets/image_1751449156638_0.png)
						- The survey aims at collecting how partners intent to exploit the results
					- ![image.png](../assets/image_1751449275847_0.png)
						- four pillars
					- ![image.png](../assets/image_1751449384604_0.png)
					- ![image.png](../assets/image_1751449480186_0.png)
					- ![image.png](../assets/image_1751449684511_0.png)
					- ![image.png](../assets/image_1751449777003_0.png){:height 549, :width 980}
					- ![image.png](../assets/image_1751449797700_0.png)
						- The "contributing partners" column should be "Exploitation partners"
					- ![image.png](../assets/image_1751449876406_0.png)
					- ![image.png](../assets/image_1751450233550_0.png)
					- ![image.png](../assets/image_1751450295902_0.png)
					- TODO We have now a latex template for deliverables. It's in our Sharepoint. DOwnload it!
					-
			- ### WP5 Presentation
			  collapsed:: true
				- ![image.png](../assets/image_1751450650894_0.png)
				- ![image.png](../assets/image_1751450694260_0.png)
				- ![image.png](../assets/image_1751450748883_0.png)
				- ![image.png](../assets/image_1751450812824_0.png)
				- ![image.png](../assets/image_1751451105724_0.png)
				- ![image.png](../assets/image_1751451377728_0.png)
				- ![image.png](../assets/image_1751451402873_0.png)
				- ![image.png](../assets/image_1751452019844_0.png)
				- ![image.png](../assets/image_1751453516554_0.png)
				-
			- ### WP8 and WP9
			  collapsed:: true
				- Talked about deliverable 8.2
				- ![image.png](../assets/image_1751461226292_0.png)
				- ![image.png](../assets/image_1751461269563_0.png)
			- ### Discussion
				- TODO [[p2]] Look at [MOSAICO Architecture - Google Drawings](https://docs.google.com/drawings/d/1zyO2GLFj8PtQD9j6MZ1AksQwwLM_XmZX8AOPGNs8m_Y/edit)
		- **Third day of the meeting [[03-07-2025]]**
		  collapsed:: true
			- Agenda: [MOSAICO 2nd Co-Creation meeting Rome_proposed agenda_20250619.docx](https://imtatlantiquefr.sharepoint.com/:w:/r/sites/MOSAICO/_layouts/15/Doc.aspx?sourcedoc=%7BBC69EB4B-582A-4E6B-A86A-13D04EF8FA93%7D&file=MOSAICO%202nd%20Co-Creation%20meeting%20Rome_proposed%20agenda_20250619.docx&action=default&mobileredirect=true)
			- Link: https://gov.teams.microsoft.us/l/meetup-join/19%3agcch%3ameeting_cb5648e689bb4db19ab298cdfad07f3f%40thread.v2/0?context=%7b%22Tid%22%3a%227a18110d-ef9b-4274-acef-e62ab0fe28ed%22%2c%22Oid%22%3a%2272d155af-f561-43e3-88f0-0ae9416888e8%22%7d
			- ### Critical and important aspects
			  collapsed:: true
				- {{query (and (or [[critical]] [[IMPORTANT]]) [[Missione ROMA Mosaico]])}}
				  query-table:: true
				  query-properties:: [:block]
				- Minimal Viable Product (MVP)
				- Possible baselines #IMPORTANT
				- **Single General-Purpose Agent**: You just use current co-pilot in agent mode
					- Developer: Nothing to program,
					- User: high automation, bad results
				- **Single inference**: You do everything in a single prompt
					- Developer: Nothing to program,
					- User: high automation, bad results
				- **No-LLM**: You do everything manually or with other tools
					- Developer: Nothing to program
					- User: no automation, good results
				- **Standard agent(s)**: programmed from scratch in an existing framework
					- Developer: Hard to program
					- User: high automation, good results
				- **Manual multi-chatbots**: user asking manually multiple chatbots for each task
					- Developer: Nothing to program
					- User: some automation (time lost, the manual part is transferring knowledge), somehow better results
				- The session is for discussing Deliverable 5.1 <!--StartFragment -->
				  [D5.1_Use_Case_Description_Document_MOSAICO.docx](https://imtatlantiquefr.sharepoint.com/:w:/r/sites/MOSAICO/Shared%20Documents/Work%20Packages/WP5/T5.1/D5.1_Use_Case_Description_Document_MOSAICO.docx?d=w6f5cdadb0be74bc0acab1a2503081cdb&csf=1&web=1&e=m2tDwW)
			- ### NBG Use Case
			  collapsed:: true
				- ![image.png](../assets/image_1751527096102_0.png){:height 516, :width 830}
				- ![image.png](../assets/image_1751527179014_0.png)
				- ![image.png](../assets/image_1751527265483_0.png)
					- #critical How all of this is related to orchestration! Scripts need to be developed by solution agents. WHo develop that?
				- ![image.png](../assets/image_1751527345389_0.png)
					- #IMPORTANT After a long discussion we decided to focus on the code generation phase as presented in this slide. The use case partner will revise the use case by focusing more on the code development and how they plan to employ MOSAICO to improve the process.
					-
				- ![image.png](../assets/image_1751527429297_0.png)
					- It is important to stress that agents will be developed by use case partners!!!!#important This applies to all the use cases / user stories.
				- ![image.png](../assets/image_1751527498570_0.png)
				- ![image.png](../assets/image_1751527521791_0.png){:height 460, :width 830}
					- #critical  I'm not sure about prompt library. We don't have it.
				- ![image.png](../assets/image_1751527597828_0.png)
					-
				- ![image.png](../assets/image_1751527728235_0.png)
				-
			- ### Immersion Use Case
			  collapsed:: true
				- ![image.png](../assets/image_1751533506935_0.png)
				  collapsed:: true
					- ![image.png](../assets/image_1751533671212_0.png)
				- ![image.png](../assets/image_1751533825031_0.png)
					- #critical In Mosaico we plan to essentially have VSCode based interaction. For this use case, it is not clear what's the kind of interaction that the use case partner will have with the system. It seems a VSCode based interaction is not relaant for this.
				- ![image.png](../assets/image_1751534792669_0.png)
				- ![image.png](../assets/image_1751534817808_0.png)
				- ![image.png](../assets/image_1751534876828_0.png)
				- <!--StartFragment -->
				  [CM2 - Co-creation - Immersion Case Study Notes.docx](https://imtatlantiquefr.sharepoint.com/:w:/r/sites/MOSAICO/Shared%20Documents/Consortium%20meetings/CM2%20-%20Rome/Presentations/Day%203%20presentations%20(Co-creation%20Workshop)/CM2%20-%20Co-creation%20-%20Immersion%20Case%20Study%20Notes.docx?d=w684558a57b9f44de9f6cce4a84e2ba3e&csf=1&web=1&e=F86OZe) [[IMPORTANT]]
			- ### Unparallel Use Case
			  collapsed:: true
				- The library upgrade use case seems to be connected to HybridMig and to the last keynote at EASE 2025 [Keynotes - EASE 2025](https://conf.researchr.org/info/ease-2025/program#title-beyond-code-completion-harnessing-llms-for-complex-code-migrations-in-an-enterprise-setting-at-google)
				-
			- ### Collins Use Case
				-
		-