SF Bay ACM Chapter

Mon, Nov 10 · 5:30 PM PST

Accelerating Startups to Put Enterprise GenAI Multi-Agent Systems in Production

Valley Research Park , 319 North Bernardo Avenue, Mountain View, CA, US

EVENT LOGISTICS:
The event is hybrid. The audience can attend in Mountain View, CA or join on Zoom or YouTube

Valley Research Park (VRP)
319 North Bernardo Ave
Mountain View, CA 94043
From the locked front door, go to the right side of the building. The 2nd door will be open.

If you want to join the discussion remotely, you can submit questions via the Zoom “discussions”. The zoom link:
(to be updated closer to the event date)
Join via YouTube:
(to be updated closer to the event date)

Agenda (one hour earlier this time, for audience in other time zones)
5:30 people start to arrive, enjoy pizza and networking. Test your connection and chat.
6:00 SFBayACM introduces upcoming events and the speaker
6:00 speaker presentation starts
7:15 - 7:30 finish, depending on Q&A

TALK DESCRIPTION:
– PROBLEM –
Key Challenges We Will Address for Different Audience Segments
1. Startups with Funding, or Looking for Execution Partners:
You have a strong vertical application and early investment but now you need to grow quickly while focusing on your core value proposition. You may already have a prototype built from initial experimentation but face the challenge of evolving it into a secure, multi-tenant, enterprise grade GenAI platform that is compliant, transparent, explainable, and aligned with human values.

2. Mid Cap and Large Enterprises:
Your teams have built GenAI prototypes yet struggle to solve real problems or get applications into production consistently. You want to identify and overcome the technical, operational, and organizational barriers that keep innovation from scaling.

3. Investors, VC’s and Venture Partners:
You are assessing how to reduce costs and risks in your portfolio companies’ GenAI strategies. Understanding why 95 percent of projects fail, as reported in MIT’s State of AI in Business 2025, can help you guide founders toward sustainable and successful models.

4. Product and Engineering Leaders:
You have ideas, and aim to design applications that surprise and delight customers by building intelligence that anticipates user intent, with a Do What I Mean (DWIM) design principle that separates great products from the rest.

5. Regulated Industry Executives:
In sectors such as financial services, healthcare, or government, you must ensure AI systems are reliable, explainable, auditable, and fully compliant with evolving laws and governance standards while maintaining speed and innovation. You may also want to monitor your systems, to comply with various company or security policies.

Who Should Attend:
Startup founders, investors, product leaders, and enterprise innovators who want to understand what it really takes to design, build and scale GenAI systems that work in the real world.

– SOLUTION –-
This talk will answer problems listed above and more. The speaker will first dive into the MIT report, to better interpret the context of the survey. Lessons learned on how to help GenAI deployments succeed will be discussed.

Studies that review knowledge worker productivity gains will be reviewed.

The speaker will discuss an architecture for a flexible software accelerator framework that can meet the needs for successful GenAI deployments. The framework can be configured to support different applications to meet specific requirements, combining best-practice software components and design principles.

Given an accelerator software architecture with these layers:
Ccube’s Lumin Lab Accelerator software

• IntelliConnect (to connect you to the intelligence of the text and data in your company) This lets users ask questions of your corporate knowledge, for example.
• Guardiance (To provide text classifications to guard your company, support compliance and AI alignment)

Tools and software:

• Microservices architecture
• MCP integrations
• Many file types and data sources (i.e. local, Google drive, Gmail, MongoDB)
• Enterprise applications (i.e. SalesForce, Service Now)
• GenAI personalization
• workflow support (n8n, UiPath)

GenAI Tools:

• Retrieval Augmented Generation (RAG) with Vector Databases, such as Weaviate or Pinecone
• Use Guardrails.ai as a foundation for text classification. We built on top conditions, +/- examples per condition, Boolean combination of conditions into rules. Support many rule actions and rule testing. Support observability of GenAI behavior, to be in alignment with your company values and brand.
• Multi-Agent with: LangGraph, LangSmith
• Make explicit the dialogue or work product (medium-term memory) that is passed between many agents and users. This work product is persisted over the employees development of a given task.
• Logging channels: system level (tokens, LLM calls, costs, latency), user-agent level chat, agent & LLM thought traces. Scheming detection rules can monitor the thought traces.
• Meaning Markers (auto tagging text with a hierarchy of tags using Named Entity Recognition (NER)
• Design of Experiments (DoE) to optimize cost and accuracy by varying: prompts, tools, LLMs, embedding models and other architecture choices as they vary over different client requirements and data.

With the above accelerator software components, support a variety of vertical applications, based on the data loaded and configurations.

– RESULT –
The speaker will show a series of demos relating to financial services and healthcare, as examples of what can be done with such a framework.

• Customer Support application covering portable computers and cell phones, using both internal trouble ticked data in SalesForce or ServiceNow, product manuals in PDF or web form and brand related support web sites.
• A medical related demo, applying about ⅓ of the 150 or so rules needed to cover all of the HIPAA laws around confidential medical information.
• A finance demo around investment advisors, insider trading or information leaking
• The design of an upcoming larger demo, supporting questions over 3 years of S&P500 company data (annual reports, proxy reports, websites).

SPEAKER BIO:
Greg Makowski, https://www.linkedin.com/in/GregMakowski has been training and deploying AI since 1992, has been growing Data Science Teams since 2010, has exited 4 startups and has 6 AI patents granted or in various stages. He is currently the Chief of Data Science at Ccube, leading GenAI/AI consulting and framework development for enterprise applications. See also: https://www.ccube.com/genai.

SPONSOR INFORMATION:
From vision to execution, Ccube partners with forward-thinking clients to co-build Apps, Data, and GenAI solutions across industries. Ccube has 10+ service lines, 30+ happy clients, 90% client retention, and saved clients ~50% costs on average.

Ccube has Silicon Valley roots, deep expertise, customer first approach and leverages lean teams for onsite in US and offshore delivery teams in India.

Watch for us also on
https://www.ccube.com/
https://www.linkedin.com/company/ccube-inc/
https://aws.amazon.com/marketplace

As a way to "thank your sponsor", Ccube invites you to share your contact info, and take a brief survey. A summary of the survey results will be shared at the event.

#ACM
#SFbayACM

#GenAI
#GenAIApplications
#EnterpriseApplications
#EnterpriseAIApplications
#EnterpriseGenAIApplications
#RAG
#RetrievalAugmentedGeneration
#Guardrails
#Obervability
#AIsafety
#GenAIcompliance

#Ccube
#LuminAILabs
#IntelliConnect
#Guardiance

Sat, Nov 15 · 8:30 AM PST

Towards Agentic Intelligence: Architectures for Multi-Agent AI Systems

Valley Research Park , 319 North Bernardo Avenue, Mountain View, CA, US

## Event Logistics

2 DAY EVENT! Saturday 11/15 AND Sunday 11/16 (details below)

REGISTER ON EVENTBRITE FOR ADMISSION
(you can join this Meetup event if you want to let others know you signed up, or add comments/questions to the event at the bottom.

Students Register for the class at this Eventbrite Link. Pricing, with discounts that stack

• 10% discount when signing up for both days with one purchase
• 20% early bird discount (goes away ~2 weeks before the event)
• 33% student discount for a full time student. Proof of enrollment is needed to hold your class spot. Send proof to "pds-multiagent at sfbayacm net" and get a discount code to use when registering. Use the email subject "multi-agent PDS: student discount".
• Free - apply to be a TA and you don't have to pay for the lab day. We will have one TA position for every 20 paid students. Send your background in Python and GenAI related experience to "pds-multiagent at sfbayacm net." Use the email subject "multi-agent PDS: TA application".
• All pricing includes a $20 annual membership to the SFbayACM

We accept optional donations to our non-profit organization, which is tax deductible. SFbayACM’s Non-Profit Taxpayer ID: 31-0963922
In past years, we have given $3,500 to support STEM education, judging 1,000+ science fair projects at the Synopsis Science Fair, https://science-fair.org/

Day 1, Labs (details below)

• Saturday, Nov 15 8:30am to 5pm
• Sign up for a limited number of seats in person at
• Valley Research Park, 319 North Bernardo Ave, Mountain View, CA.
• Go to the right side of the building, 2nd door
• Coffee breaks and lunch is included in the price
• Zoom for a remote audience
• Both the local and remote audience will be supported by TA’s. The moderator will watch the Zoom chat for questions for the speaker, and ask them.
• Remote tickets have a built in discount, because food is not provided

Day 2, Lectures (outlined below)

• Sunday, Nov 16, 9am to 5pm, in Mountain View or on Zoom
• Zoom for a remote audience
• The remote audience will be supported by questions that can be directed to the speaker by the moderator
• Remote tickets have a built in discount, because food is not provided

## Overview

Building on the tremendous response to Dhanashree Lele’s ACM talk on Multi-Agent Architectures for Enterprise AI, this 2-day, research-caliber, hands-on workshop is designed to advance the state of practice in Agentic AI system design, evaluation, and optimization.
This workshop will guide participants through theory-to-deployment workflows for constructing next-generation multi-agent frameworks, benchmarking agentic behaviors, and applying compute-efficient orchestration strategies. The curriculum draws heavily from recent breakthroughs presented at NeurIPS, ICLR, and KDD, grounding hands-on engineering in rigorous scientific principles and reproducible experimentation.
By bridging academic research and production-grade engineering, this workshop is ideal for applied researchers, industry practitioners, graduate students, and technical leaders seeking to design reliable, interpretable, and high-performance LLM-based agentic systems.

## Learning Format and Structure

This intensive two-day workshop follows a progressive “build-as-you-learn” methodology. Each module introduces core research concepts followed by guided implementation in Jupyter/Google Colab, enabling participants to translate theory directly into working systems.

### 📅 Day 1 — Architecting Multi-Agent Systems

• 4 hands-on labs focused on:
• Building multi-agentic systems/use-cases from first principles
• Exploring agent tools, MCP operability, and orchestration strategies
• Converting agentic prototypes into robust, production-ready cognitive pipelines
• Implementing coordination, planning, and tool-use protocols across agents

### 📅 Day 2 — Deep Dive: Research Frontiers and Reproduction

• Analytical walkthroughs of seminal and frontier papers in Agentic AI from NeurIPS, ICLR, and KDD
• Structured methodology for paper-to-prototype translation: reproducing cutting-edge research through practical labs
• Discussions on evaluation benchmarks, alignment frameworks, and emergent behavior analysis
• Roadmapping techniques for embedding research-grade systems into real-world enterprise use cases

## Key Outcomes

**Theoretical Foundations:**Understand the mathematical and algorithmic underpinnings of multi-agent LLM architectures, orchestration, and alignment.
**Hands-On Mastery:**Gain practical experience in building agentic systems from scratch, configuring MCP operability, and scaling prototypes into production-grade deployments.
**Evaluation & Governance:**Learn to design and apply alignment and evaluation frameworks to ensure robustness, interpretability, and responsible deployment of multi-agent systems.
**Practical Assets:**Walk away with fully functional notebooks, baseline reference architectures, curated reading lists, and reproducible workflows to accelerate implementation in your own organization.

## Prerequisites

• Intermediate to advanced Python programming
• Familiarity with APIs and Jupyter/Colab environments
• Experience with or interest in LLMs (OpenAI API will be used; open-source alternatives such as Claude, Mistral, and Llama 3 will also be discussed)

## Who Should Attend

• AI/ML Engineers, Data Scientists & AI Practitioners designing or deploying LLM applications
• Applied Researchers & Postdocs exploring Agentic AI, neuro-symbolic systems, or autonomous orchestration
• Technical Leaders & Architects integrating multi-agent reasoning in production environments, CTO

## Speaker Bio

Dhanashree is a Senior Machine Learning Engineer and AI Researcher with over a decade of experience designing and deploying advanced AI systems at scale. Her expertise spans architecting multi-agent solutions that integrate Large Language Models (LLMs), computer vision pipelines, and structured data to solve complex enterprise challenges across industries including retail, healthcare, and finance.
At Albertsons, Deloitte, and Fractal, Dhanashree has led the development of production-grade AI applications, focusing on optimization, model observability, and responsible AI practices. Her work includes designing scalable inference architectures for LLMs on modern GPU infrastructures, building hybrid pipelines that fuse vision and language models, and engineering systems that balance performance with ethical and regulatory considerations.
She actively collaborates with research institutions like the University of Illinois. Dhanashree actively engages with the research community and frequently speaks on bridging advanced AI research and production systems.
https://www.linkedin.com/in/dhanashreelele/

Dhanashree gave a prior ACM Talk - “Deploying & Scaling LLM in the Enterprise: Architecting Multi-agent AI Systems”

• Meetup Talk Description, Monday, Sept 22, 2025
• Video recording (2h 3m with many questions)

SPONSOR INFORMATION:
From vision to execution, Ccube partners with forward-thinking clients to co-build Apps, Data, and GenAI solutions across industries. Ccube has 10+ service lines, 30+ happy clients, 90% client retention, and saved clients ~50% costs on average.
Ccube has Silicon Valley roots, deep expertise, customer first approach and leverages lean teams for onsite in US and offshore delivery teams in India.
Watch for us also on
https://www.ccube.com/
https://www.linkedin.com/company/ccube-inc/
https://aws.amazon.com/marketplace

As a way to "thank your sponsor", Ccube invites you to share your contact info, and take a brief survey. A summary of the survey results will be shared at the event.

Wed, Nov 19 · 7:00 PM PST

Designing for Scale, Reliability, and Resiliency: Real-World Lessons

Valley Research Park , 319 North Bernardo Avenue, Mountain View, CA, US

Designing for Scale, Reliability, and Resiliency: Real-World Lessons from Building High-Throughput Systems

LOCATION ADDRESS (Hybrid, in person or by zoom, you choose)
Valley Research Park
319 North Bernardo Avenue
Mountain View, CA CA 93043
Don't use the front door. When facing the front door, turn right along the front of the building. Turn left around the building corner. The 2nd door should be open and have a banner and event registration.

If you want to join remotely, you can submit questions via Zoom Q&A. The zoom link:
https://acm-org.zoom.us/j/94270873151?pwd=DFGIb9xhn5GPv8iJD9Bxt1Ya2qJHmN.1
Join via YouTube:
https://youtube.com/live/

AGENDA
6:30 Door opens, food and networking (we invite honor system contributions)
7:00 SFBayACM upcoming events, introduce the speaker
7:15 speaker presentation starts
8:15 - 8:30 finish, depending on Q&A

Join SF Bay ACM Chapter for an insightful discussion on:

Talk Description:
As modern software systems grow in complexity and scale, the demand for architectures that are not just fast—but also reliable, resilient, observable, and auditable—has never been greater. In this talk, we'll dive into practical strategies and real-world patterns for designing and operating large-scale distributed systems.
Topics include:

• Traffic segmentation and routing strategies across multi-cluster environments
• Patterns for achieving high availability and failover across global infrastructure
• Monitoring and observability at scale: what to measure, how to alert
• Auditing for compliance, trust, and debugging
• Common failure modes and how to build for graceful degradation
• Real examples from mission-critical production systems

Attendees will walk away with architectural insights, tools, and mental models to apply to their own systems, whether working in startups or enterprises.

***

Speaker Bio:
I’m a Senior Software Engineer at DoorDash and previously led platform initiatives at Conviva, where I built scalable, fault-tolerant systems handling tens of millions of sessions daily for customers like Disney, HBO, and Sky. My work has spanned everything from routing frameworks and disaster recovery to monitoring pipelines and SLA enforcement. I’m passionate about making infrastructure reliable and maintainable, and I enjoy sharing lessons learned from real-world systems.
https://www.linkedin.com/in/karanluniya

---

Valley Research Park is a coworking research campus of 104,000 square feet hosting 60+ life science and technology companies. VRP has over 100 dry labs, wet labs, and high power labs sized from 125-15,000 square feet. VRP manages all of the traditional office elements: break rooms, conference rooms, outdoor dining spaces, and recreational spaces.

As a plug-and-play lab space, once companies have secured their next milestone and are ready to expand, VRP has 100+ labs ready to expand into.
https://www.valleyresearchpark.com/