monday.com AI engineering

The Agentic SDLC: From Specs to Autonomous Merge

Mon, Jul 20 · 6:00 PM IDT

monday.com, Yitzhak Sade 6, Tel Aviv, IL

Join us for an evening exploring how engineering teams are moving beyond AI-assisted coding to autonomous workflows, from turning specs into production-ready code to building AI agents trusted to review and merge pull requests.

Agenda:

18:00 Gathering, mingling, food & drinks

18:30 Humans where they matter, AI where it’s better: Agentic SDLC at monday.com - Neyema Awaskar, monday.com

19:00 No Human Needed: building a merge agent developers trust - Omri Levy & Omer Militscher, Baz

Talk Abstracts:

Talk 1:
Humans where they matter, AI where it’s better: Agentic SDLC at monday.com
Neyema Awaskar, monday.com

A year ago, engineers wrote code, opened PRs, waited for review, and merged.
Tomorrow, they write a spec—and the rest happens automatically.
When generative AI hit the scene, monday.com engineers started shipping faster than ever, but we quickly hit a wall: writing code became easy, yet review queues kept growing. The bottleneck had shifted from writing code to everything that came after.
We realized that automating code generation was just bandaging a symptom. The cure required a complete paradigm shift: moving engineers from Builders to Directors.

In this talk, we’ll share what worked, what failed, how we built trust and how we measure impact. Finally, we’ll give you a practical starting point that you can implement tomorrow to take your first step toward full autonomy.

Talk 2: No Human Needed: building a merge agent developers trust
Omri Levy & Omer Militscher, Baz

Auto-merge sounds great until you ask the real question: would you actually trust an agent to merge your PR without looking? That's a question about trust - and trust is hard to earn.

At Baz we've spent the last few years building agents across the dev cycle: deep code review that map-reduces subagents over a diff, a spec reviewer comparing your tickets and Figma designs to the actual UI, and most recently a merge agent that decides whether a PR is ready to merge, no human needed.
In this talk we'll go under the hood of the patterns behind building agents that actually work - and specifically the merge agent: how it's triggered, how it reaches a verdict, how we test and benchmark it, and what's still left to figure out.

Speaker Bios:

Omri Levy is a squad manager and part of the founding team at Baz, building AI agents for the SDLC - from code review to production monitoring. Before Baz, he was at IBM Research, working on hyper-parameter optimization for RAG pipelines on the IBM watsonx platform.

Omer Militscher is a product manager at Baz, where he builds AI agents for the SDLC - from code review to production monitoring.
Before Baz, he was a Data Scientist at Salesforce, developing a data focused conversational agent, for Tableau Next Concierge team.

AI-Ready Platforms: Building the Foundations for Scale

Mon, Jul 27 · 6:00 PM IDT

monday.com, Yitzhak Sade 6, Tel Aviv, IL

As AI reshapes software engineering, the platform behind it becomes more important than ever. Join us for an Infra & Platform meetup focused on the systems, platforms, and AI capabilities that help engineering teams build and operate at scale

Agenda:

18:00 Gathering, mingling & refreshments

18:30 From AI Adoption to Operational Impact - Amit Mazor, DevOps & Pablo Martinez, Senior SRE @ monday.com

19:00 Your tickets are half empty - Shahar Polak, Head of R&D @ Imagen

19:30 Break

19:45 Separating Platform from Business Logic - Sofi Vasserman, Senior Tech Lead & Ziv Amram, Software Engineering Team Lead @ monday.com

Talk Abstracts:

• From AI Adoption to Operational Impact - Amit Mazor, DevOps & Pablo Martinez, Senior SRE @ monday.com

A look into monday.com’s AI transformation journey, from organizational enablement and Discover how we transitioned from organizational adoption to real-world devops applications. We will begin with a brief introduction to monday.com's agentic functions before diving into how these agents operate in production environments to resolve technical challenges.

• Your tickets are half empty - Shahar Polak, Head of R&D, Imagen

Jira says there is a bug. Production says there is a problem, but the useful context is scattered across logs, traces, Slack, repositories, dashboards, deployments, and customer data.
That gap is where engineering time disappears. At Imagen AI, we were spending up to four hours on bug triage before the actual fix could even begin. So we built LADIS - an internal AI agent that reads the operational context, enriches tickets automatically, and helps engineers start from signal instead of noise.
We cut triage from roughly four hours to four minutes in many cases.
This talk shares the architecture behind it: isolated skills, strict permissions, observability integrations, automatic ticket enrichment, and the failure modes we hit when our first super-agent tried to know everything.
The lesson is simple: don’t make engineers hunt for context. Bring the context to the incident.

• Separating Platform from Business Logic - Sofi Vasserman, & Ziv Amram @ monday.com

When AI can generate a new service in minutes, how do you ensure every service follows your engineering standards? We'll explore how platform engineering can enforce reliability, security, and communication patterns by design, allowing developers and agents to focus on business logic instead of infrastructure concerns. We'll share how we moved non-functional requirements like retries, circuit breakers, caching, and resiliency into the platform itself, along with the architectural principles, trade-offs, and practical lessons that any team can apply to build AI-ready platforms that scale without sacrificing reliability.