Haggai Philip Zagury
DevOps Group & Tech Lead @Tikal Knowledge
DevOps Group & Tech Lead @Tikal Knowledge
Tel Aviv, Israel
Actions
25+ years if experience as an IT Systems Engineer.
I lectured in various conferences in Israel and abroad.
Bootstrapped my career as a systems administrator in a small StartUp, and a few years later learned about my passion to learn & teach ;) ,
My Day job was running production for a small ISP running various sub-systems, which quickly grew in demand, my journey continued when I joined Tikal ~16 years ago as a Configuration Manager and grew from there into the DevOps field.
I'm not the traditional geek 😉 I am very passionate about what I do ♾️.
HagZag
25+ лет опыта работы инженером ИТ-систем.
Я читал лекции на различных конференциях в Израиле и за рубежом.
Начал карьеру системного администратора в небольшом стартапе, а несколько лет спустя понял, что мне нравится учиться и преподавать ;) ,
Моя основная работа заключалась в управлении производством для небольшого интернет-провайдера, который запускал различные подсистемы, спрос на которые быстро рос, мое путешествие продолжилось, когда я присоединился к Tikal ~16 лет назад в качестве менеджера по конфигурации и оттуда перешел в сферу DevOps.
Я не традиционный гик 😉 Я очень увлечен тем, что я делаю ♾️.
HagZag
Area of Expertise
Topics
Harnessing Agentic DevOps & Security Compliance with A.I
Security compliance has a reputation problem: it's seen as paperwork that slows delivery down. Haggai argues the opposite — when compliance is treated as an engineering discipline and paired with agentic AI, it becomes a delivery accelerator.
Drawing on hands-on experience leading cloud compliance programs (FIPS 140-3 and FedRAMP) for regulated SaaS products, Haggai walks through how his team harnesses AI agents across the entire lifecycle: from planning (translating control frameworks into epics, backlogs, and architecture decision records), through implementation (compliant-by-default Terraform/Terragrunt modules, hardened container image curation, CI pipelines with zero static credentials), to delivery and evidence (automated SCA/policy scanning, IaC as continuous audit evidence, and agents that draft, verify, and maintain compliance documentation).
The session covers the practical harness: how to structure agent workflows, skills, and guardrails so AI output is trustworthy enough for auditors — and where humans must stay in the loop. Attendees leave with a repeatable pattern for turning any security standard into an agentic, automated DevOps workflow, plus the pitfalls learned the hard way.
Target audience: DevOps / Platform Engineers, SREs, security engineers, and engineering leaders working in (or heading toward) regulated environments — GRC-curious developers welcome. Best suited for mid-to-senior level; no prior compliance knowledge required.
Track fit: Sits at the intersection of DevOps Pro Europe and CyberWiseCon Europe; also relevant to the AI & ML Integration and Platform Engineering tracks.
Preferred duration: 40–45 min talk (can be adapted to 30 min);
Technical requirements*: Standard A/V (HDMI, screen, mic); internet connection preferred for the live demo but not mandatory.
First public delivery — this exact session has not been delivered publicly before. It builds on material from the speaker's "FedRAMP, From the Platform Side" blog series and prior conference talks on Agentic AI in DevOps (Reversim Summit, DevOps Days).
Language: English.
Content notes: All examples are anonymized from real client engagements; no vendor pitch, tooling shown is open source or widely available (Terraform/Terragrunt, GitLab CI, OPA, Syft/Grype, Claude/agent runtimes).
Choosing Your AI Harness: Portable Agentic Workflows Across Runtimes
Every benchmark now admits it: the harness changes the score. Yet most teams are quietly locking themselves into a single agent runtime — its config format, its skill system, its context conventions — the same way we once locked into a CI vendor.
Haggai works as a consultant across multiple client environments, each mandating a different runtime: Cursor here, Claude Code there, open-source harnesses elsewhere. That constraint forced a discipline: treat the harness as a replaceable execution engine, and invest in what's portable — versioned skills, layered context schemas, and the feedback loop the agent runs inside (what he calls loop engineering, the successor to prompt and context engineering).
This session walks through a working setup: a monorepo of versioned skills and project definitions, an MCP hub running on Kubernetes serving tools to any harness, and the token economics that decide whether an agentic workflow is viable at all. Attendees leave with a concrete portability checklist — what to standardize, what to abstract, and how to evaluate the next harness without rebuilding everything — plus lessons from real client migrations.
Target audience: Developers, DevOps/Platform Engineers, tech leads, and engineering managers adopting AI coding agents — anyone evaluating (or already regretting) an agent runtime choice. Mid-level and up; assumes basic familiarity with AI coding assistants, no specific runtime experience required.
Track fit: AI & ML Integration; also relevant to Platform Engineering and DevOps and Continuous Integration tracks.
Preferred duration: 40–45 min talk (adaptable to 30 min)
Format: Slides + live demo — the same versioned skill executed on two runtimes (e.g., Claude Code and an open-source harness), backed by an MCP hub on Kubernetes. Recorded fallback available.
Technical requirements: Standard A/V (HDMI, mic); internet connection preferred for the live demo, not mandatory.
First public delivery: Yes — this session has not been delivered publicly. It builds on the speaker's blog series on loop engineering and harness portability (portfolio.hagzag.com) and prior Agentic AI in DevOps talks (Reversim Summit, DevOps Days).
Language: English.
Content notes: Vendor-neutral by design — the whole point is not marrying one vendor. All tooling shown is open source or commercially available (Claude Code, OpenCode/Cursor, MCP, Toolhive, Kubernetes); client examples anonymized.
Reversim Summit 2025 Sessionize Event
swampUP 2025 Sessionize Event
DevOpsDays Tel Aviv 2022 Sessionize Event
swampUP 2022 City Tour - London Sessionize Event
Yalla DevOps Tel Aviv 2022 Sessionize Event
swampUP 2022 Sessionize Event
Cloud Native Devs !
Cloud Environments and Architectures, such as Serverless and Microservices, and their effective Deployment and Stability of Production have been our main focus, but we are now seeing the developer experience shifting. Forced to combine many subsystems together on our laptops it has become a mirror of the cloud. We used to call this our Integrated Development Environment, and we should start treating it as one. In this session, we will take a short tour of many patterns & tools designed to enhance the developer experience. From various integrations augmenting our existing IDE's to Internal Development Platforms designed as self-service platforms for developers.
https://docs.google.com/presentation/d/10HIxZq7fg9f-ArSc3Nb4dyloopIf01wkZ-BeTdkczXQ/present?slide=id.g102f21713f3_0_44
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top