68 - AI-SDLC | Yonatan Maor (Clears.ai)

When vertical AI companies should post-train open-weight models: SFT vs. RL, agentic rollouts, reward design, and simulated environments.

A grounded look at TypeSafe AI's Jev classifier model: architecture, real use cases, and where it falls short.

How frontier teams make coding agents run autonomously for hours instead of minutes: AI-ready repos, TDD guardrails, ephemeral environments, tracing, and proof-of-work loops.

Automating meetings end-to-end with agents - calendar tagging, prep briefings, learning loops, skill sharing, and self-closing feedback cycles.

A deep dive into the architecture and security model behind autonomous agent harnesses - isolation, credential gateways, and skill-based extensibility.

A behind-the-scenes look at real agentic-coding workflows: visual planning, cloud-first agents, ephemeral PR environments, custom skills, and secrets management.

How to market and sell to AI agents — discovery channels, CLI vs MCP trade-offs, authentication patterns, and the emerging agent-driven economy.

A practical, stage-by-stage look at running your entire development lifecycle with AI agents: from PRD to coding to QA.

A practical look at managing AI budgets across coding agents, customer-facing models, and production inference

Two real-world use cases are covered: CVE Enrichment for open-source vulnerability detection and real-time Malicious Command Detection, along with practical tips on cost optimization, prompt caching, and open-source vs. commercial model trade-offs.