AI DevelopmentLenny's Newsletter

How to design AI agent loops: schedules, goals, and subagents in Claude Code and Codex

Wednesday, June 17, 2026Read original

ai-coding-toolsautomation-stacksai-agent-workflows

“A loop is just an automated prompt, not a scary new paradigm”

Key takeaways

AI agent loops come in four types (heartbeat, cron, hook, goal) with specific use cases for each workflow pattern
Effective loops require five components: work trees, skills, plugins/connectors, subagents, and state tracking—think of it as onboarding an employee
Goal-based loops are the most expensive and difficult to implement correctly, with two warning signs that predict token waste before production value

Why this matters for operators: Technical teams implementing AI automation workflows, engineering leaders evaluating agent architectures

I cover AI×GTM intelligence like this every Wednesday.

AI DevelopmentLenny's Podcast

Human resistance to full AI autonomy is not purely technical—it's psychological and organizational; companies will rationalize keeping humans in decision loops even when agents are capable
The 'human-in-the-loop' requirement may become a self-perpetuating narrative rather than a genuine necessity, driven by organizational risk aversion and change resistance
Product leaders at scale (Notion) are observing this pattern, suggesting it's a widespread phenomenon across enterprise AI adoption, not isolated to specific use cases

ai-agent-adoptionhuman-in-the-loopai-governance

GTM Ops**RevOps Impact (Jeff Ignacio)

Consumption pricing fundamentally breaks traditional SaaS comp models—requires rethinking sales incentive structures around usage vs. contract value
Four distinct contract structures exist (pay-as-you-go, uncommitted, committed, hybrid), each requiring different compensation mechanics and sales behaviors
Enterprise consumption-based deals create tension: customers want flexibility, sales teams need predictability for quota attainment—comp design must bridge this gap

revenue-platform-consolidationconsumption-pricing-modelssales-comp-design

AI×GTMGTM OS: The Future GTM Operator

Model parity has arrived: OpenAI/Claude now trade evenly on core tasks, making 'better AI' a non-differentiator—the edge shifts to integration depth into existing revenue motions
Waste is quantified: teams paying $17K-$37K/month for AI seats that never touch pipeline generation; real cost is opportunity cost of unused capacity, not subscription fees
Lean teams have a structural advantage: cannot out-buy larger competitors on model access, but can out-embed them by wiring AI 1 revenue motion deep (pipeline → content → deals) with proprietary deal context competitors haven't seen

ai-sdr-adoptionrevenue-platform-consolidationback-to-basics-gtm

This analysis was produced using the STEEPWORKS system — the same agents, skills, and knowledge architecture available in the GrowthOS package.