Agentic Delivery Field Notes

From scarce resources to optimal delivery outcomes.

Practical postmortems, operating rules, and reusable tools for founders and product leaders using AI agents and subagents across product discovery, project execution, validation, and program governance.

Product managers
Founders
Project managers
Program managers

Evidence philosophy

Operating lessons with their boundaries intact.

These notes examine what appeared reasonable, what failed in practice, why it failed, and what changed. Sensitive details are generalized, and material claims distinguish observation, external evidence, inference, and proposal.

Published field notes

Two connected decisions: simplify the system, then manage its constraint.

FIELD NOTE 01 · AGENT DESIGN

Too Many Agents, Too Little Delivery

Why an AI organization chart is not an operating model.

Agent count can increase faster than accepted output. This field note explains how to recognize the failure and redesign the workflow around the smallest accountable team.

Evidence: Author reflection + proposed practice
Focus: Team design
Reading time: 11 min

Includes: Do You Need Another Agent? decision checklist

Read Too Many Agents, Too Little Delivery

FIELD NOTE 02 · SYSTEM OPTIMIZATION

The Bottleneck Moves

How agents, skills, owner decisions, and scarce capacity determine product, project, and program outcomes.

A practical framework for selecting the most valuable feasible combination of work, agents, skills, sequencing, and delegated authority under limited capacity and uncertain evidence.

Evidence: Evidence-bounded framework + checked illustration
Focus: Constraint allocation
Reading time: 16 min

Includes: Delivery Constraint and Capability Allocation Canvas

Read The Bottleneck Moves