Field Notes
A weekly dispatch from the edges of the knowledge graph.
Week of
Aug 10–Aug 16, 2026
16 sources / 79 insights
Five things worth knowing
Ethan Ding's essay argues Palantir is a vertically-integrated outcome-based software provider whose moat comes from three compounding inputs: 12 years of patient capital during a commercial PMF desert, government deployments lacking modern cloud primitives, and an outcome-based (not usage or hours-based) pricing model. This combination produced a differentiated FDE talent pool, an unusually broad product (Foundry/Ontology), and account-level economics competitors structurally cannot replicate, making Palantir near-impossible to clone in the current AI/VC funding environment that demands 3-month results.
Dex introduces /show-me, a skill for making coding agents communicate via compact visuals (component trees, call stacks, diagrams, pseudocode) instead of prose walls, then argues in a companion essay that 'lights-off' AI software factories fail because models can't maintain codebase quality over time, making human-in-the-loop program design and vertical slicing essential.
A detailed workflow for building an outbound sales agent using Hermes that connects Apollo, Clay, Crustdata, HubSpot, Telegram, Smartlead, and Unipile into a research-to-outreach pipeline: market->research->signal->message->approval->action->CRM, with staged autonomy, strict evidence rules, and hard stop conditions on replies.
Aaron Levie and Jesse Zhang analyze why FDEs are resurging in AI go-to-market: AI agents require discovering entirely new, non-deterministic workflows that neither vendor nor customer has ever seen, unlike deterministic traditional software. The Palantir playbook shows FDE pain should convert into product primitives, but many AI startups risk turning FDEs into a permanent services crutch rather than a temporary discovery phase.
Adrian outlines a structured planning workflow using Fable to front-load work before large-scale unattended agent execution: idea capture, adversarial questioning, research subagents, PRD drafting, policy setting, task decomposition into parallelizable 'beads', and adversarial review of tasks against the PRD.