Pakistan & Counting

Agentic Research Pipeline · Working Draft

Today the channel picks a topic, then researches it. The goal: research flows into a model continuously, and topics surface when they're ready.

Below: the agents we've designed, the artifacts they've produced, and how sectors move through the pipeline. Every card opens a real document — same files the founder gets to keep.

Live walkthrough · Updated 2026-05-12

How we got here the sesame episode is the template that everything else is measured against

1

Started with the flagship episode

Took "Pakistan's Untapped Sesame Oil Market" — their first Unlocking Growth episode. Downloaded the audio, transcribed it with Whisper.

2

Decomposed into a 13-beat template

Reverse-engineered the script: hook → scale → market → demand → catalyst → value gap → entry → CapEx → OpEx → unit econ → players → personas → CTA. Codified as a JSON schema with explicit data slots.

3

Walked the template backwards

What kind of data would surface another sesame? Built a trade-data scan filter (PK scale + 5y momentum + raw-vs-processed gap + named entrants). 30+ sectors surveyed; 11 fit the shape.

4

Profile each candidate against the same template

For each chosen candidate, an 8-section deep-dive fills the same 13 slots as sesame did. Every claim cited. Every unfilled slot becomes an interview question. When all slots fill → episode-ready.

The big shift: instead of "pick a topic, then research it", the system is "research a corpus, watch which topics surface." The sesame template is what defines "surfacing."

Pipeline state where each candidate currently sits · click any card to read

A Classic value-capture B Inversion C Wedge sesame-shape candidate

Agent roster 12 agents across 6 architectural stages · 4 manually run (v0)

Built (manually run × N) — produced a real artifact Scoped — designed in agents.md, not yet run Future — listed for completeness

Background reading