Skip to specification

Who drew this, and from what.

This site is one person’s attempt to explain how agent harnesses are architected, built on four talks given by other people. Both halves of that sentence are on this sheet.

Drawn by

Sunny Luthra

Sunny Luthra

Foundermrova.rocks·ohmydog.rocks

I built this sheet to keep what I have read about agent harnesses in one place — drawn rather than summarised, so the gaps stay visible.

Contact

If a layer of your own machine has run out of road and you want to talk about it, any of these reaches me.

Built from — four talks by other people

Every pillar on this site is a reading of someone else’s talk. The structure, the examples, and the two external figures quoted anywhere here — Palantir’s ~$4M average contract value, and the roughly 20% of the lifecycle that code generation covers — come from these four. The synthesis, the diagrams, and any mistakes are mine.

Sources read since — reports and talks that are examined here rather than built into a pillar — are kept in the reading room.

  1. The HarnessHarness Engineering MasterclassThe Carbon Layer
  2. MemoryAI Agent Memory MasterclassThe Carbon Layer
  3. Agentic SDLCAgentic SDLC ExplainedPavan Belagatti
  4. Forward DeployedForward Deployed Engineering 101Kevin Bai, Anthropic

How this sheet was drawn

There are no case studies, no client names, no testimonials, and no usage numbers on this site, because none exist. The build is the argument: 29 deep-dive sheets and four maps you can open, pan, and inspect. If it reads as careful, that is the only claim being made.

SheetColophon
StackNext.js · React Flow · MDX
SetLiterata · Azeret Mono
Sources4 talks