All chapters
  1. Start hereAn agent is a model call in a loop
  2. Chapter 1One call: what a model is from the outside
  3. Chapter 2The loop: where a call becomes an agent
  4. Chapter 3The abstraction ladder: six rungs over one call
  5. Chapter 4The eight jobs of a harness
  6. Chapter 5Context: deciding what the model sees
  7. Chapter 6Tools: what the model may ask for, and where it runs
  8. Chapter 7MCP: one way to plug tools into any harness
  9. Chapter 8RAG: retrieval is context assembly
  10. Chapter 9Control flow and state: stopping, pausing and resuming
  11. Chapter 10Guardrails: identity, approval and the output contract
  12. Chapter 11Reliability and cost: retries, budgets and the failures that will happen
  13. Chapter 12Observability and evals: knowing what the agent did, and whether it was right
  14. Chapter 13Many agents: more loops, and what each one costs
  15. Adopt · 1SDKs: the same loop in Python, TypeScript and Java
  16. Adopt · 2Coding harnesses: a finished harness for software work
  17. Adopt · 3Frameworks and graph runtimes: the loop as a library
  18. Adopt · 4Managed platforms: someone else runs the loop
  19. Adopt · 5Build your own: a whole harness in one file
  20. DecideBuild or adopt: who runs each job?
  21. ReferenceGlossary
  22. AboutAbout this site
About

About this site

What this site is, what it is not, and how the facts were checked.

This is a knowledge site about the software around a language model: the harness. It starts from one HTTP call, adds a loop, names the eight jobs that the loop needs done, and then reads SDKs, coding harnesses, frameworks and managed platforms as different owners of those same jobs. It is written for engineers and architects who build agent systems or choose between products that claim to build them.

What it is and is not#

It isIt is not
A map: one way to read any agent product, as eight jobs with an owner eachA standard, or the only way to divide the work
First principles, then abstractions: each problem in plain code before the product that hides itA product catalogue or a buying guide
One running example, a property-insurance quote, followed through every chapterA record of any real insurer; the company, the data and the vendors are invented or simulated
Product behavior read on the vendor's own documentation on 16 November 2026A promise that a product still behaves that way; check before you build
Descriptions by job: what a product runs for you and what stays with youA ranking. No product is called best

What is original here and what is not#

IdeaStatus
A model call, tool use, the agent loopDocumented behavior of model APIs
The eight jobs of a harnessA checklist proposed on this site. Other authors divide the same work differently
The six-rung ladderA way of ordering existing kinds of product, proposed on this site
The words BUILT IN, INTEGRATES, YOU BUILD, MANAGED, NOT ITS JOBThis site's reading of each vendor's documentation, not a vendor's own label
Checkpoints, retries, idempotent side effects, outbox, traces, golden setsStandard engineering practice, applied to agents
The miniature harnessWritten for this site, to be read in one sitting. It leaves things out on purpose, and each page says what

How the facts were checked#

Kind of claimHow it was checked
Product behaviorRead on the vendor's own documentation on the day of writing and logged with the page address and the date. More than 500 claims are logged. Where a page did not say, the site says "the docs do not say"
The product by job mapBuilt from those readings. A cell is a reading of documentation, not a test of the product
The miniatureRun. Every command and output shown from it is real, against a scripted stand-in for the model. It never called a live model for this site
Code in Python, TypeScript and JavaEach block says how far it was checked: compiled against the real package, constructed without calling a model, run against a local stand-in, or documented shape only
The full buildDescribed from the author's own implementation. Its vendors are simulated and its history is seeded. Its numbers are quoted, not re-measured
NumbersIllustrative unless a source is linked. Token counts from the miniature are the scripted model's estimates

Documentation changes. Several facts on this site differ from what the same pages said two days earlier, and the pages say so where it matters. Treat every product claim here as true on the day it was read.

What the miniature leaves out#

The miniature is about 450 lines so that it can be read whole. A production harness needs more. The gaps are stated on the pages where they matter, and collected on Build your own. Among them: it does not validate tool arguments against the schema, it screens untrusted text with four simple patterns, its trace does not record every token type, and what it calls an outbox is a key store without a worker.

Who wrote it#

Sam Muthu, an engineer and architect who builds agent systems and holds Anthropic's Claude Certified Architect credentials (Foundations and Professional). More of his work is at sammuthu.com. A sister publication, Diff to Deploy, follows one code change through a delivery pipeline that uses coding agents.

The site is a working version. If a claim is wrong or out of date, the fix is to read the vendor's page again and correct the sentence.