Aestetics

Author: alvagante

_posts/2026-05-22-reading-the-swamp.md

@@ -16,7 +16,7 @@ It's a lie, I didn't.
 
 I forced an innocent AI to read it and summarize and explain the whole thing with the patience only AIs can have nowadays.
 
-This post, written in 4 hands, well, two hands and a bunch of tokens, (you will never know, nor care, who wrote what), is the final, public, of such a journey into the swamp.
+This post, written in 4 hands, well, two hands and a bunch of tokens, (you will never know, nor care, who wrote what), is the final public summary of such a journey into the swamp.
 
 ## The map I should have read first
 
@@ -70,29 +70,55 @@ Anyone who has agonised over "should the AI write code here, or data?" feels tha
 
 It is the Puppet resource abstraction layer, reborn for agents.
 
-**Workflows.** Multi-step DAGs of jobs, with parallel steps, and — this is the good bit — they nest. Steps chain data from earlier steps with CEL expressions, so the output of one job feeds the input of the next, typed all the way. It is a pipeline, except every edge is typed and every node leaves an immutable, versioned artifact behind. My day-one naming bug lived exactly here, in a model the loader refused to discover. Now I understand why the loader has opinions.
+**Workflows.** Multi-step DAGs of jobs, with parallel steps, and — this is the good bit — they nest.
+Steps chain data from earlier steps with CEL expressions, so the output of one job feeds the input of the next, typed all the way.
 
-**Vaults.** Encrypted secret storage, referenced by expression, resolved at runtime rather than at planning time. Swappable providers: local encryption for me on my own, AWS Secrets Manager or 1Password for a team. Boring. I mean that as a compliment. Secret management that is boring is secret management done right.
+It is a pipeline, except every edge is typed and every node leaves an immutable, versioned artifact behind.
 
-**Extensions.** The thing I face-planted into on day one. Extensions package reusable components — models, vault providers, execution drivers, datastores, reports — and you publish them to a registry where they become *"a full citizen immediately"*. On day one this scared me, and it still does a little. On day two I also see it for what it is: a package manager for agent capabilities.
+My day-one naming bug lived exactly here, in a model the loader refused to discover. Now I understand why the loader has opinions.
 
-And no, Matteo, it's not just yet another collection of skills, hope this post will help in clarifying , what I not able to explain correctly.
+**Vaults.** Encrypted secret storage, referenced by expression, resolved at runtime rather than at planning time.
 
-**Reports.** Structured analysis after every run, in Markdown *and* JSON. The agent doesn't just do the thing — it tells you what it did, in a format a human and another machine can both read. An audit trail as a first-class citizen, not an afterthought.
+Swappable providers: local encryption for me on my own, AWS Secrets Manager or 1Password for a team.
 
-**Skills.** Markdown documents that teach the agent how to use Swamp, loaded on demand when a trigger fires. So the agent learns Swamp *from* Swamp. The framework documents itself to its own operator. Mildly meta. Slightly unsettling. Mostly brilliant.
+Boring. 
+I mean that as a compliment. Secret management that is boring is secret management done right.
+
+**Extensions.** The thing I face-planted into on day one. Extensions package reusable components — models, vault providers, execution drivers, datastores, reports — and you publish them to a registry where they become *"a full citizen immediately"*.
+
+On day one this scared me, and it still does a little.
+On day two I also see it for what it is: a package manager for agent capabilities.
+
+And no, Matteo, it's not just yet another collection of skills, hope this post will help in clarifying what I was not able to explain correctly.
+
+**Reports.** Structured analysis after every run, in Markdown *and* JSON.
+
+The agent doesn't just do the thing — it tells you what it did, in a format a human and another machine can both read.
+
+An audit trail as a first-class citizen, not an afterthought.
+
+**Skills.** Markdown documents that teach the agent how to use Swamp, loaded on demand when a trigger fires.
+
+So the agent learns Swamp *from* Swamp.
+
+The framework documents itself to its own operator.
+
+Mildly meta. Slightly unsettling. Mostly brilliant.
 
 ## Not only for infrastructures
 
 On day one I kept asking the same nervous question: *what repo?* Infrastructure repo? Software repo? Any repo?
 
 The honest answer the docs gave me is: **any repeatable, multi-step thing.**
 
-Infrastructure is the obvious case — inventory, provisioning, an AMI lookup feeding an EC2 model. Expected. Adam Jacob, System Initiative — of course it does infrastructure.
+Infrastructure is the obvious case — inventory, provisioning, an AMI lookup feeding an EC2 model.
+
+Expected. 
+Adam Jacob, System Initiative — of course it does infrastructure.
 
 But the moment you stop reading "automation for AI agents" as "infrastructure" and start reading it as *"anything an agent currently does ad hoc in a chat window"*, the thing gets a great deal bigger.
 
-Webframp, wrote a [enlightening post](https://webframp.com/posts/swamp-beyond-infrastructure/){:target="_blank"} about this, give it a look.
+Webframp wrote a [enlightening post](https://webframp.com/posts/swamp-beyond-infrastructure/){:target="_blank"} about this, give it a look.
 
 Use cases are whatever you do more than once with an agent (or you should/may do with it).
 
@@ -104,7 +130,10 @@ Or data remediation — a messy media library, a directory of inconsistently nam
 
 Or the dull business automations — invoicing, monthly reports, the recurring thing you always forget until it is late.
 
-The pattern underneath all of them is the same. The moment you frame a task as *"a workflow of typed models"* instead of *"a thing I ask the agent to improvise again"*, it stops being a one-off and becomes an **asset**. Reusability, abstraction, repeatability, traceability — my day-one sacred principles — except now they apply to what the AI does, not only to what I write by hand.
+The pattern underneath all of them is the same. 
+The moment you frame a task as *"a workflow of typed models"* instead of *"a thing I ask the agent to improvise again"*, it stops being a one-off and becomes an **asset**. 
+
+Reusability, abstraction, repeatability, traceability — my day-one sacred principles — except now they apply to what the AI does, not only to what I write by hand.
 
 ## Teaching my agents to swim