Deep dive · XiaoHu explains

Inside Anthropic: the harness wrapped around the model is being torn down

Once a model can work out its own steps, the orchestration bolted around it turns into a cage. A 16-minute internal conversation on what grows back after the harness thins out.
One-minute read
  • The code layer wrapped around the model — the harness — is getting thinner. What it encodes are assumptions about what the model can't do, and those assumptions expire as models improve
  • As it thins, a new layer grows on top that decides which play to run. Anthropic's own blog calls it a meta-harness
  • The permission model is shifting: from "what can this user do" to "what can this Agent do inside this compartment"
  • For enterprises, the recommended order is individual → team → cross-team process. Don't start with the hardest layer
  • The easiest trap: once everyone can go it alone, staying aligned gets harder, not easier
  • On the platform side it lands on outcomes — you hand over acceptance criteria, not steps
This is a conversation published by Anthropic itself. Both speakers are describing their own platform's direction, so anything about product capability is the vendor's account.
Start with a web of conditions

Tearing down the scaffolding around the model

Anthropic recently released a conversation titled Building the future of agentic infrastructure, running about 16 minutes. Two people on camera: Angela covers the usage patterns she sees on the customer side and how the harness has evolved; Caitlin works on the Managed Agents product line and talks about Agent identity, engineering teams, and where the platform is headed.

Six months ago the Claude platform was mostly an inference endpoint: text goes in, results come out. Since then two layers of trouble have been stacked on top — infrastructure, and harness engineering.

First, what a harness actually is

A model does exactly one thing: read text, emit text. It can't open a file, run a command, or query a database on its own. The harness is everything wrapped around it — it reads what the model emits as "it wants to use this tool," actually runs that tool, and feeds the result back so the model can keep thinking. When the context is nearly full, it compresses. When something crashes, it checkpoints and resumes.

If the model is the engine, the harness is the rest of the car: steering wheel, gearbox, fuel gauge, seatbelts.

But "harness" is a loose word for a bundle of very different things. Pull it apart and you get four categories:

Legwork
Actually running tools, reading and writing files, feeding results back to the model
Stays forever
Cleanup
Compressing a full context, reconnecting after a drop, checkpointing and resuming after a crash
Stays forever
Guardrails
What it may touch, what it may not, which actions require a human first
Stays forever
Deciding for the model
Do A, then B; only advance under these conditions; every step must follow this exact order
This is the box being torn out

The first three cover things a model fundamentally cannot do, no matter how capable it gets — someone will still be writing that code a decade from now. The fourth is different: it makes decisions on the model's behalf, and the only reason it ever existed is that the model made poor ones.

A few months ago the standard practice was to pile that fourth box high: chop the business into boxes and wire them together, gate A before B, let B fire only when a stack of conditions is satisfied, until you have a genuinely complicated web. There was a reason for it at the time — model unpredictability used to be far more painful, so you pinned it down with a standard operating procedure.

The cost is brittleness. And the logic runs backwards: you bought the model's intelligence, then the orchestration boxed it in, so the Agent never gets to show the capability you were paying for.

A concrete case: the patch that became dead weight

Anthropic's engineering blog records an incident that beats any abstract argument. Sonnet 4.5 had a quirk: partway through a task, as it approached the context limit, it would start rushing to wrap up. The engineering team called this "context anxiety." So they added a patch to the harness that did context resets specifically to fix it.

Then they moved to Opus 4.5, and the quirk disappeared on its own. The patch became, in their words, dead weight.

That's the whole meaning of "the harness is thinning." The layer made sense when it was built. Once the model improves, the part that was covering for it flips from insurance to drag. Anthropic's own framing: everything encoded in a harness is an assumption about what the model can't do, and those assumptions expire as models get stronger, so they have to be dragged out and questioned again and again.