Skip to content
All articles
Engineering26 February 2025·4 min read

Context is king: tools for feeding your code and website to LLMs

The uncomfortable part of building for agents is that the old assumptions quietly stop holding.

Paycux engineering

The uncomfortable part of building for agents is that the old assumptions quietly stop holding. There is no browser to redirect, no person to read a consent screen at the moment it matters, and no obvious place to put the word "no".

This piece walks through how we think about it at Paycux, what we have changed our minds about, and where the sharp edges are.

‍Why context matters

‍Why context matters is where this gets concrete. The audit trail matters more here than in any human flow. When something goes wrong, the question is never "did the user intend this" in the abstract — it is which agent, acting under whose authority, made which call, and whether the record can prove it.

An agent's credential should describe what it may do, not who owns it. Scope it to the narrowest set of operations that make the task possible, bind it to a single principal, and give it a lifetime measured in minutes rather than days.

Gitingest: Turn any GitHub repo into a prompt-friendly text file

Consider gitingest: turn any github repo into a prompt-friendly text file. An agent's credential should describe what it may do, not who owns it. Scope it to the narrowest set of operations that make the task possible, bind it to a single principal, and give it a lifetime measured in minutes rather than days.

The audit trail matters more here than in any human flow. When something goes wrong, the question is never "did the user intend this" in the abstract — it is which agent, acting under whose authority, made which call, and whether the record can prove it.

  • Scope every agent credential to one principal and one task
  • Give tokens minutes of life, not days
  • Record which agent acted, under whose authority, on what
  • Make revocation a single call that takes effect immediately

‍Local repository digests via a custom script

‍Local repository digests via a custom script is where this gets concrete. The audit trail matters more here than in any human flow. When something goes wrong, the question is never "did the user intend this" in the abstract — it is which agent, acting under whose authority, made which call, and whether the record can prove it.

Consent is the part most implementations get wrong. Asking once at install time and then acting indefinitely is not consent; it is a standing grant with no expiry and no visibility.

Using Cursor’s native @docs Integration

Consider using cursor’s native @docs integration. The audit trail matters more here than in any human flow. When something goes wrong, the question is never "did the user intend this" in the abstract — it is which agent, acting under whose authority, made which call, and whether the record can prove it.

The audit trail matters more here than in any human flow. When something goes wrong, the question is never "did the user intend this" in the abstract — it is which agent, acting under whose authority, made which call, and whether the record can prove it.

An agent's credential should describe what it may do, not who owns it.

How It Works

How It Works is where this gets concrete. An agent's credential should describe what it may do, not who owns it. Scope it to the narrowest set of operations that make the task possible, bind it to a single principal, and give it a lifetime measured in minutes rather than days.

The audit trail matters more here than in any human flow. When something goes wrong, the question is never "did the user intend this" in the abstract — it is which agent, acting under whose authority, made which call, and whether the record can prove it.

Why this is useful

That brings us to why this is useful. Consent is the part most implementations get wrong. Asking once at install time and then acting indefinitely is not consent; it is a standing grant with no expiry and no visibility.

An agent's credential should describe what it may do, not who owns it. Scope it to the narrowest set of operations that make the task possible, bind it to a single principal, and give it a lifetime measured in minutes rather than days.

The spec file pattern

That brings us to the spec file pattern. Consent is the part most implementations get wrong. Asking once at install time and then acting indefinitely is not consent; it is a standing grant with no expiry and no visibility.

An agent's credential should describe what it may do, not who owns it. Scope it to the narrowest set of operations that make the task possible, bind it to a single principal, and give it a lifetime measured in minutes rather than days.

Where this leaves us

None of this is exotic. It is the ordinary discipline of deciding what you own, writing down what you assume, and making the failures loud enough to notice.

If you are working through the same problem and want to compare notes, the docs cover the mechanics and the console shows the behaviour on your own data.

Everything here, already built

Sign-in, enterprise SSO, directory provisioning, roles and an audit trail behind one API. Start with the quickstart and have a working sign-in this afternoon.

Start selling to enterprise customers

Create an account, point sign-in at Paycux, and get back to the part of the product that is actually yours.