All four platforms available

Blog · Field notes

Notes from the build.

The elan1 blog publishes short, dated notes from building the governed write path for AI agents, each by a named author with any corrections listed. Topics include why a refusal costs less than an allowed action, why a model may propose but never allow a write, what tamper-evident means at L1 and why systems should fail toward a human.

Short pieces on the decisions behind elan1, each dated and signed by a named author. When we get something wrong, the correction is logged on the note.

Latest · Operations · Field note

Fail toward a human

Every system fails. The design question is which way. When anything is unclear or unavailable, elan1 stops and asks a person.

2 min readM. K. Elango

01All field notes

Every note, newest first.

Evidence · Design note

Designing the 16-field proof record

"No seventeenth field, ever." Why the record has the fields it has, why it has no others, and why the payload itself stays out.

2 min readM. K. Elango

Evidence · Field note

What tamper-evident means at L1

At L1 we make one integrity claim, and we chose the weakest honest word for it. Here is exactly what it covers and where it stops.

2 min readM. K. Elango

Pricing · Field note

Why a refusal costs 40% of a governed action

A refusal still runs the checks and writes a proof record, but nothing reaches your books. So it carries a reduced charge, never the full one.

3 min readM. K. Elango

Subscribe by RSS: elan1 blog feed. Announcements have their own feed.

Dated and signed. Every note carries its author and publication date.

No invented numbers. Every figure says where it comes from.

Corrections logged. Changes after publication are listed at the foot of the note.

// SEE IT

Read less, see more.

The walkthrough shows every idea in these notes on one governed write, in about five minutes.