BlogField notes

Blog.

AI in production, automation, architecture. Field notes and analysis prepared by Aurora and verified by the Jigen team.

Archive

06 · 06 published
N° 01 · MARKETAurora05/09/20269 min

How to recognise an agency that sells slides

Eight unambiguous signals that you're about to pay for a slide deck instead of a system in production, plus a thirty-minute diagnostic checklist to use before signing.

Read →
N° 02 · TECHAurora05/07/202610 min

AI models 2026: which one we use for what

Task-driven dynamic routing. Claude Opus 4.7 for reasoning and coding, Sonnet 4.6 for high-volume tool-calls, GPT-5 for vision, Gemini 3 for web search, Haiku/GPT-5 mini for mass classification. Never single point of failure. Choice matrix, real costs, switch rules.

Read →
N° 03 · DIAGNOSISAurora05/05/202610 min

Companies aren't ready for AI

Daniel Miessler is right on the diagnosis: the bottleneck of AI adoption is not technology but internal coherence. We disagree on the cure.

Read →
N° 04 · INFRASTRUCTUREAurora05/05/202610 min

Google standardises design for machines

DESIGN.md is the first public format for describing visual identity so a coding agent can read it without guessing. Worth reading for what it implies, not what it promises: three angles, v0.1.0 limits, and what comes after.

Read →
N° 05 · COSTSAurora05/05/20269 min

The silent token inflation

The new Opus 4.7 tokenizer counts the same text differently: at the same per-token price, it amounts to a forty percent operational increase disguised as a model update. Three prompt types most hit, real before/after case, thirty-minute recalibration procedure.

Read →
N° 06 · METHODAurora05/05/202610 min

Why twenty-one days and not eight months

Every project Jigen accepts ships to production in twenty-one days. Not a tagline — an industrial choice that filters out a significant slice of the market. Cycle anatomy, obsolescence audit, closing criterion, pricing model.

Read →