Methodology
+Methods for measuring and verifying recurring AI workflows.
-
+
++ +
Token Optimisation for AI Agents: Control Context Without Deleting the Job
Token optimisation for agents is not “make the prompt shorter.” Preserve requirements, evidence and verification while removing repeated or irrelevant context. Read the article →
-
+
++ +
We Removed Middleware From Our WordPress AI Workflow — What the Native REST API Already Gave Us
A practical case study: we moved routine AI-driven WordPress work onto the native REST API, tested posts, pages and media end to end, and kept privileged plugin deployment separate. Read the article →
-
+
++ +
Your AI Agent Said It Finished. It Hadn’t.
An AI agent saying “done” is not evidence. Use external acceptance checks, durable receipts and independent verification before treating autonomous work as complete. Read the article →
-
+
++ +
A Practical API-Cost Scenario: Inputs, FX Date and Limits
A CALCULATED illustrative API scenario shows why request volume, cache share, source rates and dated FX must travel with an estimate. Read the article →
-
+
++ +
Building AI Tools We Needed for Real Workflow Questions
Three focused browser tools address recurring decisions about agent rules, context policies and measured AI costs; adoption and savings remain unmeasured. Read the article →
-
+
++ +
Local AI vs Cloud AI: The Break-Even Inputs That Matter
A modelled break-even method covering hardware, power, utilisation, API usage, quality and human handling; no universal winner is claimed. Read the article →
-
+
++ +
Human Time Belongs in AI Workflow Economics
A measurement method for human review, setup and recovery beside machine runtime and provider waits; current minutes remain unknown. Read the article →
-
+
++ +
Cheaper-Model-First Routing Needs a Quality Gate
A method for routing to a lower-cost model only when the same acceptance standard still passes; no routing-savings result is claimed. Read the article →
-
+
++ +
LLM or Deterministic Tool? A Decision Framework for Recurring AI Work
Choose code or a model from the task’s acceptance criteria, uncertainty and verification needs—not novelty or a universal cost claim. Read the article →
-
+
++ +
Shared AI Operating Rules: Reduce Repeated Decisions Without Promising Token Savings
Shared operating rules can make recurring safeguards easier to inspect; paired tests are still needed before claiming token or quality gains. Read the article →