Token & Context
+Request-boundary measurement, context budgets and provider token usage.
-
+
++ +
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 →
-
+
++ +
Cached Input Is a Separate Usage Field, Not Free Extra Context
Keep provider-reported cached input distinct and check model-specific pricing; there is no universal cache definition or hit rate. Read the article →
-
+
++ +
Measure the Final Request Boundary, Not the Visible Prompt
A reproducible method for capturing assembled messages, tool schemas, retries and provider-reported usage without attributing tokens by guesswork. 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 →
-
+
++ +
What Is Token Optimisation? A Measurement-First Definition
A practical definition: improve recurring AI workflow efficiency while preserving the agreed result, quality checks and verification. Read the article →
-
+
++ +
Context Budgets Are an Allocation, Not a Target to Fill
A method for allocating relevant instructions, evidence and output reserve without filling a model context window by default. Read the article →
-
+
++ +
Why a one-line AI canary can still consume 10k+ input tokens
A tiny AI canary can trigger a large prompt. Learn how wrappers, history, schemas and tool context add input tokens—and how to measure the true request. Read the article →