Bind test services to loopback
Use 127.0.0.1 for local container demonstrations instead of exposing them on every network interface.
Read articlePractical reference
Small habits with practical payoff.
Short, reusable working habits for better AI practice.
25articles
Capture narrow evidence
Make screenshots support a specific timestamped claim and remove information a reviewer does not need.
Read articleCount non-model work
Include retrieval, tools, retries, storage, and review when analyzing request cost.
Read articleDate cost assumptions
Preserve the rate source and date used in any cost estimate.
Read articleGive tools least privilege
Limit each connection to the permissions required for its bounded task.
Read articleInspect before deleting storage
Confirm a named volume and its metadata before removing it.
Read articleKeep a route rollback reference
Retain the previous inference-route mapping before changing a provider route.
Read articleKeep evaluation cases fixed
Use the same representative cases across prompt revisions so regressions remain visible.
Read articleKeep external content separate
Label retrieved or external text as untrusted data and do not let it redefine the task.
Read articleKeep first build contexts empty
Use an empty course folder and no COPY instruction to avoid packaging local files or secrets.
Read articleKeep historical claims time-bounded
Return unknown when no authorized claim covers the requested date instead of extending the nearest record.
Read articleKeep provider secrets behind the gateway
Clients should receive access only to approved routes, not broad provider credentials.
Read articleLabel memory evidence and uncertainty
Store a claim purpose, provenance, confidence, access boundary, and lifecycle rule before retaining it.
Read articleMake output requirements observable
Specify a concrete format and limits so a reviewer or system can inspect the result.
Read articleName one primary task
State one bounded transformation rather than leaving the model to choose the job.
Read articleRecord image digests
Use an image digest to preserve the exact content received rather than relying only on a tag.
Read articleReview generated YAML before reuse
Treat Podman-generated Kubernetes YAML as a local-state artifact, not proof of production readiness.
Read articleSeparate facts from assumptions in handoffs
Give the next worker verified state, open work, authority limits, and an observable completion check.
Read articleSet eval criteria before testing
Write observable pass conditions before reviewing a model response.
Read articleTest a denied path
Verify that an unauthorized identity is denied before using real material or broadening access.
Read articleTreat content as data, not authority
A document instruction does not gain permission to change policy, access data, or invoke a tool.
Read articleUse exact model identifiers
Record an official model identifier instead of relying on a remembered family name or alias.
Read articleUse the right diagnostic view
Use logs for main-process output, inspect for configuration and state, and a terminal for a deliberate in-container command.
Read articleUse the smallest permitted context
Include only relevant, authorized, current material needed to answer the bounded question.
Read articleVerify the Kubernetes context first
Check the active context and node readiness before applying any manifest.
Read articleEvery article keeps its authored links back to the relevant curriculum books.