Find one repeated job, count the time it really takes, and test a smaller way to do it. A practical worksheet for owners who already have enough tools.

FIELD GUIDE

Run the business / 4 MIN

Give every enquiry a next step. Keep a human on the reply.

A simple enquiry-to-draft workflow for busy owners: clear permission, one contact record, a useful reply, and a stop rule when the conversation changes.

FIELD GUIDE

Run the business / 4 MIN

Did that automation actually give you time back?

A five-day test for owners doing sales, delivery, and admin: count the review time, catch the expensive mistakes, and decide what deserves another week.

FIELD GUIDE

Agent systems / 3 MIN

A handoff is not done when the message is sent.

Record what the next worker received, which state it used, and what actually committed. A small receipt contract for durable agent workflows.

FIELD GUIDE

Agent systems / 4 MIN

Your agent remembered. Did it change the next action?

Five source-checked changes in orchestration, execution evidence, memory validity, MCP discovery, and local inference that affect implementation choices.

RESEARCH BRIEF

Evidence & measurement / 3 MIN

You appeared in an AI answer. What did you actually measure?

A citation screenshot is a lead. A stable query panel is a record you can compare. Keep the engine, denominator, and missing observations visible.

FIELD GUIDE

Agent systems / 4 MIN

Before you buy another Mac, measure the whole request.

An evaluation protocol for MLX, Ollama, LM Studio, and exo that keeps useful output, waiting time, context, and memory in the same decision.

FIELD GUIDE

Audience signals / 4 MIN

Your next audience may be asking the wrong name for your work.

Translate demonstrated work into problems people recognize. Build an evidence ledger before turning a plausible audience into an ideal customer.

FIELD GUIDE

Agent systems / 4 MIN

The link still works. The engineering advice may not.

A working source URL is only the first check. Track the version, scope, and decision behind advice that can become wrong while its links remain alive.

FIELD GUIDE

Agent systems / 3 MIN

Your agent does not need every tool in the room.

Separate the tool catalog from the model's working set. A practical design for discovery, schema loading, authorization, and context-budget tests.

FIELD GUIDE

Agent systems / 4 MIN

Your agent remembers the answer. Who tells it the answer changed?

A small memory contract for source versions, valid time, dependency checks, and corrections that reach the answers built on an old fact.

FIELD GUIDE

AI discovery / 4 MIN

A comparison page should help someone rule an option out.

Replace feature-count rankings with constraints, evidence classes, and a clear explanation of who should choose differently.

FIELD GUIDE

Applied craft / 3 MIN

Can an answer engine read your best work?

A discovery layer for creative studios and artist-led projects: retain the experience, make the work legible, and give every substantial piece a stable address.

FIELD GUIDE

Agent systems / 3 MIN

Before you add a graph, find the missing answer.

A decision worksheet for teams choosing between a simpler retrieval baseline and a graph-based memory system.

FIELD GUIDE

AI discovery / 3 MIN

SEO, AEO, GEO: what actually changes in the build?

A practical order of operations for teams making their work discoverable in search and AI answers. Start with access, then evidence, then measurement.

FIELD GUIDE

A USEFUL READ. A CLEAR NEXT STEP.