ONLINEAGENT_OPS 2026.Q3 HOME ARTICLES CRAFT RECORD BLOG HUBS FAQ SEARCH
HOMETHE CRAFTContext Engineering
THE CRAFT · METHOD

Context Engineering

Prompting is now the small part of the job. What surrounds the prompt — the material, the history, the tools, the memory — is the large part. Four rules that hold as tooling turns over.

READ3 min
WORDS602
SECTIONS3
SOURCES2
TYPETESTED
CHECKED25 AUG 26
TL;DR — THE SHORT VERSION

Prompting is now the small part of the job. What surrounds the prompt — the material, the history, the tools, the memory — is the large part. Four rules that hold as tooling turns over.

  • A 2026 study of a widely deployed personal agent found that poisoning its persistent state raised average attack success from 24.6% to between 64% and 74%.

The category has moved. Prompting is now the small part of the job; what surrounds the prompt is the large part. This page is about that.

◈ THE SHIFT, STATED BY THE CATEGORY ITSELF

A 2026 industry guide puts it plainly: prompt engineering as a standalone discipline is shrinking, because frontier models are good enough that a decent prompt works most of the time. What moves the needle now is context — the documents, memory, tools and history surrounding the request.Taskade, "AI Prompt Generator" guide, Aug 2026 — an industry source, not a study

A 2024 workflow was: write a good prompt, paste it in. A 2026 workflow is: assemble the context, attach the tools, then ask.

What context actually is

Everything the model can see when it answers. Four things, and most people only manage the first:

  • The instruction — what you typed. The part everyone optimises.
  • The material — documents, files, pasted text, retrieved passages.
  • The history — what was said earlier in this conversation, and on some systems, earlier sessions.
  • The tools — what the model is permitted to call, and what those calls returned.

A model produces the most probable continuation given all four. Change any of them and you change the answer — which is why the same prompt gives different results in different places.

Four rules that hold

Position matters more than volume

Models attend unevenly across a long context. Material at the start and the end is weighted more heavily than material buried in the middle. If something must not be missed, do not put it in the middle of a long document.

The practical version: state the task at the top, put the reference material below it, and restate the constraint at the bottom.

More context is not better context

Filling a window with everything available is the most common mistake now that windows are large. Irrelevant material does not sit inertly — it competes.

The test: could a competent stranger do this task from exactly what you supplied, and nothing else? If yes, stop adding.

Retrieved is stronger than remembered

A model working from a document you supplied has far less room to invent than one working from training. This is the same mechanism described in why AI makes things up: rare facts have a floor, and supplying the fact removes the floor.

Pasting the source is worth more than any phrasing improvement.

Memory is an attack surface

Anything the system remembers between sessions can be edited between sessions. A 2026 study of a widely deployed personal agent found that poisoning its persistent state raised average attack success from 24.6% to between 64% and 74%.Wang et al., "Your Agent, Their Asset", arXiv 2604.04759

The rule that follows: never let fetched content become instruction. See guardrails.

What this changes about how you work

  • Stop collecting prompts. Start collecting context. A reusable brief with your constraints, your examples and your standards outlives every phrasing trick.
  • Front-load the specifics only you have. The model fills every gap with an average; your job is to leave fewer gaps.
  • Treat the window as a budget. Everything you add costs attention that something else needed.
  • Assume anything remembered can be wrong or hostile. Verify state before acting on it.
◈ WHY THIS PAGE IS SHORT ON TOOL NAMES

Retrieval stacks, memory layers and context platforms turn over constantly. The four rules above are properties of how attention works, not features of a product, which is why they will still hold when this year's tooling is gone.

◈ THE PAGE NOBODY ELSE WRITES

Every site in this category teaches you what to do. When not to use AI covers the other side — where these tools are worse than doing it yourself, and how to tell in advance.

It is the most differentiated page on this site, and it is the one people send to other people.

◈ IF YOU ARE CITING THIS

Cite the original source, not this page. Every figure here names the organisation that issued it and the date it was published — those are the citations worth carrying. This page is a signpost, not a primary source.

If you need to reference the collation itself — the comparison, the framing, or a correction logged here — the press page has the details. But if you are quoting a number, go to whoever measured it.

Or check it yourself. How to check the figures here names the feed or document behind each recurring source, and what to expect when your number differs from ours.

ABOUTMETHODVERIFYCORRECTIONSPRIVACYCONTACTINDEXAI PROMPT GENEER · CHECKED 22 AUG 2026