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.
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.
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.
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.