Eight Prompt Engineering Implementations [Updated]

In essence the discipline of Prompt Engineering is very simple and accessible. But as the LLM landscape develops, prompts are becoming programable and incorporated into more complex Generative AI structures.

Cobus Greyling
6 min readJul 31, 2023


I’m currently the Chief Evangelist @ HumanFirst. I explore & write about all things at the intersection of AI & language; ranging from LLMs, Chatbots, Voicebots, Development Frameworks, Data-Centric latent spaces & more.

Considering the image above, the implementation of Prompt Engineering within Large Language Model applications can be divided into eight broad categories:

  1. Static Prompts
  2. Prompt Composition
  3. Prompt Templates
  4. Contextual Prompts
  5. Prompt Chaining
  6. Prompt Pipelines (Retrieval Augmented Generations)
  7. Autonomous Agents
  8. Prompt Tuning / Soft Prompts

Static Prompts

The generative capabilities of LLMs are one of their key features which can be leveraged; with Prompt Engineering as the avenue with which data is presented and hence dictate the way the LLM executes on the data.

Prompts can follow a zero, single or few shot learning approach. The generative capabilities of LLMs are greatly enhanced by following a one-shot or few-shot learning approach by including example data in the prompt.

A powerful tool is to show LLMs via examples within a prompt how to go about and format output.

A static prompt is just that, plain text with no templating, injection or external information.

Prompt Templates

The next step from static prompts is prompt templating.

Prompt templating is where a static prompt is converted into a template with key values being replaced with placeholders. The placeholders are replaced with application values/variables at runtime.

Some refer to templating as entity injection or prompt injection.

In the template example below from DUST you can see the placeholders of ${EXAMPlES:question}, ${EXAMPlES:answer} and ${QUESTIONS:question} and these placeholders are replaced with values at runtime.

Prompt templating allows for prompts to the stored, re-used, shared, and programmed. Generative prompts can be incorporated into programs for programming, storage and re-use.

Prompt Composition

A next step is to have a library of prompt templates which are combined at run-time to create a more advanced prompt. As prompt composition add a level of flexibility and programability, it also introduces quite a bit of complexity.

The notebook in the article below illustrates how a contextual prompt is composed or constituted from different templates, each template has placeholders for variable injection. Hence part of a prompt can be reused.

Contextual Prompts

Even for LLMs, context is very important for increased accuracy and solving for hallucination. From the examples in the article below it is clear that a little context can go a long way in improving the accuracy of engineered prompts.

Contextual prompting negates LLM hallucination to a large extent.

Contextual prompting provides a frame of reference to the LLM when a response is generated.

Prompt Chaining

Prompt Chaining, also referred to as Large Language Model (LLM) Chaining, is the notion of creating a chain consisting of a series of model calls. This series of calls follow on each other with the output of one node in the chain serving as the input of the following.

Each chain node is intended to target small and well scoped sub-tasks, hence one or more LLMs is used to address multiple sequenced sub-components of a task.

In essence prompt chaining leverages a key principle in prompt engineering, known as chain of thought prompting.

The principle of Chain of Thought prompting is not only used in chaining, but also in Agents and Prompt Engineering.

Chain of thought prompting is the notion of decomposing a complex task into refined smaller tasks, building up to the final answer.

Prompt Pipelines

In Machine Learning a pipeline can be described as and end-to-end construct, which orchestrates a flow of events and data.

The pipeline is kicked-off or initiated by a trigger; and based on certain events and parameters, a flow is followed which results in an output.

In the case of a prompt pipeline, the flow is in most cases initiated by a user request. The request is directed to a specific prompt template.

Prompt Pipelines can also be described as an intelligent extension to prompt templates.

The variables or placeholders in the pre-defined prompt template are populated (also known as prompt injection) with the question from the user, and the knowledge to be searched from the knowledge store.

This process can be highly dynamic and autonomous, crafting the desired prompt with the given scenario containing contextual information for few-shot training.

Autonomous Agents

With LLM related operations there is an obvious need for automation. Currently this automation is in the form of what is called agents.

Prompt Chaining is the execution of a predetermined and set sequence of actions.

The attraction of Agents is that Agents do not follow a predetermined sequence of events. Agents can maintain a high level of autonomy.

Agents have access to a set of tools and any request which falls within the ambit of these tools can be addressed by the agent. The Execution pipeline lends autonomy to the Agent and a number of iterations might be required until the Agent reaches the Final Answer.

Prompt Tuning / Soft Prompts

Soft prompts are created during the process of prompt tuning.

Unlike hard prompts, soft prompts cannot be viewed and edited in text. Prompts consist of an embedding, a string of numbers, that derives knowledge from the larger model.

So for sure, a disadvantage is the lack of interpretability of soft prompts. The AI discovers prompts relevant for a specific task but can’t explain why it chose those embeddings. Like deep learning models themselves, soft prompts are opaque.

Soft prompts act as a substitute for additional training data. Researchers recently estimated that a good language classifier prompt is worth hundreds to thousands of extra data points.

⭐️ Follow me on LinkedIn for updates! ⭐️

I’m currently the Chief Evangelist @ HumanFirst. I explore & write about all things at the intersection of AI & language; ranging from LLMs, Chatbots, Voicebots, Development Frameworks, Data-Centric latent spaces & more.




Cobus Greyling

I explore and write about all things at the intersection of AI & language; LLMs/NLP/NLU, Chat/Voicebots, CCAI. www.cobusgreyling.com