Cobus Greyling
Author

Cobus Greyling

Cobus Greyling is passionate about exploring the intersection of AI and language. From Language Models, AI Agents to Agentic Applications, Development Frameworks & Data-Centric Productivity Tools, I share insights and ideas on how these technologies are shaping the future.

All Brochures

Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
Published Jun 12, 2025
4 Min Read
Read

AI agents, RAG, and agentic retrieval for enterprises

AI agents, RAG, and agentic retrieval for enterprises
Published Jun 25, 2025
4 Min Read
Read

How MCP enables smarter, adaptive AI agent integration

How MCP enables smarter, adaptive AI agent integration
Published Jun 17, 2025
4 Min Read
Read

Agentic RAG is the next step in smarter enterprise AI

Agentic RAG is the next step in smarter enterprise AI
Published May 09, 2024
4 Min Read
Read

Putting AI To work

Putting AI To work
Published May 10, 2024
4 Min Read
Read

The case for an AI productivity suite

The case for an AI productivity suite
Published May 14, 2024
4 Min Read
Read

Rapid development of intelligent generative AI APIs

Rapid development of intelligent generative AI APIs
Published May 17, 2024
4 Min Read
Read

The large language model landscape — Version 5

The large language model landscape — Version 5
Published May 22, 2024
4 Min Read
Read

Three considerations for private open-source LLM instances

Three considerations for private open-source LLM instances
Published May 21, 2024
4 Min Read
Read

A short history of chatbots

A short history of chatbots
Published May 28, 2024
4 Min Read
Read

TinyLlama is an open-source small language model

TinyLlama is an open-source small language model
Published Jun 04, 2024
4 Min Read
Read

Five levels of AI agents

Five levels of AI agents
Published Jun 06, 2024
4 Min Read
Read

Data design for fine-tuning LLM long context windows

Data design for fine-tuning LLM long context windows
Published Jun 03, 2024
4 Min Read
Read

LLM agents vs. chains: Differences & when to use each

LLM agents vs. chains: Differences & when to use each
Published Jun 14, 2024
4 Min Read
Read

Teaching LLMs To say, “I don’t know”

Teaching LLMs To say, “I don’t know”
Published Jun 10, 2024
4 Min Read
Read

LLM performance over time & LLM task contamination

LLM performance over time & LLM task contamination
Published Jun 12, 2024
4 Min Read
Read

Improving text embeddings with LLM generated synthetic data

Improving text embeddings with LLM generated synthetic data
Published Jun 16, 2024
4 Min Read
Read

Active prompting with chain-of-thought for large language models

Active prompting with chain-of-thought for large language models
Published Jun 19, 2024
4 Min Read
Read

Prompt pipelines

Prompt pipelines
Published Jul 01, 2024
4 Min Read
Read

Small & medium-sized enterprises enter the conversational AI arena

Small & medium-sized enterprises enter the conversational AI arena
Published Jul 03, 2024
4 Min Read
Read

Meta taxonomy of large language model correction & refinement

Meta taxonomy of large language model correction & refinement
Published Jul 07, 2024
4 Min Read
Read

Large language model (LLM) SWOT analysis

Large language model (LLM) SWOT analysis
Published Jul 04, 2024
4 Min Read
Read

Retrieval-Augmented generation (RAG) vs LLM fine-tuning

Retrieval-Augmented generation (RAG) vs LLM fine-tuning
Published Jul 10, 2024
4 Min Read
Read

Visualise & discover RAG data

Visualise & discover RAG data
Published Jul 12, 2024
4 Min Read
Read

The new corner store is digital

The new corner store is digital
Published Jul 12, 2024
4 Min Read
Read

AI-Assisted UI design with AI for service

AI-Assisted UI design with AI for service
Published Jul 12, 2024
4 Min Read
Read

Automate your contact center faster with AI for service

Automate your contact center faster with AI for service
Published Jul 12, 2024
4 Min Read
Read

Automation and orchestration with AI for service

Automation and orchestration with AI for service
Published Jul 12, 2024
4 Min Read
Read

Introducing effortless no-code conversational UI onboarding

Introducing effortless no-code conversational UI onboarding
Published Jul 12, 2024
4 Min Read
Read

The corner store can have a chatbot

The corner store can have a chatbot
Published Jul 12, 2024
4 Min Read
Read

Helping SMBs build conversational AI

Helping SMBs build conversational AI
Published Jul 12, 2024
4 Min Read
Read

Making conversational AI accessible for small and medium organisations

Making conversational AI accessible for small and medium organisations
Published Jul 26, 2024
4 Min Read
Read

No-code deployment and orchestration of open-sourced foundation models

No-code deployment and orchestration of open-sourced foundation models
Published Jul 22, 2024
4 Min Read
Read

Prompt-RAG: Vector embedding free retrieval-augmented generation

Prompt-RAG: Vector embedding free retrieval-augmented generation
Published Aug 12, 2024
4 Min Read
Read

Corrective RAG: Boosting response quality

Corrective RAG: Boosting response quality
Published Aug 14, 2024
4 Min Read
Read

Adding noise improves RAG performance

Adding noise improves RAG performance
Published Aug 29, 2024
4 Min Read
Read

The case For small language models

The case For small language models
Published Aug 30, 2024
4 Min Read
Read

The shifting vocabulary of AI

The shifting vocabulary of AI
Published Sep 05, 2024
4 Min Read
Read

Fine-Tuning or RAG?

Fine-Tuning or RAG?
Published Sep 19, 2024
4 Min Read
Read

LLM drift, prompt drift & cascading

LLM drift, prompt drift & cascading
Published Sep 23, 2024
4 Min Read
Read

The evolution of grounding & planning In AI agents

The evolution of grounding & planning In AI agents
Published Sep 20, 2024
4 Min Read
Read

Beyond LLMs: The shift to smaller, smarter AI models

Beyond LLMs: The shift to smaller, smarter AI models
Published Sep 26, 2024
4 Min Read
Read

Please stop saying long context windows will replace RAG

Please stop saying long context windows will replace RAG
Published Oct 14, 2024
4 Min Read
Read

Small language models: Purpose & potential

Small language models: Purpose & potential
Published Oct 04, 2024
4 Min Read
Read

Self-Reflective Retrieval-Augmented Generation (SELF-RAG)

Self-Reflective Retrieval-Augmented Generation (SELF-RAG)
Published Sep 28, 2024
4 Min Read
Read

Prompt-RAG

Prompt-RAG
Published Oct 15, 2024
4 Min Read
Read

Evaluating LLM voting under scaling laws

Evaluating LLM voting under scaling laws
Published Oct 21, 2024
4 Min Read
Read

RAT — Retrieval Augmented Thoughts

RAT — Retrieval Augmented Thoughts
Published Oct 16, 2024
4 Min Read
Read

Chain-of-Instructions (CoI) fine-tuning

Chain-of-Instructions (CoI) fine-tuning
Published Oct 27, 2024
4 Min Read
Read

DRAGIN: Dynamic RAG based on real-time information needs of LLMs

DRAGIN: Dynamic RAG based on real-time information needs of LLMs
Published Oct 24, 2024
4 Min Read
Read

A study comparing RAG & Fine-Tuning for knowledge base use-cases

A study comparing RAG & Fine-Tuning for knowledge base use-cases
Published Oct 30, 2024
4 Min Read
Read

Retrieval Augmented Fine-Tuning (RAFT)

Retrieval Augmented Fine-Tuning (RAFT)
Published Oct 30, 2024
4 Min Read
Read

Large language models excel at In-Context Learning (ICL)

Large language models excel at In-Context Learning (ICL)
Published Nov 11, 2024
4 Min Read
Read

FIT-RAG

FIT-RAG
Published Nov 01, 2024
4 Min Read
Read

Adaptive-RAG

Adaptive-RAG
Published Nov 15, 2024
4 Min Read
Read

FaaF: Facts as a function for evaluating RAG

FaaF: Facts as a function for evaluating RAG
Published Nov 18, 2024
4 Min Read
Read

Agentic Search-Augmented Factuality Evaluator (SAFE) for LLMs

Agentic Search-Augmented Factuality Evaluator (SAFE) for LLMs
Published Nov 03, 2024
4 Min Read
Read

Challenges In adopting RAG solutions

Challenges In adopting RAG solutions
Published Nov 14, 2024
4 Min Read
Read

Disambiguation: Dynamic context for effective RAG question suggestions

Disambiguation: Dynamic context for effective RAG question suggestions
Published Nov 21, 2024
4 Min Read
Read

Data design for fine-tuning to improve small language model behaviour

Data design for fine-tuning to improve small language model behaviour
Published Nov 21, 2024
4 Min Read
Read

Improve conversational UIs using social intelligence

Improve conversational UIs using social intelligence
Published Nov 25, 2024
4 Min Read
Read

Can small errors disrupt RAG pipelines?

Can small errors disrupt RAG pipelines?
Published Jan 06, 2025
4 Min Read
Read

DialogGPT

DialogGPT
Published Jan 07, 2025
4 Min Read
Read

How should large language models be evaluated?

How should large language models be evaluated?
Published Jan 08, 2025
4 Min Read
Read

OPRO explained: Smarter prompt design

OPRO explained: Smarter prompt design
Published Jan 10, 2025
4 Min Read
Read

LLM alignment, hallucination & misinformation

LLM alignment, hallucination & misinformation
Published Feb 10, 2025
4 Min Read
Read

As-Needed decomposition & planning using large language models ( ADaPT)

As-Needed decomposition & planning using large language models ( ADaPT)
Published Jan 13, 2025
4 Min Read
Read

Evaluating LLMs: What, where, and how

Evaluating LLMs: What, where, and how
Published Jan 17, 2025
4 Min Read
Read

Chain of Empathy Prompting (CoE)

Chain of Empathy Prompting (CoE)
Published Jan 15, 2025
4 Min Read
Read

What are LLMs good at & when can LLMs fail?

What are LLMs good at & when can LLMs fail?
Published Jan 20, 2025
4 Min Read
Read

Are emergent abilities In LLMs inherent or merely In-Context Learning?

Are emergent abilities In LLMs inherent or merely In-Context Learning?
Published Jan 22, 2025
4 Min Read
Read

LLM hallucination index

LLM hallucination index
Published Jan 24, 2025
4 Min Read
Read

Knowledge-Driven Chain-of-Thought (KD-CoT)

Knowledge-Driven Chain-of-Thought (KD-CoT)
Published Jan 27, 2025
4 Min Read
Read

Chain-Of-Note (CoN) retrieval for LLMs

Chain-Of-Note (CoN) retrieval for LLMs
Published Jan 31, 2025
4 Min Read
Read

Open ai structured JSON output with adherence

Open ai structured JSON output with adherence
Published Jan 30, 2025
4 Min Read
Read

The Chain-Of-X phenomenon In LLM prompting

The Chain-Of-X phenomenon In LLM prompting
Published Feb 05, 2025
4 Min Read
Read

The anatomy Of Chain-Of-Thought prompting (CoT)

The anatomy Of Chain-Of-Thought prompting (CoT)
Published Feb 03, 2025
4 Min Read
Read

Contrastive Chain-Of-Thought prompting

Contrastive Chain-Of-Thought prompting
Published Feb 07, 2025
4 Min Read
Read

Self-Consistency for Chain-Of-Thought prompting

Self-Consistency for Chain-Of-Thought prompting
Published Feb 12, 2025
4 Min Read
Read

Generative AI trends to watch in 2025 & beyond

Generative AI trends to watch in 2025 & beyond
Published Feb 14, 2025
4 Min Read
Read

Data delivery to LLMs

Data delivery to LLMs
Published Feb 16, 2025
4 Min Read
Read

Large language model programs

Large language model programs
Published Feb 18, 2025
4 Min Read
Read

What is multi-task language understanding (MMLU)

What is multi-task language understanding (MMLU)
Published Feb 20, 2025
4 Min Read
Read

Random CoT for better LLM reasoning

Random CoT for better LLM reasoning
Published Feb 25, 2025
4 Min Read
Read

Large language model hallucination mitigation techniques

Large language model hallucination mitigation techniques
Published Mar 03, 2025
4 Min Read
Read

Validating low-confidence LLM generation

Validating low-confidence LLM generation
Published Mar 14, 2025
4 Min Read
Read

Considering large language model reasoning step length

Considering large language model reasoning step length
Published Mar 12, 2025
4 Min Read
Read

Chain Of Natural Language Inference (CoNLI)

Chain Of Natural Language Inference (CoNLI)
Published Mar 17, 2025
4 Min Read
Read

Meta taxonomy of LLM correction & refinement

Meta taxonomy of LLM correction & refinement
Published Mar 24, 2025
4 Min Read
Read

Understanding LLM user experience & expectation

Understanding LLM user experience & expectation
Published Mar 27, 2025
4 Min Read
Read

Concise Chain-of-Thought (CCoT) prompting

Concise Chain-of-Thought (CCoT) prompting
Published Mar 31, 2025
4 Min Read
Read

UniMS-RAG: Unified multi-source RAG for personalised dialogue

UniMS-RAG: Unified multi-source RAG for personalised dialogue
Published Mar 28, 2025
4 Min Read
Read

Chain-of-Symbol prompting (CoS) for LLMs

Chain-of-Symbol prompting (CoS) for LLMs
Published Apr 07, 2025
4 Min Read
Read

A benchmark for verifying chain-of-thought

A benchmark for verifying chain-of-thought
Published Apr 02, 2025
4 Min Read
Read

Seven RAG engineering failure points

Seven RAG engineering failure points
Published Apr 08, 2025
4 Min Read
Read

Designing conversational UIs that match user intent

Designing conversational UIs that match user intent
Published Apr 09, 2025
4 Min Read
Read

Comparing human, LLM & LLM-RAG responses

Comparing human, LLM & LLM-RAG responses
Published Apr 10, 2025
4 Min Read
Read

Beyond Chain-of-Thought LLM reasoning

Beyond Chain-of-Thought LLM reasoning
Published Apr 14, 2025
4 Min Read
Read

T-RAG = RAG + fine-tuning + entity detection

T-RAG = RAG + fine-tuning + entity detection
Published Apr 17, 2025
4 Min Read
Read

Demonstrate, search, predict (DSP) for LLMs

Demonstrate, search, predict (DSP) for LLMs
Published Apr 23, 2025
4 Min Read
Read

Proxy Fine-Tuning LLMs

Proxy Fine-Tuning LLMs