Why Study with PlanetCert?
The Latest Questions
Practice questions and exam topics aligned with the current exam objectives.
Detailed Explanations
Go beyond the answer. Master the material with comprehensive learning and professional explanations for every concept.
AI-Powered Insights
Personalized preparation guidance that adapts to your performance and identifies weak spots automatically.
Exam Information
Official specifications published by IBM
Exam Format
90 min
62
71%
Associate
Registration
$200 USD
Pearson VUE or online proctoring
English
Validity
Lifetime (no expiration)
Not required - IBM Associate certifications do not expire
C1000-185 Exam Topics and Domains
C1000-185 is organized into 6 weighted domains.
1
Analyze and Design a Generative AI Solution
15%
Understand the five capabilities of GenAI/LLMs
- Summarization
- Classification
- Generation (including Code and Translation)
- Extraction
- Q&A
- Define and describe the five key capabilities of generative AI and large language models (LLMs)
- Review case studies or examples demonstrating each capability
- Evaluate the impact of these capabilities in various industries
- Discuss potential future developments in LLM capabilities
Articulate the components in Gen AI Patterns
- Mixture of experts (MoE)
- Variational Auto Encoders (VAE)
- Transformer based models
- Reasoning models
- Identify common patterns used in generative AI solutions
- Describe the components that constitute these patterns (e.g., input data processing, model training, output generation)
- Analyze real-world examples to illustrate how these patterns are applied
- Create a diagrammatic representation of various generative AI patterns
Understand the limitations of GenAI/LLMs
- List the technical and ethical limitations of generative AI and LLMs
- Discuss scenarios where generative AI may produce biased or incorrect outputs
- Explore strategies to mitigate these limitations in practical applications
- Evaluate the risks associated with the deployment of generative AI in sensitive or critical applications
Understand use cases and identify Gen AI application opportunities
- Study various industry sectors to identify potential use cases for generative AI
- Conduct needs analysis to determine how generative AI can address specific business problems
- Propose generative AI solutions for identified use cases
- Prepare feasibility reports for the proposed solutions
Understand how to choose the appropriate model for a use case
- Model selection based on parameter size
- Chat vs instruct
- IBM Granite models
- Billing classes
- Analyze the requirements of a given use case
- Determine criteria for selecting an appropriate model based on performance, efficiency, cost, and ethical considerations
- Simulate decision-making processes to select the optimal model for a use case
Articulate the optimal model architecture based on a use case
Agentic architectures
- Define model architecture and its significance in AI solutions
- Examine various model architectures and their components
- Match model architectures with specific use cases based on technical requirements
Identify and apply various tools and techniques like AI agents, RAG, LangChain, etc.
- RAG pattern
- Basic search
- LangChain
- AI agents
- Understand the RAG Pattern (introduction to the RAG pattern and basic search
- demonstrate the RAG pattern with LangChain)
- AI agents
Understand security risks associated with LLMs, prompt engineering, prompt, and data
- Input risks: Data Bias, Data Poisoning, Data Curation and Downstream Retraining, Data Privacy, Prompt Injection, Prompt Leaking
- Output risks: Output and Decision Bias, Revealing Confidential or Personal Information, Toxic Output, Spreading misinformation and toxicity, Harmful code generation
- Guardian models
- Understand the security risks associated with inputs
- Understand the security risks associated with output
- Understand the security and privacy for foundation models
- Guardian models
2
Prompt Engineering
16%
Differentiate between zero-shot and few-shot prompting
- Introduction to zero-shot prompting
- Introduction to few-shot prompting
- Try a zero-shot prompt sample
- Try a few-shot prompt sample
Design prompts based on use case
- Choose the right model for a use case
- Try to converse with a model for a chat use case
- Try to converse with a model to translate from one language to another
Generate prompt templates
- Introduction to prompt templates
- Evaluate prompt templates
- Create environment templates
- Deploy prompt templates
- Track prompt templates
Determine the best model parameters for each GenAI prompt
- Decoding
- Greedy decoding
- Sampling decoding
- Introduction to model parameters
- Understanding the random seed
- Understanding the repetition penalty
- Understanding the stopping criteria
- Understanding the stop sequences
- Understanding the minimum and maximum tokens
Describe the benefits of using prompt variables
- Articulate what a prompt variable is
- Identify optimal static prompt text to replace with a variable
- Summarize the value of reusable prompts
Describe the benefits of Prompt Lab
- Chat
- Structured
- Freeform
- Articulate the prompt editing options
- Demonstrate how to build reusable prompts
- Describe example input prompts and their use
Articulate hyper parameter tuning
- Greedy decoding
- Sampling decoding
- Temperature
- Top K
- Top P
- Random seed
- Repetition penalty
- Stop sequences
- Minimum and maximum tokens
- Model generation time limit
- Articulate the decoding process at a high level
- Describe the sampling decoding parameters
- Articulate stopping criteria and examples
Articulate model risks
- Hallucinations
- PII filter
- HAP filter
- Bias
- Describe hallucinations in model output (underlying causes
- techniques for avoiding)
- Articulate the risks associated with personal information (identify PII
- techniques for excluding
- PII filter)
- Hate speech, abuse, and profanity (techniques for reducing risk
- HAP filter)
- Bias (underlying cause of bias in outputs
- techniques for reducing bias)
- Debate the risks of data bias and poisoning
3
Fine-Tuning
31%
LoRA
Understand the difference between hard and soft prompts
- Differentiate between hard prompts and soft prompts (designed by humans or AI
- readability
- explainability)
- Articulate how soft prompts are generated
- Debate the benefits and drawbacks of soft prompts (performance
- simplicity
- interpretability
Reconstruct prompts to reduce the cost of using GenAI models
- Stop sequences
- Min/max token limits
- Manage the token usage of each prompt template and model
- Detect inefficient prompt techniques
- Design cost-effective prompt templates
- Employ model parameters to reduce the generation cost
Plan for Data elements for application usage
- Add data to a watsonx.ai project for tuning
- Inspect and validate data elements using Data Refinery
Articulate model quantization techniques
- Tradeoffs: reduce precision, reduce computational costs
- Quantization techniques
Understand what quantization is in the context of LLMs
Prepare the dataset for training
- Taxonomy tree-based curation
- LAB (Large-scale Alignment for chatBots) methodology
- Summarize the purpose of taxonomy tree-based curation
- Generate synthetic data using InstructLab
Customize LLMs with InstructLab
- Taxonomy driven data curation
- Large scale synthetic data generation
- Iterative, large scale alignment tuning (knowledge tuning
- skill tuning)
- Describe the components of InstructLab
- Articulate the InstructLab workflow
Generate synthetic data using the User Interface
- Kolmogorov-Smirnov
- Anderson-Darling
- Privacy budget
- Privacy leakage probability
- Random seed
- Describe the two options supported (leverage your existing data
- create from your custom data schema)
- Understand limitations on importing existing data sources and size limitations
- Understand anonymization of imported data
- Understand the two algorithms for mimicking existing data
- Understand differential privacy concepts and settings
- Understand sizing requirements for the synthetic data generator
4
Retrieval-Augmented Generation (RAG)
17%
Describe embeddings in the context of GenAI
- IBM embedding models
- Third party embedding models
- Understand concepts of text embeddings
- Describe different embedding models
Generate vector embeddings utilizing models
- Credentials
- Project ID
- Deployment ID
- Purpose built vector databases
- Vector extensions to popular databases
- Perform converting text to embedding vectors
- Describe prerequisites for the embedding API
- Understand the choices and capabilities of vector databases
Describe when to use a vector database
- Vector databases (embedded
- static)
- Watson Discovery
- GitHub code retrieval API
- watsonx Discovery
- Understand the concept of a retriever
- Describe different types of retrievers
- Understand the capabilities of retrievers
- Understand use case driven selection of a retriever
Develop using libraries
- LangChain and watsonx LLM
- LangChain, Watson ML and ElasticSearch
- LangChain, SingleStore
- LlamaIndex
- Understand the RAG pattern
- Understand implementation details of a RAG pattern
- Understand chunking/text splitting
- Agentic RAG
- AutoRAG
5
Deployment
13%
Plan for a deployment based on client needs
- Model performance
- Evaluate inferences
- Explain outcomes from prompts
- Define the deployment lifecycle of a prompt template
- Manage changes to prompt templates in applications
- Understand roles involved with deploying AI Assets
- Understand the need around AI Governance
Deploy AI Assets
- Govern lifecycle (dev/evaluation/production)
- Separate endpoints for applications to call
- Benefits of a deployment space
- Benefits when deploying a prompt template
- Changes to the application when using a deployment space
Deploy a custom model
- Understand requirements of watsonx and the foundation model
- Application access to a custom model
Plan out deployment of prompts for versioning
- RAG
- Summarization
- Q&A
- AI pipelines to update repository
- Manage data in corpus
- Adjusting text chunk size
- Understand the options between managed Software as a Service or Software
- Deployment choices based on architectural pattern
- Corpus of data repository
- Identify endpoint security and stability
- Code generation within Prompt Lab
High level architecture for deployment options
- Version using deployment spaces
- Changes to applications on a prompt version change
- Testing a new prompt template version
- Model gateway
6
Integration with Model Orchestration
8%
Integrate watsonx.ai with Other Services/Manage APIs and SDKs
- Watson Assistant
- Watson Discovery
- watsonx.governance
- API keys/credentials
- Error and exception handling
- Connect watsonx.ai to other IBM Cloud services, such as Watson Assistant for chatbot development or Watson Discovery for document understanding, to build end-to-end AI solutions
- Leverage watsonx.ai's APIs and SDKs to integrate generative AI models with external applications, platforms, or custom workflows, including utilizing LangChain for complex chain creation and management
Orchestrate AI Workflows
- Agentic RAG
- Scheduling
- Conditional logic branching
- Workflow logs and execution details
- Design and implement workflows utilizing watsonx.ai that combine multiple tasks, including LangChain-based chains
- Utilize orchestration tools to automate the execution of workflows, including scheduling, dependency management, and error handling
- Monitor and troubleshoot workflow execution, identifying bottlenecks, failures, or performance issues
Understand real-world Integration Scenarios
- Model Context Protocol
- High-level architecture diagram
- End-to-end testing
- Given a business use case, design a comprehensive solution that integrates watsonx.ai with relevant data sources, other IBM Cloud services, and external systems
- Implement the designed solution, leveraging the appropriate watsonx components and tools
- Test and validate the integration, ensuring seamless data flow, reliable communication, and expected functionality
Develop LLM based applications with LangChain
- Chains
- Agents
- Tools
- Memory
- Modularity
- Reusability
- Extensibility
- Explain the core concepts of LangChain (chains, agents, tools, memory) and their role in building complex conversational AI and generative AI applications
- Demonstrate the ability to create and customize LangChain chains, incorporating various components like LLMs, prompt templates, and external data sources
- Design and implement LangChain agents that can interact with the environment, make decisions, and take actions based on model outputs and external information
How do I earn this certification?
Passing C1000-185 earns the IBM Certified watsonx Generative AI Engineer - Associate certification. It sits in the Data, Analytics, and AI track.
Next Level Options
TBD - Future Professional-level watsonx certifications IBM may release Professional-level GenAI certifications in the future
Alternative Paths
- C1000-161 - IBM Instana Observability v1.0.277 Administrator - ProfessionalComplementary AI operations and monitoring skills
- C1000-168 - IBM Cloud Pak for Data v4.7 AdministratorEnterprise data platform administration for AI workloads
- C1000-150 - IBM Cloud Pak for Integration v2021.4 AdministrationIntegration skills for AI solution deployment
Practice with Precision
The PlanetCert Simulator mirrors the real exam environment with authentic questions and timed pressure.
How to study for this exam?
The most effective way to prepare for C1000-185 is by using the PlanetCert Simulator to practice questions and review detailed explanations.
What's changed on this exam?
Current Status
- ACTIVE
- Last content update: 2024-11-16
- Announcement date: 2024
Updates
- InstructLab 0.10.0 Major component of Fine-Tuning domain (31% weight) • Release date: 2024-10-15
- watsonx.ai Prompt Lab Latest Core tool for Prompt Engineering domain (16% weight) • Release date: 2024-09-01
- LangChain 0.2.0+ Used in Integration and RAG domains (25% combined weight) • Release date: 2024-08-01
Who should take this exam?
- 6-12 months hands-on experience with watsonx.ai
- Python programming knowledge
- Data analysis experience
- Data science fundamentals