1 min read
Memory Consolidation for AI Agents: From Short-Term to Long-Term
1. Set appropriate thresholds : Not everything needs to be remembered 2. Consolidate regularly : Don't let short term memory overflow 3. Abstract…
Blog
Thoughts on data engineering, cloud architecture, and technology. 2205 articles and counting.
Showing 24 of 2205 posts — page 30 of 92
1 min read
Procedural Memory for AI Agents: Learning How To Do Things
Procedural memory captures: Action sequences : Steps to accomplish tasks Conditions : When procedures apply Parameters : Variables in the process Success…
1 min read
Semantic Memory for AI Agents: Knowledge Representation
Aspect Semantic Memory Episodic Memory Content Facts, concepts, relationships Events, experiences Context Context free Time and place specific Example…
1 min read
Episodic Memory for AI Agents: Learning from Experiences
Unlike semantic memory (facts) or procedural memory (how to), episodic memory captures: Events : What happened Context : When and where Outcomes : Results…
1 min read
Long-Term Agent Memory: Persistent Knowledge Storage
1. Categorize memories : Different types need different handling 2. Extract automatically : Don't rely on explicit save commands 3. Maintain regularly :…
2 min read
Short-Term Agent Memory: Context Window Management
Sounds like a lot, but it fills up quickly with conversation history, system prompts, tool outputs, and retrieved documents.
1 min read
Agent Memory Patterns: Beyond Simple Context
Periodically consolidate memories for efficiency: 1. Layer your memory : Different types for different purposes 2. Manage capacity : Always have eviction…
1 min read
Human-in-the-Loop AI Agents: Building Trust Through Oversight
Irreversible actions : Deletions, payments, deployments High cost operations : Expensive API calls, resource provisioning Sensitive data : PII handling,…
1 min read
Cycles in Agent Graphs: Iterative Refinement Patterns
Real tasks often require iteration: Refinement : Improve output quality through multiple passes Retry : Handle failures with backoff strategies Search :…
1 min read
Conditional Edges in LangGraph: Dynamic Agent Flows
Route based on multiple state attributes: Sometimes you don't know all routes ahead of time: Multiple decision points in sequence: Route with randomization…
1 min read
Stateful AI Agents: Managing Context and Memory
All require state management beyond simple request-response.
1 min read
Graph-Based AI Agents: Design Patterns and Architecture
Think of your agent as a state machine: Nodes : Processing steps (functions that transform state) Edges : Transitions between steps State : Accumulated…
1 min read
LangGraph Introduction: Building Stateful AI Agents
LangGraph provides these capabilities through a graph-based execution model.
1 min read
LangChain Updates: What's New in July 2024
LangChain 0.2.x Stability LCEL (LangChain Expression Language) Maturity Azure AI Search Vector Store
1 min read
Semantic Router: Intent-Based LLM Routing
Semantic routing compares the meaning of a user's query against a set of example utterances. When the query is semantically similar to examples for a…
1 min read
Latency-Based LLM Routing: Real-Time AI Applications
Latency has multiple components: 1. Network latency : Request travel time 2. Queue time : Waiting for processing 3. Time to first token (TTFT) : Initial…
4 min read
Quality-Based LLM Routing: Maximizing Output Quality
Quality isn't one dimensional. Consider: Accuracy : Factual correctness Completeness : Covering all aspects Coherence : Logical flow and consistency…
1 min read
Cost-Based LLM Routing: Optimizing AI Spend
The difference is dramatic. A 1000-token task costs $0.02 with GPT-4o but $0.0002 with GPT-4o-mini.
5 min read
LLM Routing Strategies for Production Systems
The simplest approach: fixed rules based on task type. Pros: Simple, predictable, easy to debug Cons: Doesn't adapt, requires manual tuning
1 min read
Multi-Model Orchestration: Using Multiple LLMs Effectively
Different tasks need different capability levels. Using GPT-4o for simple classifications wastes money.
2 min read
Anthropic Models Coming to Azure: What It Means
For organizations already invested in Azure, this eliminates the complexity of managing another vendor relationship.
3 min read
Claude Artifacts: Interactive AI-Generated Content
The key difference from regular responses: artifacts persist, can be modified, and are rendered appropriately for their type.
2 min read
Claude 3.5 Sonnet vs GPT-4o: A Technical Comparison
With Claude 3.5 Sonnet and GPT-4o both available, choosing the right model for your application requires understanding their differences. I've been testing…
2 min read
Claude 3.5 Sonnet: Anthropic's New Benchmark in AI
Performance That Competes Claude 3.5 Sonnet outperforms Claude 3 Opus on most benchmarks while being significantly faster and cheaper. It's positioned as a…