Engineering high-performance AI systems.
Deep-dive technical education for software engineers. Master retrieval, memory and distributed caching for production LLM applications through structured digital products you download the moment you buy.
Digital products
Showing all 23 products
Production AI Systems with Redis
A video course on caching, memory and state for LLM applications: cluster configuration, persistence strategies and failover for production workloads.
Vector Search & RAG In-Depth
The complete written guide to embeddings, hybrid retrieval and building retrieval-augmented generation pipelines that hold up under real traffic.
AI Engineering Reference Pack
Prompt patterns, evaluation checklists and Redis command references for engineers shipping AI features every week.
Redis Fundamentals for Engineers
Start from zero: keys, expiry, data types and the mental model that makes every later Redis decision obvious.
Redis Streams & Event-Driven AI
Build durable event pipelines with Streams: consumer groups, acknowledgement, replay and backpressure for inference workloads.
Semantic Caching for LLM Apps
Cut token spend by serving answers you already paid for: similarity thresholds, invalidation and safety rails for cached generations.
Evaluating RAG Systems
Build the test harness your retrieval pipeline is missing: golden sets, offline scoring and regression gates in CI.
Agent Architecture Patterns
Tool calling, planning loops, state machines and the failure modes that make autonomous agents unusable in production.
Memory Systems for AI Agents
Short-term context, episodic recall and long-term profiles: designing memory that improves answers instead of bloating prompts.
Prompt Engineering as Software
Version, test and review prompts like code: templates, fixtures, diffs and rollback for teams past the copy-paste stage.
Observability for LLM Applications
Traces, token accounting, latency budgets and quality signals — the dashboards you need before your first bad week.
Cutting Inference Cost
Routing, batching, distillation and caching: a systematic method for halving model spend without hurting output quality.
Operating Redis at Scale
Sharding, resharding, upgrades and incident response for clusters that carry production AI traffic.
Securing AI Applications
Prompt injection, data exfiltration, tool abuse and tenant isolation — threat modelling for systems that take instructions from text.
AI, GDPR and Data Governance
Lawful basis, retention, deletion and vendor due diligence for teams putting personal data anywhere near a model.
Building Embedding Pipelines
Ingestion, deduplication, incremental reindexing and backfills for corpora that change every day.
Hybrid Search & Ranking
Fuse BM25 and vector scores, apply business rules and tune ranking with feedback you already collect.
Streaming AI Interfaces
Server-sent events, partial rendering, cancellation and error recovery for interfaces that respond token by token.
Practical Fine-Tuning
When fine-tuning beats prompting, how to build the dataset, and how to evaluate the result before it reaches users.
Multi-Tenant AI Platforms
Namespacing, quotas, noisy-neighbour control and per-tenant cost attribution for AI features sold to many customers.
Data Modelling in Redis
Access-pattern-first schema design: key naming, secondary indexes, denormalisation and the trade-offs behind each choice.
Latency Engineering for AI
Tail latency, timeouts, hedging and budget allocation across retrieval, model and tool calls.
Shipping AI Features Safely
Feature flags, staged rollout, human review queues and kill switches for behaviour you can't fully predict.
Instant access
Download links are issued immediately after a successful checkout and emailed to you. Nothing is shipped physically.
Developer centric
Every course includes the full source code, deployment scripts and architectural diagrams used in the lessons.
14-day refund policy
If a product doesn't help your work, request a refund within 14 days of purchase and we'll return the full amount.
Voices from the field
“Finally an AI resource that goes past demo notebooks. The architecture course helped us fix our retrieval cache and cut inference spend substantially.”
“The reference pack is always open on my second monitor. The most useful technical asset I've bought this year for my platform team.”
Frequently asked questions
How do I receive the files?+
After checkout you are redirected to a secure download page, and an email with your permanent download links is sent to the address you used at checkout.
What currency are prices in?+
All prices are in pounds sterling (GBP) and include any tax that applies to your location. The total is confirmed before you pay.
Are team licences available?+
Yes. For teams of five or more we offer discounted multi-user licences. Contact us for a quote.
Is the content updated?+
Products are revised as the underlying tools change. Existing customers receive those updates at no extra cost.