Skip to content
[ 02 ]Depth

Ten layers down.

The name is a promise about where we are willing to go. Below is the whole stack — surface to silicon — and what the work looks like at each level.

Layers
10
Surface
Applications
Floor
Hardware
[02The descent]
Layer 01Product surfaces & UX

Applications

The part everyone sees, and the only part most vendors touch. Interfaces that make a probabilistic system feel dependable — streaming, citations, graceful failure, and the affordances that let a person stay in control.

  • Streaming UX
  • Human-in-the-loop
  • Trust & citations
  • Latency budgets
Depth
010%
Layer 02Orchestration, tools, memory

Agents

Control flow for models. Where a task gets decomposed, which tool is reached for, what gets remembered, and when the loop must stop. Most agent failures are architecture failures, not model failures.

  • Tool contracts
  • State & memory
  • Planning loops
  • Failure containment
Depth
020%
Layer 03Retrieval, chunking, reranking

RAG

Getting the right context in front of the model at the right moment. Chunking strategy, hybrid retrieval, reranking and freshness — the difference between a demo that impresses and a system that answers.

  • Hybrid retrieval
  • Chunk strategy
  • Rerankers
  • Grounding evals
Depth
030%
Layer 04Selection & architecture

Models

Which model, and why. Capability mapped against cost, latency, licence and control — with an honest read on where a frontier API earns its price and where a smaller open model wins outright.

  • Capability mapping
  • Open vs. frontier
  • Licensing
  • Eval harnesses
Depth
040%
Layer 05Data pipelines & runs

Training

Data is the model. Collection, cleaning, deduplication, synthetic augmentation and the run itself — instrumented so that a result can be reproduced rather than retold.

  • Data curation
  • Synthetic data
  • Run instrumentation
  • Reproducibility
Depth
050%
Layer 06LoRA, preference tuning

Fine-tuning

Teaching a model your domain instead of describing it in a prompt every time. Adapters, preference optimisation and distillation that trade a general model for a specific one that is smaller, faster and yours.

  • LoRA / QLoRA
  • DPO & preference
  • Distillation
  • Adapter routing
Depth
060%
Layer 07Latency & cost engineering

Inference

Where the bill lives. Quantisation, speculative decoding, KV-cache strategy and prompt economics — the layer where a 4× cost reduction is normal and nobody is looking.

  • Quantisation
  • Speculative decoding
  • KV-cache
  • Token economics
Depth
070%
Layer 08Batching, routing, scale

Serving

Turning a model into a service. Continuous batching, request routing, autoscaling and back-pressure so that p99 stays flat when traffic does not.

  • Continuous batching
  • Model routing
  • Autoscaling
  • p99 discipline
Depth
080%
Layer 09Kernels, memory, utilization

GPU Optimization

Down where the silicon is. Kernel selection, memory layout, occupancy and utilisation — reading a profiler instead of guessing, and buying back capacity you already own.

  • Kernel profiling
  • Memory layout
  • Occupancy
  • Utilisation
Depth
090%
Layer 10Topology & procurement

Hardware

The floor of the stack. Accelerator choice, interconnect topology, capacity planning and procurement — decisions with an eighteen-month shadow, made once and lived with.

  • Accelerator choice
  • Interconnect
  • Capacity planning
  • Procurement
Depth
100%
[Why it matters]

The same symptom, two different answers.

Surface-level work treats the layer it can reach. Depth means treating the layer the problem is actually in.

Next step

Which layer is yours?

Bring the symptom. We'll locate it in the stack, tell you what it would take to fix, and be honest about whether it's worth fixing.

Typical reply within one working day.