bradshaw.cloud: Audio Edition

Compression is the family. Quantisation is one cousin. The techniques that shrink language models for self-hosting — what they do, what they cost in quality, and which ones you actually reach for.

Read the written version, with its diagrams and tables: https://bradshaw.cloud/strategy/model-compression/

Personal views, not those of my employer.

The most capable AI models available — and when a frontier model earns its cost vs when a small specialised model wins.

Read the written version, with its diagrams and tables: https://bradshaw.cloud/strategy/frontier-models/

Personal views, not those of my employer.

How NVIDIA's AI Grid reference architecture distributes AI inference across edge locations — and why it changes the economics of running AI in production.

Read the written version, with its diagrams and tables: https://bradshaw.cloud/strategy/ai-grid/

Personal views, not those of my employer.

From cloud chaos to cost control — the framework for regaining economic independence from hyperscaler lock-in.

Read the written version, with its diagrams and tables: https://bradshaw.cloud/strategy/cloud-sovereignty/

Personal views, not those of my employer.

The streaming industry solved access; now it needs to solve experience. A framework for the shift from content wars to experience wars — and what comes next.

Read the written version, with its diagrams and tables: https://bradshaw.cloud/strategy/content-wars-to-experience-wars/

Personal views, not those of my employer.

Why the build-vs-buy decision is never binary, how to think about total cost of ownership, and the hybrid approach that actually works in practice.

Read the written version, with its diagrams and tables: https://bradshaw.cloud/writing/build-vs-buy-framework/

Personal views, not those of my employer.

The decision framework every CTO faces — when to build, when to buy, and when to compose. A structured way through the trade-offs that define your stack.

Read the written version, with its diagrams and tables: https://bradshaw.cloud/strategy/build-vs-buy/

Personal views, not those of my employer.

API inference wins until about 25,000 queries a day — where $12,000 a month of self-hosted capacity meets $0.016 a query. Most workloads end up hybrid.

Read the written version, with its diagrams and tables: https://bradshaw.cloud/writing/ai-cost-curves/

Personal views, not those of my employer.

When API costs cross the self-hosting line — the economics that drive AI infrastructure decisions, and how to spot the crossover before it hits your bill.

Read the written version, with its diagrams and tables: https://bradshaw.cloud/strategy/ai-cost-curves/

Personal views, not those of my employer.

A decision guide to agentic architecture patterns — single vs multi-agent, sequential, routing, parallelisation, orchestrator-workers, evaluator-optimiser, and reflection — with trade-offs, failure modes, and the observability you can't ship without.

Read the written version, with its diagrams and tables: https://bradshaw.cloud/writing/agentic-ai-patterns/

Personal views, not those of my employer.