Software.
Everything I've written about software. Start at the top; the list compounds.
By domain.
software posts.
Showing 1–10 of 71.
When NOT to Use Composer 2.5: 6 Cases Where Opus 4.7 Still Wins
The single most-quoted line in every Composer 2.5 launch piece is that it is "ten times cheaper than the frontier models." That number is accurate at the per-token level. It is also misleading at the per-completed-task level, because a model that needs three a
Composer 2.5 + MCP: The Production Integration Guide (2026)
A pattern from the production audits I have run over the last fortnight: teams switch to Composer 2.5, see the headline 10× cost saving in their per-token bill, and watch the same agent loops still take three or four attempts to land each task. The cost-per-co
RAG vs Long-Context: When Each Actually Wins in Production (2026)
The version of this argument that runs on social media goes like this: long context windows have killed RAG. Claude Opus 4.7 has 1M tokens. Gemini 3.5 Flash has 1M with a Pro that pushes higher. You can just load the documents and ask the question. Vector data
Composer 2.5 vs Gemini 3.5 Flash: When Each Wins on Real Coding Tasks
The first surprise when you sit the two pricing sheets side by side is that the smaller-branded model isn't cheaper. Gemini 3.5 Flash lists at $1.50 per million input tokens and $9.00 per million output. Composer 2.5 lists at $0.50 input and $2.50 output on th
Building a Legal Research Agent: Gemini Flash + Opus 4.7 + RAG (Use-Case Build)
The interesting thing about legal research as an AI use case is that the work is structurally a perfect fit for the tools and yet most of the AI products in the legal vertical do not architect to that fit. The work is high-volume (thousands of pages per case),
The Strangler Fig Pattern: Migrating Legacy Monoliths to Modern Architecture
Most enterprises don't get to build the modern architecture greenfield. They have to migrate into it — from a decade-old monolith, from a sprawling SOA with bespoke point-to-point integrations, from a vendor system that was never designed to be extended the wa
Gemini 3.5 Pro Pre-Read: What June's Release Will Change for Builders
The interesting thing about Gemini 3.5 Pro is what Google did not say at I/O. Flash shipped on May 19th with full benchmarks, pricing, and API availability. Pro got a one-line mention — "coming next month" — and an admission that Google is already using it int
The Transactional Outbox Pattern: Reliable Event Publishing Without 2PC
Every event-driven system depends on a deceptively simple guarantee: when a service commits a state change to its database, the corresponding event must be published. Both happen, or neither does. The system that gets this wrong silently corrupts itself — orde
Claude Code in Production: 9 Months In, What Actually Works (2026)
Claude Code shipped quietly. There was no big launch event, no benchmark theatre — just a CLI that let you point Claude Opus at a codebase and ask it to do things. At the time, the right framing for it was "another agent harness, this one from Anthropic, proba
Service Mesh vs ESB: Where Cross-Cutting Concerns Belong
Service mesh and Enterprise Service Bus solve overlapping concerns. Routing, observability, security, traffic management, retries, circuit breaking — both architectures address all of them. The interesting question is not which is better, because that's a mean