Posts about AI
29 posts tagged AI.
Physical AI: what software teams should build before the robots arrive
Nvidia calls 2026 the age of physical AI, with humanoids in warehouse and factory pilots. For most companies the work is software: data, simulation and control.
Meta's Muse agent: what it gets right about agent security, and what it means for yours
Meta's Muse personal agent launched with a security architecture worth copying: the agent never sees a real credential. What it means for agents you build.
GPT-6 Astra: what OpenAI's new ChatGPT model changes for software teams
OpenAI's GPT-6 Astra is live in ChatGPT, Codex and the API. What's new in computer use and agentic coding, what it costs, which claims to trust, and what to do.
AI governance and guardrails: the adult in the room, built into the code
AI governance is the keyword of 2026 as agents scale and EU AI Act obligations bite in August. What guardrails mean in engineering terms, and what to build.
Agentic AI in 2026: what changes when the prompt becomes a workflow
Agentic AI tops the 2026 trend lists. What moving from one-off prompts to autonomous workflows requires in code, when multi-agent is worth it and what to build.
How much does an AI agent cost to build?
The honest range for a production AI agent, broken into the build, the harness work nobody quotes for, and the per-action running cost once it ships.
LLM security: prompt injection, data leakage, and what actually stops them
Most LLM security advice is 'write a better system prompt.' The actual defenses are architectural: what the model can see, what it can do, and what never returns to a user unchecked.
LLM observability: what to log, and what it actually catches
Traditional APM tells you a request was slow. LLM observability has to answer a different question: was the answer right, and why did the model say that?
How to build an AI analytics assistant
'Ask your data a question' is a text-to-SQL problem wearing a chat interface. The architecture that makes it trustworthy: schema grounding, guardrails, and a query the user can check.
LLM application architecture: the layers that don't change with the model
Model, harness, data layer, and product surface: the four layers of a production LLM application, and which ones survive the next model upgrade.
Agent harness: what it is, and why your agent needs one
An AI agent is a model plus a harness. The model is rented; the harness is what you own, and it is where agents succeed or fail in production. What goes in one.
How we reduced LLM costs in a multi-tenant AI platform
One customer's heavy usage was inflating everyone's bill. The per-tenant budgeting, routing, and caching changes that cut the platform's running cost by 58%.
Enterprise RAG: what changes with real documents, permissions, and scale
A RAG demo answers questions about a clean folder of PDFs. An enterprise deployment has to handle permissions per document, millions of pages, and daily churn.
RAG vs fine-tuning: what should your business use?
They get pitched as competitors and usually are not. How to tell which problem you actually have, and the cases where the right answer is both.
RAG architecture: the pipeline from document to answer
Ingestion, chunking, embedding, retrieval, reranking, generation: the six stages of a production RAG pipeline, and where each one quietly determines answer quality.
What is RAG, in plain terms?
Retrieval-augmented generation, explained without the jargon: what problem it solves, the four steps in the pipeline, and where it stops being the right tool.
Enterprise AI agents: what changes at scale
The prototype agent and the enterprise one solve the same task with a different architecture underneath. SSO, audit, governance, and the review nobody skips.
MCP servers: exposing your systems to models safely
The Model Context Protocol is now how tools reach a model. How we design an MCP server for a client system: scope, safety, and what to leave out at first.
Building AI agents that can safely modify customer data
Read access is forgiving of mistakes. Write access is not. The permission model, approval flow, and audit trail that make a write-capable agent safe to ship.
LangGraph vs CrewAI vs AutoGen: a practical comparison
Three popular agent frameworks, compared on what actually differs in production: control over the loop, debugging, and how much they decide for you.
What are AI agents, actually?
Not a chatbot, and not magic: an AI agent is a model that can call tools and decide what to do next. What that definition includes, excludes, and implies.
How to architect an AI agent platform
Not one agent behind an API: a platform. The layers that stay stable while models and frameworks underneath them change, and the order to build them in.
Evals before features: how we score AI work
The first thing we build on any AI feature is the test set, not the feature. How the evaluation set is made, what it measures, and why it changes the build.
When a RAG system is the wrong answer
Retrieval-augmented generation is the default answer to adding AI to documents. The four situations where it is the wrong one, and what to build instead.
Context engineering is the new prompt engineering
Prompt wording matters less than what the model sees. Context engineering in practice: retrieval, summarisation, exclusion, and a budget for attention.
AI coding agents in production: the review gates that make them safe
Coding agents now write a lot of software. What we put between an agent's output and production: five review gates, why each exists, and what we measure.
One agent is usually enough
Multi-agent systems are the fashionable architecture. Most problems need one agent with good tools; more is slower and harder to debug. When more is right.
Small models and routing: how we keep AI features affordable
The demo used the biggest model for everything. Production cannot. How routing, caching, and small tuned models cut the running cost of AI features by half.
What breaks in AI-generated codebases, in the order it breaks
We have audited many codebases built mostly by AI tools. The same seven problems appear in the same order, from week one to month six. How to catch them early.
Tell us what you are building.
We reply within one business day with how we would build it, what it would cost, and which engagement model fits.
- 01Tell us what you are building
A short form or an email. No deck required, and "not sure yet" is a fine answer.
- 02A call with an engineer
Within one business day. Technical questions get technical answers, from the person who would build it.
- 03A written scope and quote
Fixed price where the scope is defined. The document is yours whether or not you go ahead.