Insights & engineering notes
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.
Read the post
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.
Read the post
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.
Read the post
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.
Read the post
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.
Read the post34 posts
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.
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.