Writing
From the lab
Writing on building, running, and owning AI agents in production.
Cruq AI joins AWS Activate
Cruq AI is in AWS Activate on the Portfolio tier, with $12,000 in AWS credits. Here is what we are spending them on.
Your agent was paying for the same prompt on every turn
An agent resends its instructions, its tools and the whole conversation each time it calls the model. Claude only gives you the cached price if you ask for it, and we weren't asking. What we changed, and what it saved on a real run.
Agents that work while you're offline
Most AI at work waits for someone to type. The work that matters often happens when nobody is typing. How Cruq AI agents start on their own, do the work, stop where a person should decide, and leave a record you can check in the morning.
Jev: a model that answers questions instead of writing text
Most of what an agent runtime does is not generation. It is small judgements, dozens per run, where the answer is a bit or a label. TypeSafe's Jev only does judgement, in parallel, with a probability attached. How it works, how Cruq AI uses it for semantic guardrails, routing, eval scoring and a tool agents call themselves.
Physical AI: the agent in the supervisory loop
Most of the physical world a business runs on is not a robot. It is a fridge, a truck, a pump, a door sensor, already wired with sensors and actuators that nobody watches well. What an agent in that layer has to be, the escalation ladder that makes it safe, and what we measured when we built one for a cold chain.
The latency budget of a voice AI agent
A voice agent has under a second to reply before a call feels broken. That budget is spent across speech-to-text, a language model, and text-to-speech, and the model is usually the bottleneck. A field guide to where the milliseconds go and how to claw them back.
How in5 turned Cruq AI from an idea into a Dubai company
Cruq AI is a Dubai company because of in5. Here is what the innovation centre actually did, from the trade licence to the workspace and the introductions.
How Google for Startups helps Cruq AI run production AI
The Google for Startups Cloud Program covers a large share of cloud costs for AI startups. Here is how that maps to the infrastructure Cruq AI runs.
How Microsoft for Startups fits a model-agnostic platform
Microsoft for Startups Founders Hub gives Cruq AI Azure credits, Azure OpenAI access and developer tooling. Here is how each piece fits a platform built to stay model-agnostic.
Cruq AI joins NVIDIA Inception
Cruq AI is now in NVIDIA Inception, NVIDIA's program for AI startups. Here is what it provides, and how it fits the speech models we train for Indian languages.
How Claude for Startups fits a model-agnostic platform
Cruq AI is in Anthropic's Claude for Startups program. Here is what it provides, how we use it, and why customers still choose their own models.
How the ElevenLabs grant helps Cruq AI build voice agents
Cruq AI is in the ElevenLabs Grants program. Here is what the grant covers, what we are building with it, and why customers still bring their own ElevenLabs key.
GraphRAG: when a knowledge graph beats vector search
Vector RAG retrieves chunks that look like your question. It falls down on questions that need connecting facts across documents, or summarizing a whole corpus. GraphRAG builds a knowledge graph first. How it works, when it wins, and what it costs.
Top AI agent development companies in Dubai (2026)
Dubai has become one of the fastest markets in the world for agentic AI. A practical guide to the companies building production AI agents in the UAE, what separates a real agent platform from a demo, and how to choose a partner.
Agentic model optimization for the edge
Getting a trained model to run fast on a phone, an NPU, or a microcontroller is a brutal, coupled search across the whole stack. The shift in 2025 and 2026 is handing that search to agents that work from a goal. A field guide to the four capabilities that make it work.
Quality Intelligence: engineering trust into AI features
Shipping AI features that hold up in production takes more than model testing. It takes a Quality Intelligence framework built on reliability, clarity, and measurable excellence.
Why RL environments beat prompt engineering for edge cases
Prompts are instructions. Environments are practice. Here's why the distinction matters when your agent keeps failing on the same class of inputs.
The hidden cost of frontier models in enterprise workflows
Most teams don't realize how much of their API bill comes from a small set of repetitive tasks. We traced the pattern across 12 deployments.
Trace capture without slowing down your agent
Observability shouldn't be an afterthought. Here's our async capture architecture that adds less than 5ms overhead to any LLM call.
What we learned building private SLMs for three different verticals
Finance, legal, and ops all have different failure modes. Here's what we found when we trained domain-specific models for each.
