Building with Claude, and knowing when not to.
Claude is the model I reach for most — for long documents, for Arabic, and for anything where being wrong quietly is worse than being slow. It is not the right answer for everything, and this page is about both halves of that.
Model choice is a build decision, not a brand preference.
Picking a model is an engineering decision, not a subscription
Most "which AI should we use" conversations are really about a specific workload: this volume of documents, this language mix, this tolerance for a confident wrong answer. Those constraints pick the model. The brand argument is downstream of them, and usually irrelevant.
Where Claude tends to win is long-context work — a contract, a year of tickets, a whole codebase — and tasks where you would rather it say it is unsure than invent something plausible. That last property is worth more in production than it looks in a demo, because the failures it prevents are the expensive kind: the ones nobody notices for a month.
Where it does not win, I use something else, and the systems I build are written so that swapping the model is a configuration change rather than a rewrite. Anyone who tells you their AI product is permanently married to one provider has built it wrong.
What actually gets built with it
The workloads where it has earned its place, rather than the full capability list.
Read an inbox, classify it, pull the details out, act, and hand over what needs a person. Claude's willingness to stop and flag uncertainty is what makes an agent safe enough to leave running.
The steps a rules engine cannot express — is this complaint urgent, does this invoice match, is this reply good enough to send. The deterministic parts stay deterministic.
Document processing
Contracts, reports, statements and the long PDF nobody wants to read. Long context is the difference between summarising a document and answering questions about all of it.
Where Claude is genuinely strong, and the reason it is usually my default for this region — see the section below.
Used daily on real work: migrations, test coverage, refactors and the mechanical half of a build. It changes how fast the first version arrives; it does not change who is accountable for the last ten percent.
Evaluation and guardrails
The unglamorous part. What the model is allowed to do unsupervised, what gets logged, what a bad answer costs, and how you would know. Skipping this is how pilots quietly never ship.
Arabic is where the choice actually matters
Most model comparisons are run in English, which makes them close to useless for deciding what to deploy in Kuwait or the UAE. The real test is Gulf dialect rather than textbook Modern Standard Arabic, messages that switch between Arabic and English mid-sentence, and names and addresses that transliterate three different ways.
Claude handles that mix better than most, which is why it is usually my starting point here — but "better than most" is not "solved", and the only honest way to choose is to evaluate against your own data. A hundred real messages from your own inbox will tell you more than any benchmark.
The build matters as much as the model. Arabic-first means the prompts, the evaluation set, the interface and the fallbacks are built that way from the first version, not translated afterwards.
Where I would not use it
Stated plainly, because the alternative is discovering it after you have paid for the build.
High-volume, low-value classification where a small cheap model is accurate enough and costs a fraction as much
Anything that must be deterministic — pricing, tax, eligibility. Use code, and use the model to explain the result if you need it explained
Realtime voice, where latency budgets currently favour purpose-built models
Workloads where the data genuinely cannot leave a specific jurisdiction and no compliant deployment option exists
Problems that are not AI problems. A broken process automated is a broken process running faster
The systems I build keep the model behind an interface, so none of these are permanent decisions.
How a Claude build runs
Find the workload
One process, traced end to end, with a number attached to what it currently costs. Not "add AI to support" — the six ticket types that make up most of the volume.
Build the evaluation first
Real examples from your data with known-good answers. Without it, "it seems better" is the only measure available, and it is not a measure.
Smallest useful version
Narrow scope, real data, running alongside the existing process rather than replacing it on day one.
Decide what it may do alone
Drafting is not sending. Suggesting is not deciding. The boundary is set deliberately and widened only once the evaluation says it should be.
Hand it over
Documented, owned by someone named, with the evaluation left in place so quality can be checked later rather than assumed.
Related
Claude — the tool — What it is, plans, where it fits
Claude Code — The terminal agent, and its limits
AI Agents — Agents that complete a task
AI Automation — Removing work rather than adding dashboards
Arabic-first AI Products — Built for Arabic, not translated into it
AI in Kuwait — How this lands with businesses here
Selected work — What has actually been built
What I've written about Claude
Model comparisons, pricing analysis and what the coding agents are genuinely like to work with.
Should we use Claude, ChatGPT or Gemini?
It depends on the workload, and the honest answer usually involves more than one. Long documents, careful reasoning and Arabic push toward Claude. High-volume cheap classification often does not need a frontier model at all. I build so the choice can change without a rewrite, and I have written the comparisons up in detail rather than asking you to take my word for it.
Is Claude good at Arabic?
Better than most, in my experience, particularly with Gulf dialect and mixed Arabic-English input — which is what real messages in this region look like. But it is worth evaluating against your own data rather than any benchmark, and that evaluation is part of how I start.
Can you connect it to our existing systems?
Yes, and that is usually where the value is. A model with no access to your CRM, inbox or documents is a chatbot; connected properly it can actually do the work. The integration work is normally the larger half of the project.
Do you use AI to write the code you deliver?
Yes, Claude Code daily, for migrations, tests, refactors and the mechanical half of a build. It is reviewed, and it is my responsibility when it ships — AI-assisted does not mean unreviewed. It means more of the budget goes to the parts that need judgement.
What does this cost to run?
Model cost is usually the small part; the integration and the evaluation are the real budget. I cost the running side before building, because an automation that costs more than the process it replaced is not a saving.
Got a workload you think Claude could take?
Got a workload you think Claude could take?
Describe the process and roughly what it costs you now. Thirty minutes is usually enough to say whether it is worth building, and which model it should be built on.
Browse the site
Home
about
story
work
expertise
ai
ai ai product development
ai ai agents
ai ai automation
ai ai consulting
ai arabic ai products
ai kuwait
toolkit web
toolkit claude
toolkit lovable
toolkit notion
toolkit webflow
toolkit shopify
toolkit wordpress
toolkit ai solutions
services
services business strategy
services growth planning
tools
blog
stack
connect
quote
privacy
terms