Blog Field notes

Field notes on AI that ships.

Essays and working notes from building production AI: evals, retrieval, agents, security, and the unglamorous engineering in between. Or start from your industry.

LatestAI company guides16 min read

AI acceptance testing: criteria, scoring and a test plan.

How to decide whether an AI system built for you is good enough to accept and launch: the test set, acceptance criteria written as numbers, scoring output that varies, the gate, the pilot and what comes after. With a test plan to copy.

Read the note

Every note.

46 notes, newest first

  1. AI acceptance testing: criteria, scoring and a test plan

    How to decide whether an AI system built for you is good enough to accept and launch: the test set, acceptance criteria written as numbers, scoring output that varies, the gate, the pilot and what comes after. With a test plan to copy.

    AI company guides 16 min
  2. AI RFP template: how to write an RFP for AI development

    What an RFP for AI development must ask that a software RFP doesn’t: evaluation on your own data, a proof stage, data use, model accounts, ownership and exit. With a scoring table and a complete template to copy.

    AI company guides 16 min
  3. AI statement of work: what to include, with a template

    What an AI consulting statement of work must say that a normal software SOW doesn’t: measured acceptance criteria, data terms, model changes, ownership and exit. With a complete template to copy.

    AI company guides 18 min
  4. How long does an AI project take? Timeline by phase

    An honest AI project timeline for buyers: what happens in each phase, what really sets the length, and what you can do to shorten it. With a project plan to copy.

    AI company guides 15 min
  5. AI agents for property management: leasing to repairs

    What an AI agent can safely do for residential and commercial property managers, from leasing inquiries to emergency repairs, and which rules belong in code instead of a prompt.

    Industries 11 min
  6. AI for call centers and BPOs: voice, QA and agent assist

    What AI does for operators that run queues for many client brands: scoring every call, assisting agents inside each client’s tools, and voice agents for narrow call types, with every client’s data kept apart.

    Industries 13 min
  7. AI for consulting firms: proposals and knowledge

    What AI does well for firms that sell knowledge: proposal drafts from past wins, expert finding, cited search over past work, and the walls and checks that keep client trust.

    Industries 11 min
  8. AI for franchises: franchisee support and lead agents

    What a franchisor’s head office can safely automate: an operations-manual assistant, FDD-grounded prospect answers, local lead routing and unit reports, and who answers for what.

    Industries 11 min
  9. Adding AI features to a SaaS product: evals and safety

    What a B2B SaaS team should build before an AI feature reaches customers: release gates, tenant isolation, defenses against hostile content, usage metering, fallbacks and limits on agents.

    Industries 11 min
  10. AI for wholesale distributors: orders, quotes and ERP

    How mid-size distributors on an ERP can use AI for email and PDF order entry, part-number matching, quotes within approval limits, backorder updates, and a measured exception rate.

    Industries 11 min
  11. AI regulation for UK businesses: what applies (2026)

    The UK has no AI Act, but it has rules. What UK GDPR’s automated-decision regime, the ICO, the FCA and the MHRA expect from an AI system, and what is still draft.

    Regulation 12 min
  12. Best AI development companies in the UK (2026): 11 compared

    Eleven UK AI development firms in alphabetical order, each matched to the buyer need it suits best, with public evidence, independent ratings where they exist, and how to choose between them.

    AI company guides 11 min
  13. Evals before features

    Most AI teams build the feature, then try to work out whether it works. We build the measurement first. Here’s what that looks like in practice, and why it makes teams faster.

    Evals 5 min
  14. The EU AI Act for companies building AI systems: a 2026 guide

    What applies today, what the Digital Omnibus delayed, and who counts as the provider when you commission a custom system. For companies in the EU, and anyone selling AI into it.

    Regulation 8 min
  15. AI for insurance brokers: use cases and rules (2026)

    How brokers and MGAs use AI on submissions, quotes, renewals and client questions, where claims and underwriting fit in, and the rules that apply to AI in insurance.

    Industries 10 min
  16. Inside a WhatsApp sales agent

    Our AI sales agent handles 70% of a solar client’s monthly sales inside WhatsApp. Here’s how it’s put together, and where the human team still comes in.

    Agents 5 min
  17. AI in healthcare for clinics: safe uses and rules (2026)

    Where AI is safe in a clinic today (reception, scribing, summaries, follow-up), when a tool becomes a regulated medical device, and what HIPAA, UK and EU rules ask of the system.

    Industries 12 min
  18. AI development in Dubai and the UAE: rules and Arabic (2026)

    What UAE companies need to know before building an AI system: how federal, DIFC and ADGM data rules apply, and what Arabic and WhatsApp change about the build.

    Markets 4 min
  19. Retrieval that knows when to say “I don’t know”

    A RAG system that always answers is a liability. The useful ones retrieve carefully, cite what they used, and decline when the evidence isn’t there.

    Retrieval 4 min
  20. AI for sales teams: use cases, setup and metrics

    What an AI sales agent is, the kinds of sales AI and when each fits, how to run a pilot, which numbers to track, and where salespeople still win.

    Industries 11 min
  21. Prompt injection is an input-validation problem

    You can’t prompt your way out of prompt injection. Treat every token from outside your system as untrusted input, and design so that a successful injection can’t do much.

    Security 4 min
  22. AI in construction: use cases, risks and first steps

    What AI does for contractors, developers and consultants today, from tender packs, specifications and RFIs to site reports and handover, and how it connects to scheduling, estimating, safety and BIM tools.

    Industries 11 min
  23. Fallback chains: designing AI that fails gracefully

    Models time out, providers go down and outputs fail validation. A production system needs an answer for each of those moments before they happen.

    Reliability 4 min
  24. AI in financial services: KYC, AML and compliance (2026)

    Where AI helps banks, lenders and fintechs with KYC files, AML alerts, credit memos and service, what the FCA, FSB and EU AI Act expect of the system, and where a person must decide.

    Industries 10 min
  25. The six months after the demo

    A prototype that impresses in a meeting and a system that survives production are different projects. The gap between them is predictable, and so is the work that closes it.

    Strategy 3 min
  26. AI development in Saudi Arabia: PDPL, data residency (2026)

    What a Saudi company needs to settle before building an AI system: PDPL duties, where data may be processed, Arabic and WhatsApp, and a checklist for choosing a development partner.

    Markets 12 min
  27. AI customer service and support: setup and handover rules

    How to set up AI customer support that resolves real questions: the four modes, handover rules written as code, what the Air Canada chatbot ruling teaches, and metrics with clear definitions.

    Industries 11 min
  28. AI in retail and ecommerce: sales and support agents (2026)

    How retailers and online stores use AI agents on WhatsApp and web to answer, sell and handle returns, where AI is the wrong tool, and the rules for an AI that talks to customers.

    Industries 10 min
  29. AI for law firms: use cases, rules and an AI policy (2026)

    What AI does well for law firms, which kind of AI fits which legal task, how to stop fake citations, what the SRA and ABA rules say, and what a firm AI policy should cover.

    Industries 12 min
  30. AI in HR and recruitment: hiring AI laws checklist (2026)

    Where AI helps HR and recruiting teams today, where a person has to decide, and a checklist of the hiring AI laws in New York City, Colorado, the UK and EU as of October 2026.

    Industries 11 min
  31. AI in education: admissions, course support and rules (2026)

    What AI can safely do for applicants, students, teachers and administrators, where a person has to stay in charge, and the rules that tighten around admissions, assessment and children’s data.

    Industries 10 min
  32. AI in travel and hospitality: guest messaging and use cases

    What a hotel AI agent actually does, how to run guest messaging safely, which systems it connects to, and where a person has to stay in charge.

    Industries 12 min
  33. AI for solar companies: leads, proposals and O&M (2026)

    Where AI pays off for solar installers, EPCs and operators, from answering leads in minutes to catching failing inverters early, with results from systems in production and the rules to know.

    Industries 11 min
  34. AI for manufacturing companies: mid-size plant use cases

    Which AI projects pay off first for small and mid-size manufacturers, what each needs to connect to, where a person stays in charge, and how EU and OT security rules apply.

    Industries 10 min
  35. AI for logistics companies: use cases and first steps

    Where AI pays off in freight, 3PL and distribution today, where a language model is the wrong tool, how to measure it, and a 90-day plan for the first project.

    Industries 12 min
  36. AI agents for real estate: use cases, limits and setup

    What an AI agent does for brokers, developers and property managers in the US, the UK and Dubai, how it differs from a chatbot, what it must never do, and how to start.

    Industries 12 min
  37. AI for accounting firms: use cases and sign-off (2026)

    Where AI saves accounting firms and finance teams the most time, from client document collection and invoices to month-end and tax research, and how to keep every figure accurate enough to sign.

    Industries 10 min
  38. Best AI development companies in the US (2026): 10 compared

    Ten AI development companies serving US buyers, each matched to the need it fits best, with company facts, public work and independent ratings checked on 25 October 2026.

    AI company guides 10 min
  39. Questions to ask an AI development company before hiring

    The questions that show whether an AI development company has run systems in production or only built demos, grouped by stage, with what a good answer and a red-flag answer sound like.

    AI company guides 17 min
  40. WhatsApp AI sales agent: setup, rules and testing (2026)

    What a WhatsApp AI sales agent does from first enquiry to closed deal, what Meta’s rules allow, four ways to build one, and the test script to run before any customer talks to it.

    AI sales automation 13 min
  41. Top AI companies in Pakistan (2026): 10 firms compared

    Ten AI companies serving buyers in Pakistan, listed A to Z and each matched to the need it fits best, with company facts and public work checked on 6 November 2026.

    AI company guides 13 min
  42. AI is becoming more action-oriented, not just more intelligent

    The latest model releases show the market moving past prompt-and-response interaction toward systems that complete real work across applications and workflows.

    Product Design 3 min
  43. Enterprise AI infrastructure is now a strategic priority

    AI adoption is accelerating, and infrastructure decisions now shape deployment outcomes as much as model choice does.

    Infrastructure 3 min
  44. Multimodal AI is becoming the new standard for digital products

    The next generation of AI products is being built around multimodal experiences that combine reasoning, diverse inputs, and real workflow integration.

    Engineering 3 min
  45. Responsible AI is becoming a product requirement

    As AI systems grow more capable and more widely deployed, governance and safeguards are moving out of policy decks and into core product design.

    Governance 2 min
  46. AI partnerships show the move from pilots to deployment

    The latest strategic partnerships across the AI ecosystem show enterprise adoption shifting from pilot programs to long-term infrastructure and platform commitments.

    Enterprise AI 3 min