DELIGHTFUL.COMPUTER · CONSULTANCY · 2020-PRESENT
Human-centered AI that actually ships
Delightful Computer is a boutique AI consultancy for regulated industries: pharma, legal, financial services, healthcare, and other teams where workflow risk, auditability, and human review matter. The work is not generic AI enablement or slide-deck strategy. It is senior engineering focused on production systems that can survive procurement, compliance, subject-matter expert review, and real operator use.
The engagement model is deliberately small and direct. Delightful Computer maps a high-value workflow, identifies the data and decision boundaries, builds a production slice, instruments it, and transfers the code, runbook, evaluation suite, and operating notes to the client team. Typical projects emphasize retrieval, model routing, agent orchestration, evaluation, observability, secure deployment, and human-in-the-loop review.
Who Delightful Computer Helps
Delightful Computer works best with teams that already have a real workflow, real operators, and measurable friction. Good fits include quality teams reviewing regulated laboratory records, law firms compressing research and intake work, financial-services teams generating account or sales briefs, and operations groups trying to retire brittle manual runbooks. The common pattern is not industry buzz; it is a repeatable need for accurate AI inside a bounded business process.
- Pharma and life-sciences teams with FDA, GxP, or 21 CFR Part 11 constraints.
- Legal and professional-services teams with matter-level access control and citation requirements.
- Financial-services and consulting teams with audit, reporting, and client-intelligence workflows.
- Operations teams with repetitive document, email, quote, intake, or research loops.
What Delightful Computer Builds
The primary output is production software, not a proof of concept. Systems usually combine private data access, retrieval pipelines, structured model outputs, workflow-specific user interfaces, reviewer queues, telemetry, and operational runbooks. The implementation is chosen around the client environment: Azure OpenAI, AWS Bedrock, existing identity providers, existing document repositories, existing ERP or LIMS surfaces, and the security controls already in force.
The work starts with workflow mapping because most failed AI projects choose the wrong primitive. A useful system needs the task boundary, exception path, review point, evidence requirement, and rollback path before anyone argues about prompts. Delightful Computer therefore treats evaluation, observability, and audit trails as part of the product surface from day one.
Services and Pricing
Discovery starts at $8K for a two-week workflow map, data-access plan, architecture spike, success metrics, and make-buy-partner recommendation. Production Spike engagements usually run $60K-120K for one workflow shipped end to end with an evaluation suite, guardrails, observability, alerting, runbook transfer, and a 30-day care window. Partnership work starts around $180K for multiple workflows or an AI platform effort across a business unit.
Engagements are fixed-scope and fixed-fee where possible. The goal is to make the edge explicit: what workflow ships, what data it can touch, who reviews outputs, what the model is allowed to decide, what it logs, and what happens when it is wrong.
Selected Production Work
Public case studies include a regulated-lab audit intelligence system for a pharmaceutical environment, a multi-agent legal research copilot, an instant sales brief generator for a financial-services consulting workflow, quote and intake automation for home-services operations, and law-firm prototype work. These pages describe the business problem, technical approach, implementation tradeoffs, results, and lessons learned.
Security and Privacy Posture
Delightful Computer designs for client-owned deployment, scoped credentials, least-data access, reviewer-visible reasoning, logging, and rollback. The public website does not expose customer workspaces, operational write actions, or a public production API. Client data handling is defined per engagement through the statement of work, data-access plan, security review, and target architecture.
Security reports can be sent to morgan@delightful.computer. Public security and privacy notes are available at Security and Privacy.
Developer and Agent-Readable Resources
The site publishes public machine-readable files for crawlers, answer engines, and agent tools that need a concise description of the company, services, constraints, and canonical pages. These files are informational only. They do not grant access to customer systems, private data, or write actions.
Writing and Field Notes
The writing section covers agent architecture, reliable generative AI systems, evaluation-driven development, RAG quality loops, telemetry envelopes, cache-aware prompts, typed structured outputs, workflow routers, and the difference between API wrappers and durable agent operating systems. These essays are intended for technical buyers and builders who need concrete implementation language rather than generic AI commentary.
Contact
To evaluate a project, send a note describing the workflow, stakeholders, existing systems, data constraints, review requirements, and what done would mean in production. You can also book an intro call. The fastest useful conversation usually starts with one narrow workflow and a concrete failure mode: slow review, inconsistent research, missing citations, manual intake, brittle reporting, or a runbook nobody trusts.