THINKING FORWARD / OPEN LABS
We show how AI agents work.
Open research, reference architectures and practical experiments in connecting AI agents to real information, systems and business workflows.
Methods, sources and limitations included.
FEATURED RESEARCH
Skills for UAE Public Services.
How can an AI agent help a business navigate licences, regulatory information, supporting documents and next steps across different services? We map the available information, MCP interfaces, entities and workflow patterns — and explain where human decisions remain essential.
Three Agent Skill packages are published for inspection: company setup, Golden Visa pre-checks and e-invoicing readiness. Practitioner review is pending; this is not a validated transactional service.
Saudi Arabia — documentation in preparation · Qatar — documentation in preparation
HOW AGENTS WORK
One business request.
Multiple sources. A reviewable result.
An Agent Skill defines the job and checks. MCP connects permitted tools and information sources. The agent assembles evidence, identifies exceptions and prepares the next action. A person approves consequential decisions.
- Business taskA defined company request.
- Agent SkillInstructions, checks and stop rules.
- MCP + public sourcesRead only through permitted tools.
- Evidence + exceptionsCitations, dates and unresolved questions.
- Human reviewApprove consequential decisions.
- Business outputA decision pack and proposed tasks.
RESEARCH AREAS
From sources to executable workflows.
Official government portals, datasets, authentication models and access conditions.
Community and commercial MCP servers: capabilities, source attribution, maturity and limitations.
Licences, authorities, business activities, obligations, legal provisions, locations and deadlines.
Reusable sequences that retrieve, compare, verify, prepare and escalate — with evidence and human review.
TRANSFER TO ENTERPRISE
The same engineering.
Your business systems.
The public-services research is one example of a broader challenge: turning fragmented information and rules into reliable workflows. We apply the same approach to enterprise data, operations and approvals — from architecture to implementation and team training.
Independent technical research by Thinking Forward. No affiliation with or endorsement by UAE government authorities.