The research behind agents that hold up in production.
Addo researches how to make enterprise AI agents work reliably, improve over time and operate at a sustainable cost. Every question comes from a live deployment, and every answer that holds up goes back into Addo Core.
Reliable. Improving. Affordable.
Each area starts with a failure we have seen in production and ends with a method we can test on client workflows before it ships.
Reliable computer-use agents
Many enterprise systems have no API, so agents must work through the software itself. We research how agents verify their actions, recover from interrupted workflows and prevent duplicate submissions, even when applications give incomplete or ambiguous feedback.
Enterprise evaluation
A convincing demo is not proof of dependable performance. We research which evaluation methods best predict real-world reliability, using representative client workflows to measure task completion, policy compliance and behaviour under unexpected conditions.
Learning from operations
Every reviewer correction reveals something about how an agent fails. We research how to turn operational feedback into measurable improvements in knowledge, instructions and tool use, without regressions in workflows that already perform reliably.
Agent planning and task decomposition
Complex enterprise tasks require agents to plan, adapt and coordinate many steps. We research when agents should reason dynamically, follow structured workflows, or combine both to complete tasks reliably and efficiently.
Agent memory and context engineering
Enterprise agents need the right information at the right time. We research how memory and context strategies affect accuracy, continuity and reliability across long-running workflows, especially when information is outdated, incomplete or contradictory.
Agent efficiency and cost optimisation
More reasoning and larger models do not always produce better outcomes. We research how model selection, reasoning strategies and tool-use patterns affect cost, latency and task success, and where simpler approaches deliver comparable reliability.
Our researchers sit with the people who do the work, inside the client's operations.
Researchers sit with deployment teams.
Writing on AI, work and policy.
Addo's leaders write and speak on AI, data and the future of work, including for the World Economic Forum.
Preparing people for the AI workplace
On what education systems and employers need to change as AI takes on more of everyday work.
Regulating the sharing economy
On how governments can regulate data-driven platforms while keeping room for new services.