Blogs

Agentic AI Reliability: In-Loop and Out-of-Loop Tooling Make the Difference Between a Fancy Demo and ROI

By Felix Mottram / August 7, 2026 / Comments Off on Agentic AI Reliability: In-Loop and Out-of-Loop Tooling Make the Difference Between a Fancy Demo and ROI

In loop tooling supervises the agent while it runs. Human in the loop pauses, quantitative judges, LLM judges, repetition guards and hard stops, provenance tracking on every significant write, and a self healing loop that keeps the model out of the path once an automation works.

Digital Worker Memory: Digital Workers Continuously Learn and Improve Like Your New Hires

By Felix Mottram / August 7, 2026 / Comments Off on Digital Worker Memory: Digital Workers Continuously Learn and Improve Like Your New Hires

The more you interact with a Digital Worker, the more autonomous it becomes. Every correction, every judgement call a business user makes on an edge case, every “actually, we handle that differently here” gets captured and applied on the next run.

Agentic AI Reliability: Automating Agentic QA

By Felix Mottram / August 7, 2026 / Comments Off on Agentic AI Reliability: Automating Agentic QA

Agentic QA gives the agent a browser and a test runner. It explores the application to learn how it actually behaves, then writes and iterates on Playwright tests against that understanding.

You Can Trust Your Digital Workers With Structured Data: The Structured Data Module

By Felix Mottram / August 7, 2026 / Comments Off on You Can Trust Your Digital Workers With Structured Data: The Structured Data Module

Accuracy on structured data is not a leaderboard metric. It is an audit question. Regulated teams do not ask whether a number is probably right. They ask who can show the working.
We built the Structured Data Module so the answer is the Digital Worker itself.

Your Digital Workers Do Not Need a Data Lake: Agentic Data Mesh

By Felix Mottram / July 31, 2026 / Comments Off on Your Digital Workers Do Not Need a Data Lake: Agentic Data Mesh

Centralising your data is not a prerequisite for automating your work. It is a multi-year programme that delays every use case behind it. The agentic data mesh removes it from the critical path.

Agentic AI reliability: Causal Verification

By Felix Mottram / July 30, 2026 / Comments Off on Agentic AI reliability: Causal Verification

“Trust me” is not an audit trail. When an AI agent makes a decision, all you get back is prose. Make the agent commit to a structured claim.

Change Management for Agentic AI Is Not an IT Programme

By Felix Mottram / July 28, 2026 / Comments Off on Change Management for Agentic AI Is Not an IT Programme

Most large enterprises are running agentic AI adoption through the same change management playbook they used for their last ERP upgrade. Training modules, phased rollouts, a comms plan. It will not work, because agentic AI is not one change. It is two.

Towards Agentic Determinism

By Felix Mottram / July 28, 2026 / Comments Off on Towards Agentic Determinism

Enterprises keep asking the wrong question about agentic AI: “How do we make it deterministic?” You don’t. You make the delivery deterministic, exactly as software engineering did decades ago.

IT Teams Love causaLens

By Felix Mottram / July 22, 2026 / Comments Off on IT Teams Love causaLens

We fit into your data and AI strategy, we do not fight it. One Docker image, deployed inside Snowflake, Databricks, your ERP, your CRM, or fully on your private cloud. Your data never leaves your perimeter.

Everything Your Agents Produce Belongs to You

By Felix Mottram / July 20, 2026 / Comments Off on Everything Your Agents Produce Belongs to You

The outputs of your agentic systems are your IP. Not just the work product. The memory, the traces, the evals. All of it.