Knowledge, retrieval and context

Case studies

Evidence from the log

1. 19 Oct 2026

   Extended coverage reporting to mobile test suites

   Mobile teams write tests in Java with TestNG, which the first parser couldn't read. Added a Java-aware parser so their coverage shows up in the same weekly report.

   AI angleAn agent asked "how covered is the app?" needs every platform in one model, or it answers for web only. This closes the gap so the coverage data an MCP server will serve to agents describes the whole product.

   Telecom, Quality engineering. Part of Coverage intelligence, a quality data layer for agents

2. 14 Oct 2026

   Published a structure and naming standard for 20+ test repositories

   Every team laid out its repository differently, which made automated reporting brittle. Wrote one standard for folders, tags and naming, with a migration checklist per team.

   AI angleA predictable layout is the context layer agents need. With one standard, every agent (test generation, review, coverage queries) finds tests, page objects and tags in the same place in every repository, instead of each agent being tuned per team.

   Telecom, Quality engineering. Part of Coverage intelligence, a quality data layer for agents

3. 6 Oct 2026

   Shipped the first weekly automation-coverage report

   21 teams, measured straight from code instead of spreadsheets. The first run put regression automation coverage at 81.7%.

   AI angleGives the AI test-automation programme a baseline measured from code, so the effect of test-generation agents shows up in the numbers, and gives future agents a trusted source to query.

   Telecom, Quality engineering. Part of Coverage intelligence, a quality data layer for agents

4. 29 Sep 2026

   Started coverage measurement from source

   Leadership's automation numbers came from hand-kept spreadsheets nobody could trace. Prototyped a zero-dependency pipeline that clones every team repository and counts tests by tag.

   AI angleThe first step toward a quality data layer agents can read through MCP. An agent can't reason about coverage when the only source is a spreadsheet.

   Telecom, Quality engineering. Part of Coverage intelligence, a quality data layer for agents

5. 18 Aug 2026

   Started the legacy documentation agents

   Modernization projects stall because nobody understands the old code. Began an agent pipeline that combines deterministic static analysis with parallel LLM explorers.

   AI angleDeterministic tools handle what must be exact (call graphs, registers) and agents handle what needs reading and explanation. The result becomes context for the agents that do the migration.

   Legacy modernization. Part of Multi-agent legacy documentation

6. 19 Jan 2026

   Mapped a legacy codebase into a knowledge graph

   Turned repositories into a Neo4j graph of modules, calls and data flows, so engineers and agents query structure instead of grepping. Code navigation got 70% faster.

   AI angleGraphRAG over code. Agents get relationships (who calls what, where data flows) that plain vector search misses.

   Banking and financial services, Legacy modernization. Part of Agentic legacy modernization and code intelligence

7. 7 Jul 2025

   Grounded estimates in historical projects

   Added retrieval over past estimates with Azure AI Search and a regression baseline on Databricks, so every number comes with a confidence interval and citations.

   AI angleGrounding keeps the LLM from inventing numbers. It adjusts a statistical baseline and cites the past projects it used.

   Banking and financial services. Part of Estimation platform for an enterprise bank

8. 14 Apr 2025

   Reached 99.3% accuracy on bank-site extraction

   Added a validation pass that screenshots each page and has a vision model confirm every extracted value. Two weeks of market analysis now runs in under an hour.

   AI angleOne model extracts and another, with a different input (the screenshot), verifies. Cross-modal checking is what moved accuracy into the range analysts trust.

   Banking and financial services. Part of Market research agents for retail banking

9. 3 Mar 2025

   Built an LLM crawler for 20+ bank websites

   Selector-based scrapers broke every time a site changed. The crawler lets a model read rendered pages into a fixed schema instead.

   AI angleUses the LLM for what it's good at, reading messy pages like a person, and constrains it with a fixed output schema.

   Banking and financial services. Part of Market research agents for retail banking

10. 27 Jan 2025

    Drew Azure and AWS architectures for GenAI proofs of concept

    Reference designs for RAG, agent hosting and guardrails that pre-sales could adapt per client. They backed 10+ proofs of concept and 3 client wins.

    AI angleReusable blueprints for RAG, agents and guardrails, so each proof of concept starts from a sound architecture instead of a blank page.

    Banking and financial services, Telecom. Part of GenAI solution architecture and pre-sales

11. 21 Oct 2024

    Joined mobileLIVE (now ML Arteka) as an AI Engineer

    First weeks on proofs of concept for enterprise banking clients, from RAG assistants to agent workflows.

    AI angleMoved from research into building LLM systems for clients, starting with RAG and agent proofs of concept.

    Banking and financial services, Telecom. Part of GenAI solution architecture and pre-sales

12. 15 May 2023

    Built crop-disease detection and a policy chatbot

    At Agriculture and Agri-Food Canada, built computer vision for early crop-disease detection and a chatbot that answers farmers' policy questions.

    AI angleVision models and a retrieval chatbot over policy documents. My first RAG system, in a public-sector setting.

    Research and public sector. Part of Applied AI prototypes, from crops to small models