Knowledge base
The whole argument, one entry at a time
20 entries. They build one case: that agentic analytics is a stack rather than a model, that its hard half is the data underneath, and that an open lakehouse is what makes that half work for a whole organisation rather than one pilot team.
What this is
What agentic analytics means, how it differs from what came before, and where the earlier attempts stalled.
- 01 What is agentic analytics An AI agent doing the work of an analyst against governed data, with the authority to run queries and the obligation to show where the answer came from.
- 02 From dashboards to questions Dashboards answer questions somebody anticipated. Agents answer the ones nobody did, which changes what the data layer has to support.
- 03 Text to SQL and why it stalls Generating SQL from a question was solved years ago. Generating the right SQL against a real schema was not, and the gap is definitional rather than technical.
The agentic stack
Model, harness, and open interfaces. Three separable layers with three distinct failure modes.
- 04 The agentic stack Three separable layers, model, harness, and open interfaces, each with its own failure mode. Most agent problems are misattributed across them.
- 05 The model What the reasoning layer actually contributes, what it cannot know, and why treating model choice as the whole architecture leads people astray.
- 06 The harness The program that runs the loop. It decides context, tools, retries, memory, and when to stop, which is where most agent behaviour actually comes from.
- 07 Open interfaces The four contracts an analytics agent speaks through, why each should be a specification rather than a product, and what a closed one costs later.
The data substrate
The open lakehouse underneath: what each Apache project settles, and where each one stops.
- 08 Why an open lakehouse Agents multiply the number of readers and the number of questions. That pressure breaks architectures that assume one engine, one copy, and predictable queries.
- 09 The semantic layer as an agent contract The place where a business writes down what its terms mean. Without it, an agent guesses at definitions, and a fluent guess is worse than an error.
- 10 Apache Iceberg The table format that lets many readers and writers share one set of files safely, which is exactly the condition agentic analytics creates.
- 11 Apache Polaris An open catalog that resolves table names, decides who may read them, and hands out credentials scoped to just those files. The enforcement point agents cannot route around.
- 12 Apache Arrow A standard in-memory layout for tabular data, so results move between the engine, the tool, and the agent without being repeatedly converted.
- 13 Apache Parquet The columnar file format most lakehouse data sits in. Its statistics are what let an agent's exploratory query read a fraction of the table instead of all of it.
- 14 Apache Ossie An incubating project defining a vendor-neutral standard for semantic metadata, so a metric definition is portable rather than trapped in one tool.
Running it for real
Governance, evaluation, cost, portability, and the order to do the work in.
- 15 Governance for agents Identity, scoped credentials, and audit, arranged so that an agent cannot reach what its user cannot reach, and so you can prove it afterwards.
- 16 One copy, many readers The architectural property that decides whether agentic analytics scales past a pilot, and the specific way copy sprawl produces disagreeing answers.
- 17 Evaluation and trust How to know whether an analytics agent is right, why accuracy on a benchmark is not the question, and what to measure instead.
- 18 Cost and latency Agentic analytics changes the shape of the workload from few large queries to many small ones, which moves where the money goes and what needs optimising.
- 19 Portability and lock-in What it would actually cost to replace each component of an agentic analytics stack, and why the semantic layer is now the most likely trap.
- 20 Rolling this out enterprise wide What separates an agent pilot that impresses a steering committee from a capability a whole organisation uses, and the order to do the work in.