Hacker News: matthieu_bl

Google WeatherNext 3

matthieu_bl — Thu, 03 Sep 2026 16:06:08 +0000

Article URL: https://deepmind.google/science/weathernext/

Comments URL: https://news.ycombinator.com/item?id=49552299

Points: 23

# Comments: 1

Revolut Receives Conditional Approval to Form a US National Bank

matthieu_bl — Thu, 03 Sep 2026 15:34:31 +0000

Article URL: https://www.revolut.com/news/revolut_receives_conditional_approval_from_u_s_office_of_the_comptroller_of_the_currency_to_form_a_national_bank/

Comments URL: https://news.ycombinator.com/item?id=49551726

Points: 2

# Comments: 0

Open AI X post on Astra

matthieu_bl — Thu, 03 Sep 2026 15:03:40 +0000

Article URL: https://twitter.com/OpenAI/status/2095527557924082061

Comments URL: https://news.ycombinator.com/item?id=49551018

Points: 12

# Comments: 4

Forty production-ready industry data models

matthieu_bl — Thu, 03 Sep 2026 12:51:21 +0000

Article URL: https://github.com/databricks-industry-solutions/lakehouse-industry-data-models

Comments URL: https://news.ycombinator.com/item?id=49549309

Points: 1

# Comments: 0

New comment by matthieu_bl in "Can I opt out of my input or output data being used for training?"

matthieu_bl — Wed, 02 Sep 2026 14:45:16 +0000

Summary of the different scenarios

Service: Vibe Plan: Non-Enterprise Default: Opted in Opt-out possible? Yes

Service: Vibe Plan: Enterprise Default: Opted out Opt-out possible? Yes (admin-managed)

Service: Mistral Studio/API Plan: Not specified Default: Not stated, I assume opted in Opt-out possible? Yes

New comment by matthieu_bl in "Show HN: Assemble context for analytics agents from schemas, SQL and docs"

matthieu_bl — Mon, 31 Aug 2026 13:45:20 +0000

Hi HN, a bit of background on this project.

I’m building Cassis, a tool for maintaining the context used by analytics agents.

Of course, before you can maintain context, you need a context to begin with.

By context, we mean the information an analytics agent needs to generate the right queries to answer questions reliably: what business domains that data covers, what tables and columns mean, what are governed metrics and joins, etc.

So far, we’ve been building that first version manually with customers. They send us what they have (schema dumps, dbt repos, glossaries, internal documentation, query logs, dashboard exports, and so on) and we assemble it with the help of coding agents. Eventually, we want to automate as much of this as possible in the product.

In the meantime, I wanted teams to be able to assemble their initial context without us, so I packaged our internal methodology into skill (instructions, scripts, and review checkpoints). The guiding principles behind it are: 1. you already have most of what an analytics agent need in your repo and internal docs and 2. you should never let an LLM invent business meaning for you. So bootstrapping context is mostly about recovering what already exists, connecting it to the right data objects, and keeping track of what each source can actually support.

The skill takes in: your schema dump, dbt code, plus glossaries, docs, dashboards and query logs if you have them. During the process, it generates a list of questions to answer for key decisions (e.g. how to cut your business into relevant domains), when it detects gaps, and when it detects ambiguities. The result is a repo with a first version of your context as YAML and markdow files, in a file tree, that you can feed your analytics agent (or a PR enriching your dbt repo with structured metadata and docs): metrics, business domains, joins.

It runs locally with your favorite coding agent and doesn’t require a Cassis account. We’ve built and tested the workflow with Claude Code so far.

Happy to get your feedback on the approach and the skill itself.

Show HN: Assemble context for analytics agents from schemas, SQL and docs

matthieu_bl — Mon, 31 Aug 2026 13:45:04 +0000

Article URL: https://github.com/GetCassis/ontology-bootstrap

Comments URL: https://news.ycombinator.com/item?id=49509733

Points: 3

# Comments: 1

The Shape and Feel of the Post-AI Data Stack

matthieu_bl — Mon, 31 Aug 2026 10:19:53 +0000

Article URL: https://www.iandmacomber.com/blog/post-ai-data-stack/

Comments URL: https://news.ycombinator.com/item?id=49507952

Points: 2

# Comments: 0

Integrations That Write Themselves

matthieu_bl — Thu, 27 Aug 2026 12:46:27 +0000

Article URL: https://builders.ramp.com/post/integrations-that-write-themselves

Comments URL: https://news.ycombinator.com/item?id=49463978

Points: 1

# Comments: 0

Bolt migrated 10M monthly Looker queries from Presto to Databricks

matthieu_bl — Wed, 26 Aug 2026 09:31:43 +0000

Article URL: https://bolt.eu/en/blog/migrating-looker-to-databricks/

Comments URL: https://news.ycombinator.com/item?id=49446186

Points: 3

# Comments: 0

Reconstructing the benchmark behind Luc Julia's 64% LLM reliability claim

matthieu_bl — Wed, 26 Aug 2026 08:00:26 +0000

Article URL: https://github.com/angeluriot/Julia_bench

Comments URL: https://news.ycombinator.com/item?id=49445460

Points: 4

# Comments: 0

Auditing 5,284 dbt models across 13 public repos for analytics-agent readiness

matthieu_bl — Tue, 25 Aug 2026 16:02:13 +0000

Article URL: https://blog.getcassis.com/dbt-context-for-analytics-agents/

Comments URL: https://news.ycombinator.com/item?id=49436311

Points: 1

# Comments: 1

New comment by matthieu_bl in "We built a structured entity graph for an AI agent. Then we removed most of it"

matthieu_bl — Tue, 25 Aug 2026 13:34:03 +0000

A way for it to know is to build a maintenance loop around the context.

Technical changes are relatively easy to track. A system can monitor code diffs, schema changes, failed queries, etc and update or flag the affected context.

Business meaning changes are harder to detect, but users reveal them whenever they use the agent: through the questions they ask (and that the existing context cannot answer), the ambiguities it encounters, and the corrections or clarifications they provide. Your maintenance system can capture those signals, connects them to the relevant parts of the context, and proposes an update.