The response log keeps what the agent said, not the path it took. The Foundry trace keeps the order of the steps, the failures and the tokens of each turn, and leaves the content to a protected table. See what the trace shows, who can see the content and what changed in Agent Framework 1.22.0, with an example run locally.
Declaring a quality rule is not blocking the data. In Delta, NOT NULL and CHECK block; in Lakeflow, an expectation with no action retains the row; keys and unique only declare; MERGE ignores the new column. See what each layer does, how to build a quarantine and how to read the count, with an example run locally.
An agent can consume Copilot Credits in Work IQ, capacity in Fabric, and tokens or PTUs in Foundry. Examine the meters, a calculated example, and how to separate consumption, attributed cost, and the invoice without counting an operation twice.
Learn to discover paths, inspect schemas, and read messages with Work IQ MCP. A read-only example shows why fewer tools do not remove access, coverage, and authorization boundaries.
The slide had a single box labeled Microsoft IQ, and the relationship manager’s agent got one question right out of four. Microsoft IQ is the name of a set: Work IQ, Fabric IQ, Foundry IQ and Web IQ, each with its own question, data home, status per component, identity and boundary. This article maps the four layers: what is GA and what is in preview, who answers in each one, where they meet and how far the data goes.
The deploy went green, and a full refresh wiped the bronze table that Kafka could no longer replay. In Databricks Lakeflow, the bundle carries the code from dev to prod, but state stays in each environment: the deployment record, the streaming checkpoints, the tables themselves and the identity that runs the pipeline. This article shows the four states the bundle does not carry, what each command can delete and the guards you declare in the bundle before the first production deploy.