Signal SentrySearchUpdated Nov 20, 05:30 UTCAM Drop
Agents · industry

Agents in Data analytics

Agent deployments and launches in Data analytics, from the Drops.

From the Drops

AgentsData analyticsLiveHuman in loop: unclear

Google adds agent telemetry, token quotas and evals across BigQuery and Looker

Google Cloud says conversation logging to customer-owned BigQuery tables and agent monitoring dashboards are GA, with daily token quotas per project, user or agent in preview. ADK and LangGraph agents can stream traces too.

Why it matters: By design, logging skips turns whose sources use row-level security or masked data. Check that gap against your audit needs before relying on these logs.

From Drop #085 · Sat, Nov 14, 2026 · Morning
AgentsData analyticsLiveHuman in loop: yes

Databricks makes Genie in Slack generally available, acting with each asker's permissions

Databricks says Genie answers in Slack DMs and channels under the asking user's identity and Unity Catalog rights, and can edit documents, tickets and records via MCP connectors only after that user approves each change.

Why it matters: A ready pattern for chat agents: actions run as the person asking, not a shared bot. Decide whether channel answers default to private and which MCP tools need approval.

From Drop #082 · Thu, Nov 12, 2026 · Evening
AgentsData analyticsLiveHuman in loop: unclear

Nvidia open-sources Auto Ontology, a data-meaning layer agents query over MCP

Nvidia's Apache-2.0 library builds an ontology from enterprise metadata and checks agent-written SQL against certified definitions, per its README. Without Vault, UI-added database credentials are stored unencrypted in Postgres.

Why it matters: Nvidia's pitch is that agents need trusted metric definitions, not just database access. If you try it, configure Vault, set token expiry and keep its internal API port private.

From Drop #064 · Tue, Nov 3, 2026 · Evening
AgentsData analyticsLiveHuman in loop: yes

AWS shares how its Deep Insight multi-agent analyst made it to production

AWS's Solutions Architecture team says eight agents split the work: a Haiku model routes requests, an Opus planner drafts steps for user approval, and a Validator re-runs each calculation. A code interpreter runs on AWS Fargate.

Why it matters: The lessons: route easy requests to small models, plan before acting, verify numbers. Note the web version auto-approves a plan after 300 seconds with no reply.

On the Frontier watch →From Drop #039 · Thu, Oct 22, 2026 · Morning
AgentsData analyticsTestingHuman in loop: no

Preprint: Data World synthesizes training worlds for data agents

Researchers report a multi-agent engine yielding 2,135 training tasks from 1,037 worlds and a 100-task benchmark that ten frontier models find hard, especially insight discovery. Their RL-trained model gains 20.90 on DABstep-Hard.

Why it matters: The authors say synthetic environments address the cost, privacy and IP limits that make real company files hard to use for training data agents.

From Drop #031 · Sun, Oct 18, 2026 · Morning