General-Purpose Agents Are Mature. Do Vertical Apps Still Need Their Own?
How I let external Agents keep their general capabilities, use a built-in Agent for a deeper analytics workflow, and connect both to one control plane.
Read article →Lantide Data Blog
Ideas and field guides for reliable, reviewable AI-assisted data analysis.
AI Analysis Insights
View all →AI Made Analysis Faster. Now It Is Harder to Explain Where a Conclusion Came From
Once AI Agents find data, write SQL, run notebooks, and revise reports, chat history and file versions no longer preserve the full evidence chain. This is why data analysis needs Analysis Lineage.
Read article →The Limits of Skills in Data Analytics: Why Skills Are Not Enough for Real-World Data Analysis
A Skill can preserve an analytical method and package SQL or context from a specific case. Real analysis also depends on data versions, execution state, human decisions, evidence, and limitations.
Read article →What Is the Difference Between an AI Agent and a Chatbot? From Answering Questions to Completing Verifiable Work
An AI agent does more than produce longer answers: it uses tools based on state, advances multi-step work, and leaves verifiable deliverables. This article explains the differences, evaluation criteria, use cases, and adoption boundaries through data analysis.
Read article →The Greatest Risk in AI Data Analysis Is Not a Calculation Error—It Is Not Knowing How the Number Was Calculated
The hardest AI analysis errors to detect come from definitions, denominators, joins, and time windows. This article presents four review layers: Plan, SQL, checkpoints, and limitations.
Read article →If Natural Language Can Query Data, Why Do We Still Need SQL in 2026?
Natural language lowers the barrier to querying data, but it cannot replace SQL as reviewable evidence for grain, joins, filters, and aggregation. The better division of work is AI drafting, SQL preserving evidence, and people reviewing it.
Read article →Why Should Formal Analysis Start with a Plan Before AI Executes?
A Plan aligns the decision question, denominator, grain, time window, and validation approach before data retrieval. Execute then becomes a clear human authorization boundary, preventing ambiguous assumptions from turning into official numbers.
Read article →What Is Reproducible AI Analysis?
Learn how reproducible AI analysis preserves inputs, SQL, assumptions, validation, and reports so teams can rerun results and explain every change.
Read article →AI Analysis Tools, Conversational BI, and Traditional BI: How Should They Divide the Work?
Analysis agents, conversational BI, and traditional BI serve different stages. Quick answers, definition exploration, and stable monitoring should not be confused. This article provides a five-dimensional selection matrix and three practical scenarios.
Read article →What Is Local-First AI Data Analysis?
Learn how local-first AI data analysis reduces data movement, queries local files, and preserves reusable work while clarifying cloud model boundaries.
Read article →Agent Governance
View all →Is Prompt Engineering Obsolete? Context Engineering Is What Makes or Breaks an Agent
Prompt engineering is not obsolete, but agents must also manage tools, data, state, history, and memory. Context engineering determines what the model actually sees on each turn.
Read article →Is a Larger Context Window Always Better? The Context Rot That Long Tasks Actually Face
A larger context window can hold more tokens, but that does not mean a model uses every passage equally reliably. Long tasks need compaction, structured artifacts, and on-demand loading to control context rot.
Read article →AI Agent Memory Is Not About Remembering Everything: Why Enterprise Knowledge Needs Approval
Long-term agent memory affects analysis across conversations, so enterprise knowledge needs provenance, scope, approval, and retirement. This article provides a practical Memory governance framework and Queued Knowledge approval flow.
Read article →What Is MCP, and Why Is It Becoming the Data and Tool Interface for AI Agents?
MCP connects AI applications, data, and tools through a standardized client-server protocol. This article explains its core components, security boundaries, and Lantide's two-way MCP integration.
Read article →Is a Database Safe Once It Is Connected Through MCP? Five Layers from Tool Access to Least Privilege
MCP standardizes connections but does not guarantee least privilege. Use host, credential, scope, capability, approval, and audit controls to review agent data access.
Read article →How Do You Put AI Agent Governance into Practice? Map Who Can Do What Before Writing Policy
AI Agent governance starts by defining capability boundaries among users, agents, tools, and data, then adding approval, monitoring, and recovery. Use this six-part capability map to assign owners and create testable controls.
Read article →Why Does AI Still Calculate the Wrong Answer When It Has the Schema? Data Analysis Needs Business Semantics
Table names and field types describe the shape of data, not the definitions of valid customers, revenue, conversion, or time windows. Learn which business semantics AI analysis needs and how to turn definitions into a reviewable contract.
Read article →Integrate with Lantide
View all →Claude Code and Codex for Reusable Analysis
Use Lantide as a local MCP workspace for Claude Code and Codex, keeping plans, SQL, evidence, and reports reusable across data analysis sessions.
Read article →Why Do You Still Need Lantide When Using PostHog?
PostHog excels at product events, funnels, and experiment significance. When local CRM or finance data should not move to the cloud, or you need reviewable SQL and a formal Report, use Lantide for local diagnosis.
Read article →Why Do You Still Need Lantide When Using Hex?
Hex excels at collaborative cloud notebooks, reactive execution, and app publishing. When data must stay local or ad hoc exploration does not deserve a cloud project, use Lantide for local-first analysis and send sanitized results back to Hex.
Read article →Why Do You Still Need Lantide When Using dbt?
dbt is built for production transformations, tests, and CI. For one-off hypothesis validation, use Lantide as a local sandbox, then write standard SQL back to the dbt repository once the definition is proven.
Read article →Why Do You Still Need Lantide When Using Notion?
Notion is suited to PRDs, knowledge bases, and database charts, but it is not a local SQL engine. Run rerunnable analysis in Lantide, then put the HTML or Markdown result back in Notion so planning pages cite evidence-backed conclusions.
Read article →Why Do You Still Need Lantide When Using Obsidian?
Obsidian and Dataview excel at local Markdown knowledge and note metadata queries. Lantide adds DuckDB SQL, rerunnable analysis lineage, and governed Agent memory; the two connect through files rather than replacing each other.
Read article →Data Analysis Practice
View all →How to Repeat a Weekly CSV or Excel Report Without Starting Over
A practical workflow for rerunning weekly CSV or Excel analysis while preserving inputs, metric definitions, SQL, validation checks, and report limitations.
Read article →Before Analyzing a CSV with AI, Run These 8 Data Quality Checks
AI can explore CSV files quickly, but it cannot define correct data for you. This checklist covers encoding, types, nulls, duplicates, keys, time zones, units, and outliers with rerunnable SQL checkpoints.
Read article →Query Excel and CSV with SQL—No Database Installation Required: Who Is DuckDB For?
DuckDB is an embedded analytical database that queries local CSV, Parquet, and Excel files directly. It excels at file-based ad hoc analysis but does not replace a shared warehouse or scheduled ETL.
Read article →How to Review AI-Generated SQL: A 7-Point Checklist Beyond 'Does It Run?'
Successful execution does not mean AI-generated SQL answered the right question. Review grain, JOINs, filters, NULLs, time, denominators, and LIMITs with these minimal validation queries.
Read article →Why Does Everyone Calculate Conversion Differently? Align Denominators, Events, and Time Windows First
A funnel conversion rate has no single universal formula. User versus event grain, cohort versus calendar windows, event order, and cancellation rules all change the answer.
Read article →Numbers Explode After a JOIN? The Fan-Out Trap AI Analysis Often Misses
When totals grow after a JOIN, the aggregation is usually not broken—the tables have incompatible grains. Use these order examples and SQL checks to catch duplicate counting before delivery.
Read article →Quick Question or Formal Analysis? Decide by Risk, Not Length
Quick and formal analysis differ not by question length but by the impact of a wrong answer and the chance it will be reused. This two-dimensional matrix helps choose the right workflow.
Read article →Data Lineage Is Not Just for Big Data Platforms: Even a Local Report Should Show Its Origins
Data lineage traces sources, transformations, and outputs. Even with local CSV files and a monthly report, reusable work benefits from minimal lineage, naming rules, and a rerun path.
Read article →What Are the 6 Essential Parts of a Trustworthy AI Analysis Report?
A trustworthy AI report needs more than a summary: decision question, definitions, findings, traceable evidence, limitations, and next steps. Use this six-part template tied to SQL evidence.
Read article →Team Adoption
View all →PMs Can Review AI Analysis Without SQL: Ask These 6 Questions Before Execute
A PM need not rewrite SQL line by line. Confirm the decision, population, denominator, time, exclusions, and validation before Execute to protect business definitions and accountability.
Read article →How Should Analysts Work with AI Agents? Save Human Time for Definitions, Validation, and Interpretation
Agents can accelerate schema exploration, SQL drafts, and report drafts. Analysts should own problem definition, business metrics, validation, anomaly interpretation, and decision communication.
Read article →Before an External AI Agent Touches Company Data: A Platform Team Checklist
Before connecting an external Agent, define sources, capabilities, workspace boundaries, credential lifecycle, formal evidence, writer ownership, audit, and recovery.
Read article →From First Pilot to Team Adoption: A 30-Day Roadmap for Governed AI Analysis
A 30-day AI analysis pilot should begin with a real, controlled retrospective, then establish quality, review failures, permissions, and expansion criteria.
Read article →