{"id":3491,"date":"2026-08-08T13:27:00","date_gmt":"2026-08-08T13:27:00","guid":{"rendered":"https:\/\/futurenews24.com\/index.php\/2026\/08\/08\/snowflake-ai-agents-semantic-governance\/"},"modified":"2026-08-09T08:59:04","modified_gmt":"2026-08-09T08:59:04","slug":"snowflake-ai-agents-semantic-governance","status":"publish","type":"post","link":"https:\/\/futurenews24.com\/index.php\/2026\/08\/08\/snowflake-ai-agents-semantic-governance\/","title":{"rendered":"Governing AI Brokers: Deploying Semantic Views on Snowflake"},"content":{"rendered":"


\n<\/p>\n

\n

This yr, many information groups have added AI brokers to their roadmaps. The thrill is actual: an agent that turns a two-day evaluation right into a two-minute dialog can change how analysts and enterprise groups work collectively.<\/p>\n

However brokers are solely as dependable as the info basis beneath them. Level them at uncooked tables or outdated metadata, and so they could sound convincing whereas being incorrect. This text outlines a sensible framework for producing and deploying ruled semantic views on Snowflake.<\/p>\n

Why Agent High quality Breaks Down<\/h2>\n

Three failure patterns present up repeatedly as soon as brokers transfer from demo to manufacturing:<\/p>\n

Governance will get traded for velocity. Groups below strain to ship skip questions on information integrity and entry management till an agent is already answering questions for the enterprise.<\/p>\n

Duplication proliferates. With no shared course of, completely different groups construct overlapping brokers that reply the identical query in subtly completely different \u2013 and inconsistent \u2013 methods.<\/p>\n

Solutions are non-deterministic. The identical query, requested twice, returns two completely different numbers. That\u2019s worse than being reliably incorrect, as a result of no one is aware of when to mistrust the reply.<\/p>\n

All three hint again to 1 root trigger: there\u2019s no standardized, enforced course of governing how a semantic definition will get created, reviewed, versioned, and promoted. Tooling that helps you creator semantic views sooner doesn\u2019t resolve this by itself \u2013 velocity and governance are completely different axes, and a corporation can have loads of one and little or no of the opposite.<\/p>\n

What a Semantic Layer Really Does<\/h2>\n

Ask 5 groups \u201cwhat’s the complete variety of energetic members in Q1 2026?\u201d and not using a shared semantic layer, and it’s possible you’ll get 5 completely different numbers. Every staff applies its personal filters, joins its personal tables, and defines \u201cenergetic\u201d in another way \u2013 and an LLM requested the identical query with no grounding will hallucinate a sixth reply that sounds simply as assured as the opposite 5.<\/p>\n

A semantic layer solves this by sitting between the uncooked warehouse and each client \u2013 dashboards, spreadsheets, and now AI brokers \u2013 and answering three questions the identical method, each time: which tables maintain this information, what filters apply, and what\u2019s the aggregation logic and grain. Snowflake\u2019s personal documentation frames this as addressing the mismatch between how enterprise customers describe information and the way it\u2019s really saved in database schemas \u2013 for instance, defining \u201cweb income\u201d as soon as, persistently, as SUM(gross_revenue * (1 – low cost)), somewhat than leaving the calculation to be reinvented in each report.<\/p>\n

The place This Lives in Snowflake<\/h2>\n

In Snowflake, the semantic layer is carried out as a semantic view, a schema-level object saved immediately within the database that defines enterprise metrics and fashions entities and their relationships, which Cortex Analyst \u2013 Snowflake\u2019s text-to-SQL software, can then question in pure language. Cortex Agent is the AI orchestrator that holds a number of semantic views, alongside search providers and customized instruments, and decides which useful resource solutions a given query \u2013 the identical structure underpinning Snowflake CoWork(previously Snowflake Intelligence).<\/p>\n

Right here\u2019s what that specification appears like stuffed in with an actual instance. Beneath is a semantic view over a SaaS billing dataset \u2013 two logical tables (billing and clients), joined on buyer ID, with three licensed income metrics outlined as soon as:<\/p>\n

title: SAAS_BILLING
\ndescription: Combines buyer data with subscription billing particulars
\n to help licensed MRR, web MRR, and churned income metrics.
\ntables:
\n – title: BILLING
\n base_table: { database: FINANCE, schema: ANALYTICS, desk: FCT_SAAS_BILLING }
\n dimensions:
\n – title: BILLING_DATE
\n expr: BILLING_DATE
\n data_type: DATE
\n – title: PLAN_TYPE
\n expr: PLAN_TYPE
\n data_type: VARCHAR(20)
\n details:
\n – title: MRR_AMOUNT
\n expr: MRR_AMOUNT
\n data_type: NUMBER(10,2)
\n metrics:
\n – title: TOTAL_MRR
\n expr: SUM(billing.MRR_AMOUNT)
\n – title: NET_MRR
\n expr: SUM(billing.MRR_AMOUNT) – SUM(billing.DISCOUNT_AMOUNT)
\n – title: CHURNED_REVENUE
\n expr: SUM(IFF(billing.IS_ACTIVE = FALSE, billing.MRR_AMOUNT, 0))
\n primary_key: { columns: [BILLING_ID] }
\n – title: CUSTOMERS
\n base_table: { database: FINANCE, schema: ANALYTICS, desk: DIM_CUSTOMERS }
\n dimensions:
\n – title: COMPANY_NAME
\n expr: COMPANY_NAME
\n data_type: VARCHAR(100)
\n – title: INDUSTRY
\n expr: INDUSTRY
\n data_type: VARCHAR(50)
\n primary_key: { columns: [CUSTOMER_ID] }
\nrelationships:
\n – title: CUSTOMER_BILLING
\n left_table: BILLING
\n right_table: CUSTOMERS
\n relationship_columns:
\n – { left_column: CUSTOMER_ID, right_column: CUSTOMER_ID }<\/p>\n

(Trimmed for readability \u2013 the complete generated file consists of each column remark and entry modifier. Repo has the complete semantic definition )<\/p>\n

What\u2019s not in query is that this object works. What’s in query is: how does a semantic view like this get created within the first place?<\/p>\n

The Two Governance Pillars Behind Each Licensed Metric<\/h2>\n

Earlier than the pipeline itself, it\u2019s price being exact concerning the two ruled inputs it is dependent upon.<\/p>\n

The Information Catalog: One authoritative supply for enterprise descriptions, information varieties, sensitivity tags (PII\/PHI), pattern values, and certification standing for each column and desk. On this implementation that\u2019s Snowflake Horizon \u2013 tags are set on the column degree or desk degree. The catalog comprises the info kind, description, synonyms, pattern values and so forth., and a dynamic masking coverage can prohibit who ever sees a flagged column. A certification_status=”Licensed” tag is the inexperienced gentle for th at column\u2019s metadata for use in a semantic view in any respect.<\/p>\n

The Metric Stock: A single ruled dwelling for each metric system, with an outline, enterprise proprietor, supply desk, area, sensitivity classification, and critically a certification standing. The operative rule: every metric is outlined as soon as and reused in all places, and \u201cas soon as\u201d is gated behind an precise sign-off from a website proprietor or information steward. That is what’s going to resolve the issue that the identical metric may be answered 6 other ways throughout groups.<\/p>\n

The Framework: A Governance Harness for Semantic View Era<\/h2>\n

The core thought is straightforward to state: deal with semantic view technology as a ruled software program launch, not a one-off modeling train. In apply meaning 5 parts, every implementing a rule that a casual course of usually leaves optionally available. Earlier than strolling by way of every one, it helps to see the entire pipeline finish to finish, after which how that pipeline suits into the broader Snowflake structure \u2013 the 2 diagrams beneath cowl precisely that. <\/p>\n

Governance Framework Circulate Diagram<\/h3>\n
\n
\"Semantic<\/figure>\n<\/div>\n

Zooming out one degree: this pipeline is barely the build-time half of the image. Determine 2 reveals the way it suits alongside the techniques that truly devour its output \u2013 Cortex Analyst, Cortex Brokers, Snowflake Cowork, and the BI instruments mentioned later on this article. <\/p>\n

System structure<\/h3>\n
\n
\"Governance<\/figure>\n<\/div>\n

The total code for the beneath parts breakdown is right here.<\/p>\n

An orchestration script connects to Horizon and the metric stock and pulls, for a given area, solely licensed metric formulation and tagged schema. This step is deterministic \u2013 it retrieves already-approved details, it doesn\u2019t infer something:<\/p>\n

cursor.execute(f”””
\n SELECT metric_name, description, expression, base_table
\n FROM GOVERNANCE_DB.SEMANTICS.METRIC_INVENTORY
\n WHERE certification_status=”Licensed”
\n AND base_table IN ({table_list})
\n“””)
\nmetrics = [
\n {“metric_name”: r[0], “description”: r[1], “expression”: r[2], “desk”: r[3]}
\n for r in cursor.fetchall()
\n]<\/p>\n

The method pulls schema and tag context immediately from Horizon tag references.<\/p>\n

catalog_query = f”””
\n WITH physical_schema AS (
\n SELECT table_schema, table_name, column_name, data_type, remark AS column_description
\n FROM {database}.INFORMATION_SCHEMA.COLUMNS
\n WHERE table_schema IN ({schema_list}) AND table_name IN ({table_list})
\n ),
\n horizon_tags AS ( {real_time_tags_cte} )
\n SELECT p.table_name, p.column_name, p.data_type, p.column_description, t.tag_value AS privacy_tag
\n FROM physical_schema p
\n LEFT JOIN horizon_tags t
\n ON p.table_name = t.table_name AND p.column_name = t.column_name
\n“””<\/p>\n

That is the primary structural distinction from usage-inference approaches price stating plainly: this pipeline solely ever proposes definitions that hint again to a pre-approved supply, somewhat than a definition surfaced as a result of it was the most typical sample in somebody\u2019s question historical past. Reputation is a helpful discovery sign; it isn\u2019t the identical declare as governance sign-off.<\/p>\n

Part 2 \u2013 Constrained Era<\/h3>\n

An LLM of selection (Claude, GPT, Qwen, GLM and so forth) converts the extracted context right into a strictly formatted dbt mannequin utilizing the dbt_semantic_view package deal syntax. The important thing management is constraint: the system immediate fixes the output schema and clause order and requires each generated area to map to a catalog or stock entry as an alternative of the mannequin\u2019s personal judgment. A trimmed model of the particular system immediate used on this pipeline:<\/p>\n

SYSTEM_PROMPT = “””You might be an knowledgeable Information Engineer constructing dbt semantic
\nfashions for Snowflake.<\/p>\n

You’ll obtain a JSON context payload with:
\n – metrics: licensed metric definitions (metric_name, expression, desk)
\n – catalog: bodily columns per desk (desk, column, data_type,
\n description, tag)
\n – table_descriptions: [{ table, description }]
\n supply desk in Snowflake<\/p>\n

Produce ONE legitimate dbt mannequin file utilizing the Snowflake-Labs dbt_semantic_view
\npackage deal. Output ONLY the uncooked file contents. No prose, no markdown fences,
\nno preamble.<\/p>\n

Required clauses, on this actual order, separated by newlines:<\/p>\n

{{ config(materialized=’semantic_view’) }}<\/p>\n

TABLES (
\n AS {{ supply(”, ”) }}
\n [ PRIMARY KEY () ] [ COMMENT = ” ]
\n )<\/p>\n

RELATIONSHIPS (
\n AS () REFERENCES
\n )<\/p>\n

FACTS (
\n . AS [ COMMENT = ‘…’ ] [, …]
\n )<\/p>\n

DIMENSIONS (
\n . AS [ COMMENT = ‘…’ ] [, …]
\n )<\/p>\n

METRICS (
\n . AS [ COMMENT = ‘…’ ] [, …]
\n )<\/p>\n

COMMENT = ”<\/p>\n

PII dealing with: any column whose `tag` comprises ‘PII’ (case-insensitive) MUST
\nbe excluded from FACTS, DIMENSIONS, and METRICS.
\n“””<\/p>\n

As a result of the extracted context consists of the PII tag, the mannequin robotically omits or masks flagged columns as an alternative of creating case-by-case judgments.<\/p>\n

Past PII filtering, two controls implement governance:<\/p>\n

Predictable output:\u00a0Prohibit the mannequin to a strict, non-conversational format so reviewers can confirm the generated code persistently and effectively.<\/p>\n

Information Integrity: The mannequin should solely use the precise information offered within the enter, which prevents it from \u201challucinating\u201d or inventing its personal columns and formulation.<\/p>\n

By making use of this method immediate to the catalog and metric context, the pipeline robotically generates the required semantic view dbt mannequin, changing handbook coding with verified, automated output which might be 95% correct.<\/p>\n

Part 3 \u2013 Human Certification Gate<\/h3>\n

Nevertheless correct the LLM\u2019s output normally is, manufacturing metrics can\u2019t tolerate even a small share of hallucinated logic. So the generated definition is rarely merged robotically \u2013 it\u2019s dedicated to a brand new department and opened as a pull request in opposition to the semantic-layer dbt repository. The orchestrator operate ties 4 smaller GitHub API calls collectively:<\/p>\n

def open_pr_for_file(proprietor, repo, file_path, content material, commit_message,
\n pr_title, pr_body, department, base=”grasp”,
\n token=””, draft=False) -> str:
\n if not token:
\n elevate ValueError(“GITHUB_TOKEN is required”)
\n base_sha = get_default_branch_sha(proprietor, repo, token, base=base)
\n create_branch(proprietor, repo, base_sha, department, token)
\n put_file(proprietor, repo, file_path, content material, commit_message, department, token)
\n return create_pr(proprietor, repo, pr_title, pr_body, department, base,
\n token, draft=draft)<\/p>\n

Every of these 4 calls is a small, single-purpose wrapper across the GitHub REST API \u2013 intentionally stored easy so the evaluate path stays legible:<\/p>\n

# Create a brand new department off the bottom commit
\ndef create_branch(proprietor, repo, base_sha, new_branch, token) -> None:
\n r = requests.put up(
\n f”{API}\/repos\/{proprietor}\/{repo}\/git\/refs”,
\n headers=_headers(token),
\n json={“ref”: f”refs\/heads\/{new_branch}”, “sha”: base_sha},
\n timeout=30,
\n )
\n _check(r)<\/p>\n

# Lookup the present file SHA, if it already exists on this department
\ndef get_file_sha(proprietor, repo, path, department, token) -> Optionally available[str]:
\n r = requests.get(
\n f”{API}\/repos\/{proprietor}\/{repo}\/contents\/{path}”,
\n headers=_headers(token), params={“ref”: department}, timeout=30,
\n )
\n if r.status_code == 404:
\n return None
\n return _check(r).get(“sha”)<\/p>\n

# Commit the generated semantic view file to that department
\ndef put_file(proprietor, repo, path, content material, message, department, token) -> dict:
\n payload = {
\n “message”: message,
\n “content material”: base64.b64encode(content material.encode(“utf-8”)).decode(“ascii”),
\n “department”: department,
\n }
\n current = get_file_sha(proprietor, repo, path, department, token)
\n if current:
\n payload[“sha”] = current
\n r = requests.put(
\n f”{API}\/repos\/{proprietor}\/{repo}\/contents\/{path}”,
\n headers=_headers(token), json=payload, timeout=60,
\n )
\n return _check(r)<\/p>\n

# Open the PR for the info steward to evaluate
\ndef create_pr(proprietor, repo, title, physique, head, base, token,
\n draft=False) -> str:
\n r = requests.put up(
\n f”{API}\/repos\/{proprietor}\/{repo}\/pulls”,
\n headers=_headers(token),
\n json={“title”: title, “physique”: physique, “head”: head,
\n “base”: base, “draft”: draft},
\n timeout=30,
\n )
\n return _check(r)[“html_url”]<\/p>\n

A website-mapped information steward \u2013 the named proprietor from the metric stock \u2013 opinions the diff in opposition to the certification rubric outlined within the subsequent part. It is a arduous gate: the CI pipeline blocks deployment with out an approving evaluate from a certified reviewer, enforced the identical method a manufacturing codebase enforces required reviewers.<\/p>\n

Part 4 \u2013 CI\/CD Lifecycle<\/h3>\n

After approval and merge, Git variations the definition like another code artifact, preserving historical past, promotion workflows, and rollback functionality. That is what offers the group one thing advert hoc semantic-view creation structurally can not: an audit path answering, for any metric on any date, precisely which commit produced it and who permitted it.<\/p>\n

Part 5 \u2013 Native Deployment<\/h3>\n

Merging to the primary department triggers a GitHub Actions workflow that runs dbt construct, compiling the licensed mannequin right into a native Snowflake SEMANTIC VIEW object:<\/p>\n

on:
\n push:
\n branches: [master]
\n paths: [‘semantic_models\/models\/semantic_views\/**’]
\njobs:
\n deploy-dbt-models:
\n runs-on: ubuntu-latest
\n steps:
\n – makes use of: actions\/checkout@v4
\n – makes use of: actions\/setup-python@v5
\n with: { python-version: ‘3.10’ }
\n – run: pip set up -r necessities.txt
\n – run: dbt deps
\n – run: dbt debug
\n – run: dbt construct –select semantic_views<\/p>\n

From this level ahead, Cortex Analyst, Cortex Brokers, and Snowflake CoWork question the deployed object precisely as they’d one constructed another method. One implementation observe: Snowflake internally represents the semantic view as YAML. Groups can deploy it immediately from a YAML specification, however dbt SQL permits the human-review and CI\/CD workflow described above.<\/p>\n

Part 5b \u2013 An Optionally available Apache Ossie (previously OSI) Export<\/h3>\n

Price designing for earlier than you want it: emit the identical licensed artifact a second time in Apache Ossie format, alongside the Snowflake deployment. Ossie is the vendor-neutral, Apache 2.0 spec previously referred to as Open Semantic Interchange (OSI), renamed when it entered the Apache Incubator in July 2026. It describes datasets, metrics, dimensions, relationships, and context so instruments and brokers interpret them persistently.<\/p>\n

It suits the pipeline as a result of Ossie\u2019s constructing blocks map nearly immediately onto what Elements 1 by way of 3 already extract and certify. Including it’s a serialization step on high of governance work you\u2019ve already finished, not a brand new governance burden.<\/p>\n

Specs<\/h3>\n

Beneath is a sneak peek (full spec right here), illustrative somewhat than a part of the reference repo since nothing consumes it but, constructed in opposition to the general public\u00a0spec.yaml\u00a0schema and mapping the identical licensed\u00a0SAAS_BILLING\u00a0fields into\u00a0datasets\u00a0\/\u00a0relationships\u00a0\/\u00a0metrics:<\/p>\n

model: 0.1.1
\nsemantic_model:
\n – title: saas_billing
\n description: >
\n Combines buyer data with subscription billing particulars to
\n help licensed MRR, web MRR, and churned income metrics.
\n ai_context: >
\n Use this mannequin to reply questions on MRR, income churn, and
\n buyer billing. “Energetic” means IS_ACTIVE = TRUE on the billing document.
\n datasets:
\n – title: billing
\n supply: FINANCE.ANALYTICS.FCT_SAAS_BILLING
\n primary_key:
\n – BILLING_ID
\n fields:
\n – title: billing_date
\n expression:
\n dialects:
\n – dialect: SNOWFLAKE
\n expression: BILLING_DATE
\n dimension:
\n is_time: true
\n – title: plan_type
\n expression:
\n dialects:
\n – dialect: SNOWFLAKE
\n expression: PLAN_TYPE
\n – title: is_active
\n expression:
\n dialects:
\n – dialect: SNOWFLAKE
\n expression: IS_ACTIVE
\n – title: mrr_amount
\n expression:
\n dialects:
\n – dialect: SNOWFLAKE
\n expression: MRR_AMOUNT
\n description: Month-to-month recurring income quantity.
\n – title: clients
\n supply: FINANCE.ANALYTICS.DIM_CUSTOMERS
\n primary_key:
\n – CUSTOMER_ID
\n fields:
\n – title: company_name
\n expression:
\n dialects:
\n – dialect: SNOWFLAKE
\n expression: COMPANY_NAME
\n – title: trade
\n expression:
\n dialects:
\n – dialect: SNOWFLAKE
\n expression: INDUSTRY
\n relationships:
\n – title: customer_billing
\n from: billing
\n to: clients
\n from_columns:
\n – CUSTOMER_ID
\n to_columns:
\n – CUSTOMER_ID
\n metrics:
\n – title: churned_revenue
\n expression:
\n dialects:
\n – dialect: SNOWFLAKE
\n expression: SUM(IFF(billing.is_active = FALSE, billing.mrr_amount, 0))
\n description: Income misplaced from canceled plans
\n ai_context: >
\n Use this when the consumer asks about misplaced, canceled, or churned
\n income, not for questions on buyer counts.<\/p>\n

This export offers two fundamental benefits:<\/p>\n

Diminished conversion work, not magic portability: The expression.dialects construction lets a metric carry engine-specific expressions in a single widespread artifact, which cuts conversion effort for any client that implements the usual. It doesn’t make the metric robotically executable in all places \u2013 portability nonetheless is dependent upon every client supporting the related dialect and semantic conduct.<\/p>\n

AI-facing context, not a governance retailer: The ai_context area is for AI steerage \u2013 synonyms, examples, and utilization directions that assist an agent select the suitable metric. Maintain possession, certification proof, and approval historical past in your authoritative governance techniques (catalog, metric stock, PR data), or in clearly outlined customized extensions \u2013 not in ai_context.<\/p>\n

\n
\n
\n

Doesn\u2019t Snowflake already do that?<\/p>\n<\/blockquote>\n<\/blockquote>\n<\/blockquote>\n

No. Snowflake\u2019s tooling solves discovery. This framework solves certification.<\/p>\n

Autopilot finds statistical consensus in question historical past. That tells you what individuals already do, not what\u2019s appropriate, and two groups can produce two conflicting \u201cconsensus\u201d definitions with no proprietor compelled to reconcile them.<\/p>\n

Horizon Context helps brokers discover an current semantic view. It doesn\u2019t inform you whether or not that view was ever reviewed, by whom, or in opposition to what model historical past.<\/p>\n

Cortex Sense ranks undocumented information by relevance, recognition, and freshness, like net search. That\u2019s a distinct belief mannequin totally.<\/p>\n

None of it is a knock on Snowflake\u2019s roadmap. For licensed metrics, require a named approver and a versioned audit path earlier than launch.<\/p>\n

A technology framework has restricted worth when organizations can use licensed artifacts solely inside Snowflake AI surfaces.<\/p>\n

\n

Instrument
\n Integration
\n Standing
\n Metric reuse
\n Key limitations<\/p>\n

Energy BI
\n Energy BI consuming a Snowflake semantic view immediately
\n Unsupported
\n No
\n Energy BI doesn’t help non-native semantic fashions.<\/p>\n

Energy BI \/ Tableau (reverse)
\n Snowflake ingests .pbit\/.pbix information through Semantic View Autopilot
\n Public Preview
\n Partial
\n Works in the wrong way; Energy BI nonetheless can not question a stay Snowflake semantic view.<\/p>\n

Tableau (TDS export)
\n Export a semantic view as a Tableau Information Supply (.tds) from Snowsight
\n Public Preview
\n Sure
\n Auto-assigned dimensions and measures may have handbook adjustment.<\/p>\n

Sigma
\n Sigma consuming Snowflake semantic views
\n Beta
\n Partial
\n Limitations round joins, unions, APIs, derived metrics, inherited semantics, and AI assistant consciousness.<\/p>\n

Omni
\n Native two-way integration with Snowflake semantic views
\n Accessible
\n Sure
\n Some documented modeling and question edge circumstances stay.<\/p>\n

AtScale (XMLA bridge)
\n Expose Snowflake semantic views to Energy BI and Excel through XMLA
\n Personal Preview (introduced Jun 2, 2026)
\n Sure
\n Preview characteristic; verify availability and manufacturing readiness earlier than adoption.<\/p>\n<\/div>\n

Few takeaways:<\/p>\n

Snowflake nonetheless doesn’t help direct Energy BI consumption of semantic views, though it will probably ingest Energy BI property into Autopilot and a third-party XMLA bridge is in personal preview.<\/p>\n

Assist stays uneven throughout platforms; Omni affords a comparatively direct two-way integration, Tableau offers a preview TDS export that preserves metrics, and Sigma stays in beta with notable limitations.<\/p>\n

The place native help is absent, groups nonetheless must duplicate some modeling work, which open requirements akin to Apache Ossie purpose to scale back over time.<\/p>\n

A Certification Rubric, So \u201cHuman within the Loop\u201d Isn\u2019t a Slogan<\/h2>\n

The effectiveness of your evaluate course of relies upon totally on the standard of the guidelines used. At a minimal, each human reviewer ought to confirm these factors:<\/p>\n

Supply monitoring: Verify that each information level clearly traces again to an official, pre-approved checklist or catalog.<\/p>\n

Defend privateness:\u00a0Take away or prohibit entry to any column that comprises delicate private or well being info, and have a human confirm that the safety measure is in place.<\/p>\n

Method accuracy: Confirm that the mathematics and logic within the code precisely match the official permitted variations, making certain the generated code is exact somewhat than only a shut estimate.<\/p>\n

Make clear labels and naming:\u00a0Outline all labels and phrases clearly so the AI doesn’t confuse completely different metrics or ideas.<\/p>\n

Carry out sensible testing:\u00a0Run no less than one real-world take a look at for each main metric and confirm that the code produces appropriate outcomes on precise information earlier than finalizing it.<\/p>\n

Official approval: Get hold of formal sign-off from the area house owners or information stewards, confirming that they agree with the ultimate definitions.<\/p>\n

Make these necessities a compulsory code-approval guidelines so human-in-the-loop evaluate turns into an enforceable apply, not a buzzword.<\/p>\n

From Deployment to Reply: Cortex Analyst and Brokers<\/h2>\n

As soon as the SAAS_BILLING semantic view is stay, it may be opened immediately in Cortex Analyst and queried in pure language. Cortex Analyst resolves\u00a0TOTAL_MRR, teams by\u00a0PLAN_TYPE, and generates SQL robotically with out human-written queries or metric redefinition.<\/p>\n

\n
\"Cortex<\/figure>\n<\/div>\n

Cortex Analyst (Textual content-to-SQL)<\/p>\n

From there, builders can construct a Cortex Agent that makes use of this semantic view as one among its instruments. They’ll connect a number of semantic views and supply orchestration directions that specify when the agent ought to use every one.<\/p>\n

\n
\"Finance<\/figure>\n<\/div>\n

Cortex Agent<\/p>\n

Previewed inside Snowflake CoWork (Previewed inside Snowflake Cowork) the agent presents a conversational, chat-style expertise,<\/p>\n

\n
\"Snowflake<\/figure>\n<\/div>\n

The next picture traces precisely what occurs between the consumer typing that query and the reply showing on display:<\/p>\n

\n
\"Runtime<\/figure>\n<\/div>\n

This chain grounds each reply in licensed metrics and column definitions that handed the Part 3 certification gate, not in model-generated logic. That’s the objective of the pipeline: earlier than a query reaches Cortex Analyst in Step 4, reviewers have already outlined, reviewed, and versioned the that means of \u201cMRR\u201d lengthy earlier than any consumer asks a query.<\/p>\n

Conclusion<\/h2>\n

Agent high quality is essentially a governance drawback. A semantic view is barely as reliable as the method behind it, so organizations want certified-source extraction, constrained technology, human approval, and a whole CI\/CD audit path earlier than deployment.<\/p>\n

Deal with that course of as a regular in its personal proper, impartial of semantic-view authoring velocity. Including optionally available Apache Ossie export future-proofs licensed artifacts, whereas present BI-tool limitations present why portability nonetheless issues.<\/p>\n

Learn extra: Unlocking Information Insights with Snowflake Cortex Analyst<\/p>\n

\n

Analytics Vidhya Content material staff<\/p>\n<\/p><\/div>\n

Login to proceed studying and revel in expert-curated content material.<\/h4>\n

Maintain Studying for Free\n <\/p>\n

\n
\n
\n
\n

\"imag\"<\/p><\/div><\/div><\/div><\/div>\n

\n
\n
\n
\n
\n

Enter e-mail handle to proceed<\/h2>\n<\/p><\/div><\/div><\/div><\/div>\n<\/div>\n
\n
\n
\n
\n

Resend OTP<\/p>\n

Resend OTP in 45s<\/span><\/p>\n<\/p><\/div><\/div><\/div>\n<\/div>\n

\n
\n
\n

\"Popup<\/p><\/div><\/div>\n<\/div>\n

\n
\n
\n

\"AI<\/p><\/div><\/div>\n<\/div>\n<\/div>\n


\n
Source link <\/a><\/p>\n","protected":false},"excerpt":{"rendered":"

This yr, many information groups have added AI brokers to their roadmaps. The thrill is actual: an agent that turns a two-day evaluation right into a two-minute dialog can change how analysts and enterprise groups work collectively. However brokers are solely as dependable as the info basis beneath them. Level them at uncooked tables or […]<\/p>\n","protected":false},"author":1,"featured_media":3493,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"fifu_image_url":"https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2026\/08\/Ahh-here-we-go-again.webp","fifu_image_alt":"","jnews-multi-image_gallery":[],"jnews_single_post":[],"jnews_primary_category":[],"jnews_override_bookmark_settings":[],"jnews_social_meta":[],"jnews_override_counter":[],"footnotes":""},"categories":[7],"tags":[210,3868,3867,921,3781,1678],"class_list":["post-3491","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-data-science-mlops","tag-agents","tag-deploying","tag-governing","tag-semantic","tag-snowflake","tag-views"],"yoast_head":"\nGoverning AI Brokers: Deploying Semantic Views on Snowflake - Future News 24<\/title>\n<meta name=\"description\" content=\"A practical framework for generating, governing, and deploying certified semantic views on Snowflake using Data Build Tool.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/futurenews24.com\/index.php\/2026\/08\/08\/snowflake-ai-agents-semantic-governance\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Governing AI Brokers: Deploying Semantic Views on Snowflake - Future News 24\" \/>\n<meta property=\"og:description\" content=\"A practical framework for generating, governing, and deploying certified semantic views on Snowflake using Data Build Tool.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/futurenews24.com\/index.php\/2026\/08\/08\/snowflake-ai-agents-semantic-governance\/\" \/>\n<meta property=\"og:site_name\" content=\"Future News 24\" \/>\n<meta property=\"article:published_time\" content=\"2026-08-08T13:27:00+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2026-08-09T08:59:04+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2026\/08\/Ahh-here-we-go-again.webp\" \/>\n<meta name=\"author\" content=\"Future News 24\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:image\" content=\"https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2026\/08\/Ahh-here-we-go-again.webp\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Future News 24\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"19 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/futurenews24.com\\\/index.php\\\/2026\\\/08\\\/08\\\/snowflake-ai-agents-semantic-governance\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/futurenews24.com\\\/index.php\\\/2026\\\/08\\\/08\\\/snowflake-ai-agents-semantic-governance\\\/\"},\"author\":{\"name\":\"Future News 24\",\"@id\":\"https:\\\/\\\/futurenews24.com\\\/#\\\/schema\\\/person\\\/cecad1bde21cfc357cf70128144d6c83\"},\"headline\":\"Governing AI Brokers: Deploying Semantic Views on Snowflake\",\"datePublished\":\"2026-08-08T13:27:00+00:00\",\"dateModified\":\"2026-08-09T08:59:04+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/futurenews24.com\\\/index.php\\\/2026\\\/08\\\/08\\\/snowflake-ai-agents-semantic-governance\\\/\"},\"wordCount\":3741,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\\\/\\\/futurenews24.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/futurenews24.com\\\/index.php\\\/2026\\\/08\\\/08\\\/snowflake-ai-agents-semantic-governance\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/cdn.analyticsvidhya.com\\\/wp-content\\\/uploads\\\/2026\\\/08\\\/Ahh-here-we-go-again.webp\",\"keywords\":[\"Agents\",\"Deploying\",\"Governing\",\"Semantic\",\"Snowflake\",\"Views\"],\"articleSection\":[\"Data Science & MLOps\"],\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\\\/\\\/futurenews24.com\\\/index.php\\\/2026\\\/08\\\/08\\\/snowflake-ai-agents-semantic-governance\\\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/futurenews24.com\\\/index.php\\\/2026\\\/08\\\/08\\\/snowflake-ai-agents-semantic-governance\\\/\",\"url\":\"https:\\\/\\\/futurenews24.com\\\/index.php\\\/2026\\\/08\\\/08\\\/snowflake-ai-agents-semantic-governance\\\/\",\"name\":\"Governing AI Brokers: Deploying Semantic Views on Snowflake - Future News 24\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/futurenews24.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/futurenews24.com\\\/index.php\\\/2026\\\/08\\\/08\\\/snowflake-ai-agents-semantic-governance\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/futurenews24.com\\\/index.php\\\/2026\\\/08\\\/08\\\/snowflake-ai-agents-semantic-governance\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/cdn.analyticsvidhya.com\\\/wp-content\\\/uploads\\\/2026\\\/08\\\/Ahh-here-we-go-again.webp\",\"datePublished\":\"2026-08-08T13:27:00+00:00\",\"dateModified\":\"2026-08-09T08:59:04+00:00\",\"description\":\"A practical framework for generating, governing, and deploying certified semantic views on Snowflake using Data Build Tool.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/futurenews24.com\\\/index.php\\\/2026\\\/08\\\/08\\\/snowflake-ai-agents-semantic-governance\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/futurenews24.com\\\/index.php\\\/2026\\\/08\\\/08\\\/snowflake-ai-agents-semantic-governance\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/futurenews24.com\\\/index.php\\\/2026\\\/08\\\/08\\\/snowflake-ai-agents-semantic-governance\\\/#primaryimage\",\"url\":\"https:\\\/\\\/cdn.analyticsvidhya.com\\\/wp-content\\\/uploads\\\/2026\\\/08\\\/Ahh-here-we-go-again.webp\",\"contentUrl\":\"https:\\\/\\\/cdn.analyticsvidhya.com\\\/wp-content\\\/uploads\\\/2026\\\/08\\\/Ahh-here-we-go-again.webp\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/futurenews24.com\\\/index.php\\\/2026\\\/08\\\/08\\\/snowflake-ai-agents-semantic-governance\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/futurenews24.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Governing AI Brokers: Deploying Semantic Views on Snowflake\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/futurenews24.com\\\/#website\",\"url\":\"https:\\\/\\\/futurenews24.com\\\/\",\"name\":\"Future News 24\",\"description\":\"The Smart Hub for AI and Next-Gen Innovation\",\"publisher\":{\"@id\":\"https:\\\/\\\/futurenews24.com\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/futurenews24.com\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/futurenews24.com\\\/#organization\",\"name\":\"Future News 24\",\"url\":\"https:\\\/\\\/futurenews24.com\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/futurenews24.com\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/futurenews24.com\\\/wp-content\\\/uploads\\\/2026\\\/06\\\/fn24-favicon.png\",\"contentUrl\":\"https:\\\/\\\/futurenews24.com\\\/wp-content\\\/uploads\\\/2026\\\/06\\\/fn24-favicon.png\",\"width\":250,\"height\":250,\"caption\":\"Future News 24\"},\"image\":{\"@id\":\"https:\\\/\\\/futurenews24.com\\\/#\\\/schema\\\/logo\\\/image\\\/\"}},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/futurenews24.com\\\/#\\\/schema\\\/person\\\/cecad1bde21cfc357cf70128144d6c83\",\"name\":\"Future News 24\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/d57f07142d73cb5503ab2446ea7bc9ef3d0a5ba378d64a6157692311e42bf097?s=96&d=mm&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/d57f07142d73cb5503ab2446ea7bc9ef3d0a5ba378d64a6157692311e42bf097?s=96&d=mm&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/d57f07142d73cb5503ab2446ea7bc9ef3d0a5ba378d64a6157692311e42bf097?s=96&d=mm&r=g\",\"caption\":\"Future News 24\"},\"sameAs\":[\"https:\\\/\\\/futurenews24.com\"],\"url\":\"https:\\\/\\\/futurenews24.com\\\/index.php\\\/author\\\/mridulpahuja20\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Governing AI Brokers: Deploying Semantic Views on Snowflake - Future News 24","description":"A practical framework for generating, governing, and deploying certified semantic views on Snowflake using Data Build Tool.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/futurenews24.com\/index.php\/2026\/08\/08\/snowflake-ai-agents-semantic-governance\/","og_locale":"en_US","og_type":"article","og_title":"Governing AI Brokers: Deploying Semantic Views on Snowflake - Future News 24","og_description":"A practical framework for generating, governing, and deploying certified semantic views on Snowflake using Data Build Tool.","og_url":"https:\/\/futurenews24.com\/index.php\/2026\/08\/08\/snowflake-ai-agents-semantic-governance\/","og_site_name":"Future News 24","article_published_time":"2026-08-08T13:27:00+00:00","article_modified_time":"2026-08-09T08:59:04+00:00","og_image":[{"url":"https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2026\/08\/Ahh-here-we-go-again.webp","type":"","width":"","height":""}],"author":"Future News 24","twitter_card":"summary_large_image","twitter_image":"https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2026\/08\/Ahh-here-we-go-again.webp","twitter_misc":{"Written by":"Future News 24","Est. reading time":"19 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/futurenews24.com\/index.php\/2026\/08\/08\/snowflake-ai-agents-semantic-governance\/#article","isPartOf":{"@id":"https:\/\/futurenews24.com\/index.php\/2026\/08\/08\/snowflake-ai-agents-semantic-governance\/"},"author":{"name":"Future News 24","@id":"https:\/\/futurenews24.com\/#\/schema\/person\/cecad1bde21cfc357cf70128144d6c83"},"headline":"Governing AI Brokers: Deploying Semantic Views on Snowflake","datePublished":"2026-08-08T13:27:00+00:00","dateModified":"2026-08-09T08:59:04+00:00","mainEntityOfPage":{"@id":"https:\/\/futurenews24.com\/index.php\/2026\/08\/08\/snowflake-ai-agents-semantic-governance\/"},"wordCount":3741,"commentCount":0,"publisher":{"@id":"https:\/\/futurenews24.com\/#organization"},"image":{"@id":"https:\/\/futurenews24.com\/index.php\/2026\/08\/08\/snowflake-ai-agents-semantic-governance\/#primaryimage"},"thumbnailUrl":"https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2026\/08\/Ahh-here-we-go-again.webp","keywords":["Agents","Deploying","Governing","Semantic","Snowflake","Views"],"articleSection":["Data Science & MLOps"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/futurenews24.com\/index.php\/2026\/08\/08\/snowflake-ai-agents-semantic-governance\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/futurenews24.com\/index.php\/2026\/08\/08\/snowflake-ai-agents-semantic-governance\/","url":"https:\/\/futurenews24.com\/index.php\/2026\/08\/08\/snowflake-ai-agents-semantic-governance\/","name":"Governing AI Brokers: Deploying Semantic Views on Snowflake - Future News 24","isPartOf":{"@id":"https:\/\/futurenews24.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/futurenews24.com\/index.php\/2026\/08\/08\/snowflake-ai-agents-semantic-governance\/#primaryimage"},"image":{"@id":"https:\/\/futurenews24.com\/index.php\/2026\/08\/08\/snowflake-ai-agents-semantic-governance\/#primaryimage"},"thumbnailUrl":"https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2026\/08\/Ahh-here-we-go-again.webp","datePublished":"2026-08-08T13:27:00+00:00","dateModified":"2026-08-09T08:59:04+00:00","description":"A practical framework for generating, governing, and deploying certified semantic views on Snowflake using Data Build Tool.","breadcrumb":{"@id":"https:\/\/futurenews24.com\/index.php\/2026\/08\/08\/snowflake-ai-agents-semantic-governance\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/futurenews24.com\/index.php\/2026\/08\/08\/snowflake-ai-agents-semantic-governance\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/futurenews24.com\/index.php\/2026\/08\/08\/snowflake-ai-agents-semantic-governance\/#primaryimage","url":"https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2026\/08\/Ahh-here-we-go-again.webp","contentUrl":"https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2026\/08\/Ahh-here-we-go-again.webp"},{"@type":"BreadcrumbList","@id":"https:\/\/futurenews24.com\/index.php\/2026\/08\/08\/snowflake-ai-agents-semantic-governance\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/futurenews24.com\/"},{"@type":"ListItem","position":2,"name":"Governing AI Brokers: Deploying Semantic Views on Snowflake"}]},{"@type":"WebSite","@id":"https:\/\/futurenews24.com\/#website","url":"https:\/\/futurenews24.com\/","name":"Future News 24","description":"The Smart Hub for AI and Next-Gen Innovation","publisher":{"@id":"https:\/\/futurenews24.com\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/futurenews24.com\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/futurenews24.com\/#organization","name":"Future News 24","url":"https:\/\/futurenews24.com\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/futurenews24.com\/#\/schema\/logo\/image\/","url":"https:\/\/futurenews24.com\/wp-content\/uploads\/2026\/06\/fn24-favicon.png","contentUrl":"https:\/\/futurenews24.com\/wp-content\/uploads\/2026\/06\/fn24-favicon.png","width":250,"height":250,"caption":"Future News 24"},"image":{"@id":"https:\/\/futurenews24.com\/#\/schema\/logo\/image\/"}},{"@type":"Person","@id":"https:\/\/futurenews24.com\/#\/schema\/person\/cecad1bde21cfc357cf70128144d6c83","name":"Future News 24","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/secure.gravatar.com\/avatar\/d57f07142d73cb5503ab2446ea7bc9ef3d0a5ba378d64a6157692311e42bf097?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/d57f07142d73cb5503ab2446ea7bc9ef3d0a5ba378d64a6157692311e42bf097?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/d57f07142d73cb5503ab2446ea7bc9ef3d0a5ba378d64a6157692311e42bf097?s=96&d=mm&r=g","caption":"Future News 24"},"sameAs":["https:\/\/futurenews24.com"],"url":"https:\/\/futurenews24.com\/index.php\/author\/mridulpahuja20\/"}]}},"_links":{"self":[{"href":"https:\/\/futurenews24.com\/index.php\/wp-json\/wp\/v2\/posts\/3491","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/futurenews24.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/futurenews24.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/futurenews24.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/futurenews24.com\/index.php\/wp-json\/wp\/v2\/comments?post=3491"}],"version-history":[{"count":1,"href":"https:\/\/futurenews24.com\/index.php\/wp-json\/wp\/v2\/posts\/3491\/revisions"}],"predecessor-version":[{"id":3492,"href":"https:\/\/futurenews24.com\/index.php\/wp-json\/wp\/v2\/posts\/3491\/revisions\/3492"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/futurenews24.com\/index.php\/wp-json\/wp\/v2\/media\/3493"}],"wp:attachment":[{"href":"https:\/\/futurenews24.com\/index.php\/wp-json\/wp\/v2\/media?parent=3491"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/futurenews24.com\/index.php\/wp-json\/wp\/v2\/categories?post=3491"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/futurenews24.com\/index.php\/wp-json\/wp\/v2\/tags?post=3491"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}